[ { "id": 339126766, "name": "IkomiaApi", "full_name": "Ikomia-dev/IkomiaApi", "url": "https://github.com/Ikomia-dev/IkomiaApi", "description": "Deploy Computer Vision solutions with a few lines of code.", "stars": 244, "forks": 13, "watches": 244, "language": "Python", "license": "Apache License 2.0", "topics": [ "computer-vision", "computer-vision-ai", "computer-vision-algorithms", "computer-vision-opencv", "computer-vision-tools", "computervision", "deep-learning", "detectron2", "human-pose-estimation", "image-processing", "machine-learning", "object-detection", "opencv", "openmmlab", "pose-estimation", "python", "pytorch", "tensorflow", "yolo" ], "owner": { "login": "Ikomia-dev", "avatar_url": "https://avatars.githubusercontent.com/u/53618017?v=4", "html_url": "https://github.com/Ikomia-dev" } }, { "id": 516834101, "name": "morl-baselines", "full_name": "LucasAlegre/morl-baselines", "url": "https://github.com/LucasAlegre/morl-baselines", "description": "Multi-Objective Reinforcement Learning algorithms implementations.", "stars": 526, "forks": 104, "watches": 526, "language": "Python", "license": "MIT License", "topics": [ "gym", "gymnasium", "mo-gymnasium", "morl", "multi-objective", "multi-objective-rl", "pytorch", "reinforcement-learning", "rl", "rl-algorithms" ], "owner": { "login": "LucasAlegre", "avatar_url": "https://avatars.githubusercontent.com/u/20215161?v=4", "html_url": "https://github.com/LucasAlegre" } }, { "id": 233749704, "name": "leopard", "full_name": "Picovoice/leopard", "url": "https://github.com/Picovoice/leopard", "description": "On-device speech-to-text engine powered by deep learning ", "stars": 480, "forks": 29, "watches": 480, "language": "Python", "license": "Apache License 2.0", "topics": [ "asr", "automatic-speech-recognition", "on-device", "speech-recognition", "speech-to-text", "stt", "transcription", "voice-recognition", "voice-to-text" ], "owner": { "login": "Picovoice", "avatar_url": "https://avatars.githubusercontent.com/u/37164515?v=4", "html_url": "https://github.com/Picovoice" } }, { "id": 206714054, "name": "Chrome-Web-Speech-API", "full_name": "bensonruan/Chrome-Web-Speech-API", "url": "https://github.com/bensonruan/Chrome-Web-Speech-API", "description": "Chrome Web Speech API", "stars": 117, "forks": 38, "watches": 117, "language": "JavaScript", "license": "MIT License", "topics": [ "artificial-intelligence", "chrome", "javascript", "machine-learning", "speech-recognition", "speech-to-text", "voice-recognition", "voice-to-text", "web-speech-api" ], "owner": { "login": "bensonruan", "avatar_url": "https://avatars.githubusercontent.com/u/36299151?v=4", "html_url": "https://github.com/bensonruan" } }, { "id": 1160039722, "name": "Aegis", "full_name": "antropos17/Aegis", "url": "https://github.com/antropos17/Aegis", "description": "Open-source EDR for AI agents. Monitor processes, files, network, and behavior of autonomous AI agents.", "stars": 131, "forks": 19, "watches": 131, "language": "JavaScript", "license": "MIT License", "topics": [ "ai", "ai-agents", "ai-safety", "ai-security", "cybersecurity", "desktop-app", "developer-tools", "edr", "electron", "monitoring", "open-source", "privacy", "security", "svelte", "typescript" ], "owner": { "login": "antropos17", "avatar_url": "https://avatars.githubusercontent.com/u/180439056?v=4", "html_url": "https://github.com/antropos17" } }, { "id": 1150569470, "name": "openclaw-skills-security", "full_name": "UseAI-pro/openclaw-skills-security", "url": "https://github.com/UseAI-pro/openclaw-skills-security", "description": "Curated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, supply chain attacks, credential leaks. Works with Codex CLI, Claude Code, any LLM.", "stars": 58, "forks": 10, "watches": 58, "language": "Python", "license": "MIT License", "topics": [ "ai-safety", "ai-security", "llm-security", "malware-detection", "moltbot", "moltbot-skills", "openclaw", "openclaw-security", "openclaw-setup", "openclaw-skills", "prompt-injection", "security-audit", "skill-marketplace" ], "owner": { "login": "UseAI-pro", "avatar_url": "https://avatars.githubusercontent.com/u/208442297?v=4", "html_url": "https://github.com/UseAI-pro" } }, { "id": 1104401168, "name": "RLLaVA", "full_name": "TinyLoopX/RLLaVA", "url": "https://github.com/TinyLoopX/RLLaVA", "description": "RLLaVA is a user-friendly framework for multi-modal RL research and optimized for resource-constrained teams.", "stars": 58, "forks": 6, "watches": 58, "language": "Python", "license": "Apache License 2.0", "topics": [ "agentic", "llava", "modular", "multimodal", "reinforcement-learning", "rl", "vlm" ], "owner": { "login": "TinyLoopX", "avatar_url": "https://avatars.githubusercontent.com/u/238719059?v=4", "html_url": "https://github.com/TinyLoopX" } }, { "id": 218935815, "name": "PaddlePaddle-DeepSpeech", "full_name": "yeyupiaoling/PaddlePaddle-DeepSpeech", "url": "https://github.com/yeyupiaoling/PaddlePaddle-DeepSpeech", "description": "基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。", "stars": 761, "forks": 147, "watches": 761, "language": "Python", "license": "Apache License 2.0", "topics": [ "asr", "chinese", "deep-learning", "deepspeech", "deepspeech2", "docker", "nvidia-docker", "paddlepaddle", "speech-recognition", "speech-to-text" ], "owner": { "login": "yeyupiaoling", "avatar_url": "https://avatars.githubusercontent.com/u/26297768?v=4", "html_url": "https://github.com/yeyupiaoling" } }, { "id": 65221460, "name": "Naomi", "full_name": "NaomiProject/Naomi", "url": "https://github.com/NaomiProject/Naomi", "description": "The Naomi Project is an open source, technology agnostic platform for developing always-on, voice-controlled applications!", "stars": 296, "forks": 60, "watches": 296, "language": "Python", "license": "MIT License", "topics": [ "assistant", "hacktoberfest", "home-automation", "iot", "jarvis", "jasper", "linux", "naomi", "personal-assistant", "raspberry-pi", "speech-recognition", "speech-synthesis", "speech-to-text", "text-to-speech", "vocal-assistant", "voice" ], "owner": { "login": "NaomiProject", "avatar_url": "https://avatars.githubusercontent.com/u/20894415?v=4", "html_url": "https://github.com/NaomiProject" } }, { "id": 139062293, "name": "tensorflow_object_counting_api", "full_name": "ahmetozlu/tensorflow_object_counting_api", "url": "https://github.com/ahmetozlu/tensorflow_object_counting_api", "description": "🚀 The TensorFlow Object Counting API is an open source framework built on top of TensorFlow and Keras that makes it easy to develop object counting systems!", "stars": 1332, "forks": 543, "watches": 1332, "language": "Python", "license": "MIT License", "topics": [ "computer-vision", "data-science", "deep-learning", "deep-neural-networks", "image-processing", "machine-learning", "object-counting", "object-counting-api", "object-detection", "object-detection-api", "object-detection-label", "object-detection-pipelines", "opencv", "pedestrian-counting", "shelf-management", "shelf-navigation", "tensorflow", "tensorflow-api", "tensorflow-object-detection-api", "vehicle-counting" ], "owner": { "login": "ahmetozlu", "avatar_url": "https://avatars.githubusercontent.com/u/22610163?v=4", "html_url": "https://github.com/ahmetozlu" } }, { "id": 266422105, "name": "f1tenth-RL", "full_name": "MichaelBosello/f1tenth-RL", "url": "https://github.com/MichaelBosello/f1tenth-RL", "description": "Dqn with lidar data on f1tenth real car or f1tenth simulator", "stars": 61, "forks": 14, "watches": 61, "language": "Python", "license": "Apache License 2.0", "topics": [ "deep-reinforcement-learning", "dqn", "f110", "f1tenth", "lidar", "reinforcement-learning", "rl", "ros", "ros-melodic", "tensorflow", "tensorflow2" ], "owner": { "login": "MichaelBosello", "avatar_url": "https://avatars.githubusercontent.com/u/14661511?v=4", "html_url": "https://github.com/MichaelBosello" } }, { "id": 259710503, "name": "speechbrain", "full_name": "speechbrain/speechbrain", "url": "https://github.com/speechbrain/speechbrain", "description": "A PyTorch-based Speech Toolkit", "stars": 11576, "forks": 1690, "watches": 11576, "language": "Python", "license": "Apache License 2.0", "topics": [ "asr", "audio", "audio-processing", "deep-learning", "huggingface", "language-model", "pytorch", "speaker-diarization", "speaker-recognition", "speaker-verification", "speech-enhancement", "speech-processing", "speech-recognition", "speech-separation", "speech-to-text", "speech-toolkit", "speechrecognition", "spoken-language-understanding", "transformers", "voice-recognition" ], "owner": { "login": "speechbrain", "avatar_url": "https://avatars.githubusercontent.com/u/54749030?v=4", "html_url": "https://github.com/speechbrain" } }, { "id": 1079394550, "name": "TheWhisper", "full_name": "TheStageAI/TheWhisper", "url": "https://github.com/TheStageAI/TheWhisper", "description": "Optimized Whisper models for streaming and on-device use", "stars": 887, "forks": 56, "watches": 887, "language": "Python", "license": "MIT License", "topics": [ "apple-silicon", "coreml", "mlx", "nvidia-gpu", "on-device-ai", "real-time", "speech-recognition", "speech-to-text", "streaming", "transcription", "translation", "voice", "voice-ai" ], "owner": { "login": "TheStageAI", "avatar_url": "https://avatars.githubusercontent.com/u/121886129?v=4", "html_url": "https://github.com/TheStageAI" } }, { "id": 620611450, "name": "SwiftWhisper", "full_name": "exPHAT/SwiftWhisper", "url": "https://github.com/exPHAT/SwiftWhisper", "description": "🎤 The easiest way to transcribe audio in Swift", "stars": 779, "forks": 104, "watches": 779, "language": "Swift", "license": "MIT License", "topics": [ "ios", "macos", "openai", "speech-recognition", "speech-to-text", "swift", "transcription", "whisper", "whisper-cpp" ], "owner": { "login": "exPHAT", "avatar_url": "https://avatars.githubusercontent.com/u/7348226?v=4", "html_url": "https://github.com/exPHAT" } }, { "id": 578408073, "name": "Omniverse-Virtual-Assisstant", "full_name": "zslrmhb/Omniverse-Virtual-Assisstant", "url": "https://github.com/zslrmhb/Omniverse-Virtual-Assisstant", "description": "Audio2Face Avatar with Riva SDK functionality", "stars": 74, "forks": 18, "watches": 74, "language": "Python", "license": "MIT License", "topics": [ "animation", "audio2face", "google-cloud", "nvidia", "omniverse", "python", "speech-recognition", "speech-to-text", "text-to-speech", "virtual-assistant" ], "owner": { "login": "zslrmhb", "avatar_url": "https://avatars.githubusercontent.com/u/59853402?v=4", "html_url": "https://github.com/zslrmhb" } }, { "id": 1190450534, "name": "claudini", "full_name": "romovpa/claudini", "url": "https://github.com/romovpa/claudini", "description": "Autoresearch for LLM adversarial attacks", "stars": 218, "forks": 24, "watches": 218, "language": "Python", "license": "Apache License 2.0", "topics": [ "ai-safety", "ai-security", "autoresearch", "jailbreak", "prompt-injection" ], "owner": { "login": "romovpa", "avatar_url": "https://avatars.githubusercontent.com/u/152387?v=4", "html_url": "https://github.com/romovpa" } }, { "id": 902628968, "name": "shekar", "full_name": "amirivojdan/shekar", "url": "https://github.com/amirivojdan/shekar", "description": "Simplifying Persian NLP for Modern Applications", "stars": 66, "forks": 4, "watches": 66, "language": "Python", "license": "MIT License", "topics": [ "embeddings", "keyword-extraction", "lemmatization", "morphology", "named-entity-recognition", "natural-language-processing", "ner", "nlp", "normalization", "offensive-language-detection", "part-of-speech-tagging", "persian", "persian-nlp", "pos", "sentiment-analysis", "spell-checker", "text-processing", "wordcloud" ], "owner": { "login": "amirivojdan", "avatar_url": "https://avatars.githubusercontent.com/u/5096712?v=4", "html_url": "https://github.com/amirivojdan" } }, { "id": 571613891, "name": "supervision", "full_name": "roboflow/supervision", "url": "https://github.com/roboflow/supervision", "description": "We write your reusable computer vision tools. 💜", "stars": 39752, "forks": 3573, "watches": 39752, "language": "Python", "license": "MIT License", "topics": [ "classification", "coco", "computer-vision", "deep-learning", "hacktoberfest", "image-processing", "instance-segmentation", "low-code", "machine-learning", "metrics", "object-detection", "oriented-bounding-box", "pascal-voc", "python", "pytorch", "tensorflow", "tracking", "video-processing", "yolo" ], "owner": { "login": "roboflow", "avatar_url": "https://avatars.githubusercontent.com/u/53104118?v=4", "html_url": "https://github.com/roboflow" } }, { "id": 481566311, "name": "gym-simplegrid", "full_name": "damat-le/gym-simplegrid", "url": "https://github.com/damat-le/gym-simplegrid", "description": "Simple Grid Environment for Gymnasium", "stars": 66, "forks": 15, "watches": 66, "language": "Python", "license": "Apache License 2.0", "topics": [ "environment", "farama-foundation", "grid", "grid-environment", "gridworld", "gridworld-environment", "gym", "gym-environment", "gymnasium", "gymnasium-environment", "openai", "openai-gym", "reinforcement-learning", "reinforcement-learning-environments", "rl" ], "owner": { "login": "damat-le", "avatar_url": "https://avatars.githubusercontent.com/u/76538587?v=4", "html_url": "https://github.com/damat-le" } }, { "id": 142219189, "name": "lingvo", "full_name": "tensorflow/lingvo", "url": "https://github.com/tensorflow/lingvo", "description": "Lingvo", "stars": 2863, "forks": 449, "watches": 2863, "language": "Python", "license": "Apache License 2.0", "topics": [ "asr", "distributed", "gpu-computing", "language-model", "lm", "machine-translation", "mnist", "nlp", "research", "seq2seq", "speech", "speech-recognition", "speech-synthesis", "speech-to-text", "tensorflow", "translation", "tts" ], "owner": { "login": "tensorflow", "avatar_url": "https://avatars.githubusercontent.com/u/15658638?v=4", "html_url": "https://github.com/tensorflow" } }, { "id": 334862293, "name": "viet-asr", "full_name": "dangvansam/viet-asr", "url": "https://github.com/dangvansam/viet-asr", "description": "VietASR - Vietnamese Automatic Speech Recognition", "stars": 169, "forks": 58, "watches": 169, "language": "Python", "license": "Apache License 2.0", "topics": [ "asr", "automatic-speech-recognition", "ctc-decode", "ctc-loss", "dangvansam", "speech-recognition", "speech-to-text", "stt", "viet-tts", "vietasr", "vietnamese", "vietnamese-language", "vietnamese-nlp", "vietnamese-speech-recognition", "viettts" ], "owner": { "login": "dangvansam", "avatar_url": "https://avatars.githubusercontent.com/u/45785880?v=4", "html_url": "https://github.com/dangvansam" } }, { "id": 765056095, "name": "uttertype", "full_name": "dhruvyad/uttertype", "url": "https://github.com/dhruvyad/uttertype", "description": "Short code for dictation using OpenAI Whisper for transcription.", "stars": 117, "forks": 15, "watches": 117, "language": "Python", "license": "MIT License", "topics": [ "dictation", "openai", "openai-whisper", "speech-recognition", "speech-to-text", "transcription" ], "owner": { "login": "dhruvyad", "avatar_url": "https://avatars.githubusercontent.com/u/19387874?v=4", "html_url": "https://github.com/dhruvyad" } }, { "id": 189556185, "name": "teanaps", "full_name": "fingeredman/teanaps", "url": "https://github.com/fingeredman/teanaps", "description": "자연어 처리와 텍스트 분석을 위한 오픈소스 파이썬 라이브러리 입니다.", "stars": 108, "forks": 14, "watches": 108, "language": "Jupyter Notebook", "license": "Apache License 2.0", "topics": [ "classification", "clustering", "data-mining", "google-colabotory", "korean-nlp", "korean-text-processing", "morphological-analysis", "named-entity-recognition", "natural-language-processing", "nlp", "python", "python-package", "summarization", "syntax-analysis", "teanaps", "text-mining", "text-processing", "topic-modeling" ], "owner": { "login": "fingeredman", "avatar_url": "https://avatars.githubusercontent.com/u/6668535?v=4", "html_url": "https://github.com/fingeredman" } }, { "id": 237978237, "name": "perke", "full_name": "alirezatheh/perke", "url": "https://github.com/alirezatheh/perke", "description": "A keyphrase extractor for Persian ", "stars": 73, "forks": 8, "watches": 73, "language": "Python", "license": "MIT License", "topics": [ "data-mining", "data-processing", "information-retrieval", "keyphrase", "keyphrase-extraction", "keyphrase-extractor", "keyword", "keyword-extraction", "keyword-extractor", "machine-learning", "ml", "natural-language-processing", "nlp", "persian", "persian-language", "python", "text-mining", "text-processing", "unsupervised-learning" ], "owner": { "login": "alirezatheh", "avatar_url": "https://avatars.githubusercontent.com/u/17493246?v=4", "html_url": "https://github.com/alirezatheh" } }, { "id": 259793931, "name": "drq", "full_name": "denisyarats/drq", "url": "https://github.com/denisyarats/drq", "description": "DrQ: Data regularized Q", "stars": 422, "forks": 54, "watches": 422, "language": "Jupyter Notebook", "license": "MIT License", "topics": [ "actor-critic", "control", "data-augmentation", "deep-learning", "deep-reinforcement-learning", "dm-control", "drq", "gym", "model-free", "mujoco", "off-policy", "pixel", "python", "pytorch", "reinforcement-learning", "rl", "sac", "soft-actor-crit" ], "owner": { "login": "denisyarats", "avatar_url": "https://avatars.githubusercontent.com/u/15959920?v=4", "html_url": "https://github.com/denisyarats" } }, { "id": 933734981, "name": "Awesome-Multimodal-Reasoning", "full_name": "The-Martyr/Awesome-Multimodal-Reasoning", "url": "https://github.com/The-Martyr/Awesome-Multimodal-Reasoning", "description": "Latest Advances on (RL based) Multimodal Reasoning and Generation in Multimodal LLMs", "stars": 64, "forks": 4, "watches": 64, "language": "", "license": "MIT License", "topics": [ "chain-of-thought", "cot", "image-generation", "image-reasoning", "image-understanding", "large-language-models", "llm", "lvlm", "mllm", "multimodal-learning", "multimodal-reasoning", "o1", "r1", "reinforcement-learning", "rl", "video-generation", "video-reasoning", "video-understanding" ], "owner": { "login": "The-Martyr", "avatar_url": "https://avatars.githubusercontent.com/u/115147700?v=4", "html_url": "https://github.com/The-Martyr" } }, { "id": 541269386, "name": "whisper.cpp", "full_name": "ggml-org/whisper.cpp", "url": "https://github.com/ggml-org/whisper.cpp", "description": "Port of OpenAI's Whisper model in C/C++", "stars": 50281, "forks": 5592, "watches": 50281, "language": "C++", "license": "MIT License", "topics": [ "inference", "openai", "speech-recognition", "speech-to-text", "transformer", "whisper" ], "owner": { "login": "ggml-org", "avatar_url": "https://avatars.githubusercontent.com/u/134263123?v=4", "html_url": "https://github.com/ggml-org" } }, { "id": 809877633, "name": "june", "full_name": "mezbaul-h/june", "url": "https://github.com/mezbaul-h/june", "description": "Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit", "stars": 784, "forks": 53, "watches": 784, "language": "Python", "license": "MIT License", "topics": [ "ai", "assistant-chat-bots", "chatbot", "chatbots", "cli-app", "command-line-tool", "coqui-tts", "huggingface", "large-language-models", "llm", "python", "speech-recognition", "speech-to-text", "text-to-speech", "whisper" ], "owner": { "login": "mezbaul-h", "avatar_url": "https://avatars.githubusercontent.com/u/11481344?v=4", "html_url": "https://github.com/mezbaul-h" } }, { "id": 546926571, "name": "LiveWhisper", "full_name": "Nikorasu/LiveWhisper", "url": "https://github.com/Nikorasu/LiveWhisper", "description": "A nearly-live implementation of OpenAI's Whisper, using sounddevice. Requires existing Whisper install.", "stars": 360, "forks": 49, "watches": 360, "language": "Python", "license": "MIT License", "topics": [ "ai", "assistant", "chatbot", "dictation", "numpy", "openai", "openai-whisper", "python", "sounddevice", "speech-recognition", "speech-to-text", "terminal", "text-to-speech", "transcription", "translation", "tts", "voice", "voice-assistant", "voice-recognition", "whisper" ], "owner": { "login": "Nikorasu", "avatar_url": "https://avatars.githubusercontent.com/u/1338231?v=4", "html_url": "https://github.com/Nikorasu" } }, { "id": 129260609, "name": "textvec", "full_name": "textvec/textvec", "url": "https://github.com/textvec/textvec", "description": "Text vectorization tool to outperform TFIDF for classification tasks", "stars": 197, "forks": 27, "watches": 197, "language": "Python", "license": "MIT License", "topics": [ "machine-learning", "natural-language-processing", "nlp", "python", "text-analysis", "text-classification", "text-processing", "tf-idf" ], "owner": { "login": "textvec", "avatar_url": "https://avatars.githubusercontent.com/u/56171200?v=4", "html_url": "https://github.com/textvec" } }, { "id": 199133070, "name": "python-gatenlp", "full_name": "GateNLP/python-gatenlp", "url": "https://github.com/GateNLP/python-gatenlp", "description": "Python text processing, pattern matching, and NLP framework", "stars": 67, "forks": 8, "watches": 67, "language": "Jupyter Notebook", "license": "Apache License 2.0", "topics": [ "annotations", "gatenlp", "language-engineering", "natural-language-processing", "nlp", "pattern-matching", "python", "python-gatenlp", "python3", "text-processing" ], "owner": { "login": "GateNLP", "avatar_url": "https://avatars.githubusercontent.com/u/14233746?v=4", "html_url": "https://github.com/GateNLP" } }, { "id": 1176073451, "name": "rlix", "full_name": "rlops/rlix", "url": "https://github.com/rlops/rlix", "description": "Run more RL experiments. Wait less for GPUs.", "stars": 286, "forks": 17, "watches": 286, "language": "Python", "license": "Apache License 2.0", "topics": [ "agentic-rl", "gpu-scheduling", "llm-training", "lora", "ml-systems", "mlops", "reinforcement-learning", "rl", "tinker" ], "owner": { "login": "rlops", "avatar_url": "https://avatars.githubusercontent.com/u/262526519?v=4", "html_url": "https://github.com/rlops" } }, { "id": 240232771, "name": "TensorFlowASR", "full_name": "TensorSpeech/TensorFlowASR", "url": "https://github.com/TensorSpeech/TensorFlowASR", "description": ":zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords", "stars": 1008, "forks": 240, "watches": 1008, "language": "Python", "license": "Apache License 2.0", "topics": [ "automatic-speech-recognition", "conformer", "contextnet", "ctc", "deepspeech2", "end2end", "jasper", "rnn-transducer", "speech-recognition", "speech-to-text", "streaming-transducer", "subword-speech-recognition", "tensorflow", "tensorflow2", "tflite", "tflite-convertion", "tflite-model" ], "owner": { "login": "TensorSpeech", "avatar_url": "https://avatars.githubusercontent.com/u/67569298?v=4", "html_url": "https://github.com/TensorSpeech" } }, { "id": 587900919, "name": "VocalForge", "full_name": "rioharper/VocalForge", "url": "https://github.com/rioharper/VocalForge", "description": "Your one-stop solution for voice dataset creation", "stars": 130, "forks": 24, "watches": 130, "language": "Python", "license": "MIT License", "topics": [ "artificial-intelligence", "audio", "audio-processing", "dataset", "dataset-generation", "python", "speech-recognition", "speech-to-text", "toolkit" ], "owner": { "login": "rioharper", "avatar_url": "https://avatars.githubusercontent.com/u/50555644?v=4", "html_url": "https://github.com/rioharper" } }, { "id": 590111284, "name": "speech-recognition-experiments", "full_name": "fquirin/speech-recognition-experiments", "url": "https://github.com/fquirin/speech-recognition-experiments", "description": "Experiments to test different speech recognition systems for SEPIA Framework", "stars": 63, "forks": 5, "watches": 63, "language": "Python", "license": "MIT License", "topics": [ "asr", "coqui", "kaldi", "nemo", "nvidia", "raspberry-pi", "speech-recognition", "speech-to-text", "stt", "tensorflow", "vosk", "wake-word-detection", "whisper" ], "owner": { "login": "fquirin", "avatar_url": "https://avatars.githubusercontent.com/u/18550513?v=4", "html_url": "https://github.com/fquirin" } }, { "id": 780947181, "name": "advanced-computer-vision-engineer-roadmap-2024", "full_name": "farukalamai/advanced-computer-vision-engineer-roadmap-2024", "url": "https://github.com/farukalamai/advanced-computer-vision-engineer-roadmap-2024", "description": "A comprehensive roadmap that outlines the key steps and topics you should cover on your journey to becoming a Full Stack Computer Vision Engineer. ", "stars": 76, "forks": 8, "watches": 76, "language": "", "license": "MIT License", "topics": [ "computer-vision", "computer-vision-roadmap", "deep-learning", "image-classification", "image-processing", "image-segmentation", "machine-learning", "object-detection", "object-tracking", "opencv", "python", "pytorch", "segment-anything", "tensorflow" ], "owner": { "login": "farukalamai", "avatar_url": "https://avatars.githubusercontent.com/u/92469073?v=4", "html_url": "https://github.com/farukalamai" } }, { "id": 145385156, "name": "catalyst", "full_name": "catalyst-team/catalyst", "url": "https://github.com/catalyst-team/catalyst", "description": "Accelerated deep learning R\u0026D", "stars": 3378, "forks": 400, "watches": 3378, "language": "Python", "license": "Apache License 2.0", "topics": [ "computer-vision", "deep-learning", "distributed-computing", "image-classification", "image-processing", "image-segmentation", "information-retrieval", "infrastructure", "machine-learning", "metric-learning", "natural-language-processing", "object-detection", "python", "pytorch", "recommender-system", "reinforcement-learning", "reproducibility", "research", "text-classification", "text-segmentation" ], "owner": { "login": "catalyst-team", "avatar_url": "https://avatars.githubusercontent.com/u/46644555?v=4", "html_url": "https://github.com/catalyst-team" } }, { "id": 544445890, "name": "whisper-playground", "full_name": "saharmor/whisper-playground", "url": "https://github.com/saharmor/whisper-playground", "description": "Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/", "stars": 833, "forks": 145, "watches": 833, "language": "Python", "license": "MIT License", "topics": [ "machine-learning", "openai", "speech-recognition", "speech-to-text", "whisper" ], "owner": { "login": "saharmor", "avatar_url": "https://avatars.githubusercontent.com/u/6180201?v=4", "html_url": "https://github.com/saharmor" } }, { "id": 557780811, "name": "obsidian-transcription", "full_name": "djmango/obsidian-transcription", "url": "https://github.com/djmango/obsidian-transcription", "description": "Obsidian plugin to create high-quality transcriptions from markdown linked audio files", "stars": 222, "forks": 23, "watches": 222, "language": "TypeScript", "license": "MIT License", "topics": [ "asr", "ffmpeg", "obsidian-md", "obsidian-plugin", "speech-recognition", "speech-to-text", "transcription", "video" ], "owner": { "login": "djmango", "avatar_url": "https://avatars.githubusercontent.com/u/28496988?v=4", "html_url": "https://github.com/djmango" } }, { "id": 227466211, "name": "Cognitive-Services-Voice-Assistant", "full_name": "Azure-Samples/Cognitive-Services-Voice-Assistant", "url": "https://github.com/Azure-Samples/Cognitive-Services-Voice-Assistant", "description": "Welcome to the Microsoft Voice Assistant samples repository! Here you will find samples to help you get started building client application for your bot or Custom Command service. You will also be able to easily deploy a working Custom Command based Voice Assistant to your own Azure subscription", "stars": 122, "forks": 101, "watches": 122, "language": "C++", "license": "MIT License", "topics": [ "bot", "bot-framework", "botframework", "bots", "dotnet-core", "microsoft", "microsoft-bot-framework", "microsoft-cognitive-services", "sdk", "speech-recognition", "speech-to-text", "voice-assistant", "voice-commands", "voice-control", "voice-synthesis", "wpf" ], "owner": { "login": "Azure-Samples", "avatar_url": "https://avatars.githubusercontent.com/u/1844662?v=4", "html_url": "https://github.com/Azure-Samples" } }, { "id": 385371383, "name": "DiscordEarsBot", "full_name": "inevolin/DiscordEarsBot", "url": "https://github.com/inevolin/DiscordEarsBot", "description": "A speech-to-text framework and bot for Discord. Take control of your Discord server using speech and voice commands. Can also be useful for hearing impaired and deaf people.", "stars": 80, "forks": 355, "watches": 80, "language": "JavaScript", "license": "MIT License", "topics": [ "discord", "discord-bot", "discord-js", "hearing-aids", "hearing-impaired", "speech", "speech-processing", "speech-recognition", "speech-synthesis", "speech-to-text", "stt" ], "owner": { "login": "inevolin", "avatar_url": "https://avatars.githubusercontent.com/u/53948000?v=4", "html_url": "https://github.com/inevolin" } }, { "id": 250666668, "name": "UnityAndroidSpeechRecognizer", "full_name": "EricBatlle/UnityAndroidSpeechRecognizer", "url": "https://github.com/EricBatlle/UnityAndroidSpeechRecognizer", "description": "🗣️ Speech recognition on Unity and Android without the annoying google popup!", "stars": 71, "forks": 14, "watches": 71, "language": "ShaderLab", "license": "MIT License", "topics": [ "android", "android-plugin", "plugin", "speech-recognition", "speech-to-text", "unity", "unity3d" ], "owner": { "login": "EricBatlle", "avatar_url": "https://avatars.githubusercontent.com/u/15261880?v=4", "html_url": "https://github.com/EricBatlle" } }, { "id": 76385243, "name": "react-speech-recognition", "full_name": "JamesBrill/react-speech-recognition", "url": "https://github.com/JamesBrill/react-speech-recognition", "description": "💬Speech recognition for your React app", "stars": 839, "forks": 129, "watches": 839, "language": "JavaScript", "license": "MIT License", "topics": [ "react", "speech-recognition", "speech-to-text" ], "owner": { "login": "JamesBrill", "avatar_url": "https://avatars.githubusercontent.com/u/2140027?v=4", "html_url": "https://github.com/JamesBrill" } }, { "id": 619125144, "name": "whisper.unity", "full_name": "Macoron/whisper.unity", "url": "https://github.com/Macoron/whisper.unity", "description": "Running speech to text model (whisper.cpp) in Unity3d on your local machine.", "stars": 730, "forks": 176, "watches": 730, "language": "C#", "license": "MIT License", "topics": [ "asr", "openai", "speech-recognition", "speech-to-text", "stt", "unity3d", "whisper" ], "owner": { "login": "Macoron", "avatar_url": "https://avatars.githubusercontent.com/u/6161335?v=4", "html_url": "https://github.com/Macoron" } }, { "id": 586233849, "name": "ChatGPT-OpenAI-Smart-Speaker", "full_name": "Olney1/ChatGPT-OpenAI-Smart-Speaker", "url": "https://github.com/Olney1/ChatGPT-OpenAI-Smart-Speaker", "description": "This AI Smart Speaker uses speech recognition, TTS (text-to-speech), and STT (speech-to-text) to enable voice and vision-driven conversations, with additional web search capabilities via OpenAI and Langchain agents.", "stars": 313, "forks": 38, "watches": 313, "language": "Python", "license": "MIT License", "topics": [ "agents", "ai", "artificial-intelligence", "chatgpt", "gpt-4", "langchain", "langsmith", "openai", "smarthome", "smartspeaker", "speech-recognition", "speech-to-text", "tavily", "text-to-speech", "vision", "vision-and-language", "webscraping" ], "owner": { "login": "Olney1", "avatar_url": "https://avatars.githubusercontent.com/u/84375142?v=4", "html_url": "https://github.com/Olney1" } }, { "id": 563641298, "name": "sirius", "full_name": "UT-Austin-RPL/sirius", "url": "https://github.com/UT-Austin-RPL/sirius", "description": "Official codebase for Sirius: Robot Learning on the Job", "stars": 66, "forks": 6, "watches": 66, "language": "Python", "license": "MIT License", "topics": [ "behavioral-cloning", "human-in-the-loop", "human-robot-interaction", "imitation-learning", "pytorch", "robot-learning", "robotics" ], "owner": { "login": "UT-Austin-RPL", "avatar_url": "https://avatars.githubusercontent.com/u/61921293?v=4", "html_url": "https://github.com/UT-Austin-RPL" } }, { "id": 608634021, "name": "whisper-jax", "full_name": "sanchit-gandhi/whisper-jax", "url": "https://github.com/sanchit-gandhi/whisper-jax", "description": "JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.", "stars": 4683, "forks": 414, "watches": 4683, "language": "Jupyter Notebook", "license": "Apache License 2.0", "topics": [ "deep-learning", "jax", "speech-recognition", "speech-to-text", "whisper" ], "owner": { "login": "sanchit-gandhi", "avatar_url": "https://avatars.githubusercontent.com/u/93869735?v=4", "html_url": "https://github.com/sanchit-gandhi" } }, { "id": 640953950, "name": "FasterWhisper", "full_name": "AlexxIT/FasterWhisper", "url": "https://github.com/AlexxIT/FasterWhisper", "description": "Faster Whisper for Home Assistant - custom integration with a local Speech-to-Text engine", "stars": 98, "forks": 8, "watches": 98, "language": "Python", "license": "MIT License", "topics": [ "hacs", "home-assistant", "speech-recognition", "speech-to-text" ], "owner": { "login": "AlexxIT", "avatar_url": "https://avatars.githubusercontent.com/u/511909?v=4", "html_url": "https://github.com/AlexxIT" } }, { "id": 1105984666, "name": "voxtype", "full_name": "peteonrails/voxtype", "url": "https://github.com/peteonrails/voxtype", "description": "Voice-to-text with push-to-talk for Wayland compositors", "stars": 809, "forks": 52, "watches": 809, "language": "Rust", "license": "MIT License", "topics": [ "accessibility", "dictation", "gnome", "hyprland", "kde", "linux", "offline", "push-to-talk", "rust", "speech-recognition", "speech-to-text", "sway", "voice-to-text", "voice-typing", "wayland", "whisper", "whisper-cpp" ], "owner": { "login": "peteonrails", "avatar_url": "https://avatars.githubusercontent.com/u/9593?v=4", "html_url": "https://github.com/peteonrails" } }, { "id": 544273829, "name": "whisper-youtube", "full_name": "ArthurFDLR/whisper-youtube", "url": "https://github.com/ArthurFDLR/whisper-youtube", "description": "🔉 Youtube Videos Transcription with OpenAI's Whisper", "stars": 421, "forks": 115, "watches": 421, "language": "Jupyter Notebook", "license": "MIT License", "topics": [ "automatic-speech-recognition", "colab-notebook", "speech-recognition", "speech-to-text", "transformer", "whisper", "youtube" ], "owner": { "login": "ArthurFDLR", "avatar_url": "https://avatars.githubusercontent.com/u/41486077?v=4", "html_url": "https://github.com/ArthurFDLR" } }, { "id": 478243159, "name": "computing-Korean-STT-error-rates", "full_name": "hyeonsangjeon/computing-Korean-STT-error-rates", "url": "https://github.com/hyeonsangjeon/computing-Korean-STT-error-rates", "description": "STT 한글 문장 인식기 출력 스크립트의 외자 오류율(CER), 단어 오류율(WER)을 계산하는 Python 함수 패키지", "stars": 72, "forks": 11, "watches": 72, "language": "Python", "license": "MIT License", "topics": [ "amazon", "aws", "cer", "character-error-rate", "computing-error-rates", "evaluate", "evaluation-functions", "evaluation-metrics", "korean", "normalization", "openai", "speech-analysis", "speech-recognition", "speech-to-text", "test", "text-digitisation", "text-evaluation", "transcribe", "wer", "word-error-rate" ], "owner": { "login": "hyeonsangjeon", "avatar_url": "https://avatars.githubusercontent.com/u/25292366?v=4", "html_url": "https://github.com/hyeonsangjeon" } }, { "id": 1173456244, "name": "voiceblender", "full_name": "VoiceBlender/voiceblender", "url": "https://github.com/VoiceBlender/voiceblender", "description": "A programmable voice platform: SIP and WebRTC call control, multi-party mixing, recording, TTS/STT, and pluggable AI agents (ElevenLabs, VAPI, Pipecat, Deepgram) — all driven through a REST API, webhooks, and a WebSocket event stream", "stars": 71, "forks": 8, "watches": 71, "language": "Go", "license": "MIT License", "topics": [ "ai-agents", "api", "asr", "audio-processing", "codec", "moq", "opus-codec", "sip", "speech-recognition", "speech-to-text", "stt", "tts", "voice-agents", "voice-ai", "webrtc", "websockets" ], "owner": { "login": "VoiceBlender", "avatar_url": "https://avatars.githubusercontent.com/u/264701926?v=4", "html_url": "https://github.com/VoiceBlender" } }, { "id": 886612923, "name": "UltraEval-Audio", "full_name": "OpenBMB/UltraEval-Audio", "url": "https://github.com/OpenBMB/UltraEval-Audio", "description": "Your faithful, impartial partner for audio evaluation — know yourself, know your rivals. 真实评测，知己知彼。", "stars": 301, "forks": 24, "watches": 301, "language": "Python", "license": "Apache License 2.0", "topics": [ "evaluation", "speech-recognition", "speech-to-speech", "speech-to-text" ], "owner": { "login": "OpenBMB", "avatar_url": "https://avatars.githubusercontent.com/u/89920203?v=4", "html_url": "https://github.com/OpenBMB" } }, { "id": 762264662, "name": "speech-dataset-generator", "full_name": "davidmartinrius/speech-dataset-generator", "url": "https://github.com/davidmartinrius/speech-dataset-generator", "description": "🔊 Create labeled datasets, enhance audio quality, identify speakers, support diverse dataset types. 🎧👥📊 Advanced audio processing.", "stars": 260, "forks": 27, "watches": 260, "language": "Python", "license": "MIT License", "topics": [ "audio-analysis", "audio-processing", "dataset-generation", "speech-recognition", "speech-to-text", "text-to-speech" ], "owner": { "login": "davidmartinrius", "avatar_url": "https://avatars.githubusercontent.com/u/16558194?v=4", "html_url": "https://github.com/davidmartinrius" } }, { "id": 941344611, "name": "hud-python", "full_name": "hud-evals/hud-python", "url": "https://github.com/hud-evals/hud-python", "description": "OSS RL environment + evals toolkit", "stars": 256, "forks": 58, "watches": 256, "language": "Python", "license": "MIT License", "topics": [ "grpo", "llm", "llms", "lora", "qwen", "qwen3", "reinforcement-learning", "reinforcement-learning-environments", "rl" ], "owner": { "login": "hud-evals", "avatar_url": "https://avatars.githubusercontent.com/u/187057607?v=4", "html_url": "https://github.com/hud-evals" } }, { "id": 785061703, "name": "GenerativeRL", "full_name": "opendilab/GenerativeRL", "url": "https://github.com/opendilab/GenerativeRL", "description": "Python library for solving reinforcement learning (RL) problems using generative models (e.g. Diffusion Models).", "stars": 209, "forks": 12, "watches": 209, "language": "Python", "license": "Apache License 2.0", "topics": [ "diffusion", "diffusion-models", "diffusion-policy", "flow-model", "generative-ai", "generative-model", "offline-rl", "reinforcement-learning", "rl" ], "owner": { "login": "opendilab", "avatar_url": "https://avatars.githubusercontent.com/u/86840398?v=4", "html_url": "https://github.com/opendilab" } }, { "id": 569959091, "name": "FunASR", "full_name": "modelscope/FunASR", "url": "https://github.com/modelscope/FunASR", "description": "Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.", "stars": 16647, "forks": 1716, "watches": 16647, "language": "Python", "license": "MIT License", "topics": [ "asr", "audio", "chinese", "emotion-recognition", "mcp-server", "multilingual-asr", "openai-compatible-api", "paraformer", "punctuation", "pytorch", "real-time", "speaker-diarization", "speech-recognition", "speech-to-text", "streaming-asr", "transcription", "vad", "vllm", "voice-activity-detection", "whisper-alternative" ], "owner": { "login": "modelscope", "avatar_url": "https://avatars.githubusercontent.com/u/109945100?v=4", "html_url": "https://github.com/modelscope" } }, { "id": 634319313, "name": "awesome-russian-speech", "full_name": "alphacep/awesome-russian-speech", "url": "https://github.com/alphacep/awesome-russian-speech", "description": "Russian speech technology links", "stars": 397, "forks": 26, "watches": 397, "language": "", "license": "Apache License 2.0", "topics": [ "asr", "awesome-list", "g2p", "speech-recognition", "speech-synthesis", "speech-to-text", "tts", "vosk" ], "owner": { "login": "alphacep", "avatar_url": "https://avatars.githubusercontent.com/u/26358566?v=4", "html_url": "https://github.com/alphacep" } }, { "id": 637992839, "name": "furniture-bench", "full_name": "clvrai/furniture-bench", "url": "https://github.com/clvrai/furniture-bench", "description": "FurnitureBench: Real-World Furniture Assembly Benchmark (RSS 2023)", "stars": 231, "forks": 36, "watches": 231, "language": "Python", "license": "MIT License", "topics": [ "furniture-assembly", "reinforcement-learning-environments", "robot-learning", "robotics", "robotics-simulation" ], "owner": { "login": "clvrai", "avatar_url": "https://avatars.githubusercontent.com/u/29267020?v=4", "html_url": "https://github.com/clvrai" } }, { "id": 949984901, "name": "Awesome-Embodied-AI", "full_name": "wadeKeith/Awesome-Embodied-AI", "url": "https://github.com/wadeKeith/Awesome-Embodied-AI", "description": "Curated embodied AI list: surveys, VLA models, datasets, simulators, humanoids, robot learning, and safety resources.", "stars": 210, "forks": 10, "watches": 210, "language": "Python", "license": "MIT License", "topics": [ "awesome-list", "datasets", "embodied-ai", "humanoid-robotics", "physical-ai", "reinforcement-learning", "robot-learning", "robot-manipulation", "robotics", "safety", "simulators", "vision-language-action" ], "owner": { "login": "wadeKeith", "avatar_url": "https://avatars.githubusercontent.com/u/34277382?v=4", "html_url": "https://github.com/wadeKeith" } }, { "id": 363552464, "name": "deepgram-js-sdk", "full_name": "deepgram/deepgram-js-sdk", "url": "https://github.com/deepgram/deepgram-js-sdk", "description": "Official JavaScript SDK for Deepgram.", "stars": 260, "forks": 93, "watches": 260, "language": "TypeScript", "license": "MIT License", "topics": [ "ai", "asr", "deepgram", "hacktoberfest", "javascript", "speech-recognition", "speech-to-text", "text-to-speech", "typescript", "voice-agent", "voice-ai" ], "owner": { "login": "deepgram", "avatar_url": "https://avatars.githubusercontent.com/u/17422641?v=4", "html_url": "https://github.com/deepgram" } }, { "id": 168543012, "name": "open-speech-corpora", "full_name": "coqui-ai/open-speech-corpora", "url": "https://github.com/coqui-ai/open-speech-corpora", "description": "💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies", "stars": 1396, "forks": 150, "watches": 1396, "language": "", "license": "MIT License", "topics": [ "speech-emotion-recognition", "speech-processing", "speech-recognition", "speech-separation", "speech-synthesis", "speech-to-text", "stt", "text-to-speech", "tts", "voice-activity-detection", "voice-cloning", "voice-recognition" ], "owner": { "login": "coqui-ai", "avatar_url": "https://avatars.githubusercontent.com/u/75583352?v=4", "html_url": "https://github.com/coqui-ai" } }, { "id": 877081404, "name": "Fast-Powerful-Whisper-AI-Services-API", "full_name": "Evil0ctal/Fast-Powerful-Whisper-AI-Services-API", "url": "https://github.com/Evil0ctal/Fast-Powerful-Whisper-AI-Services-API", "description": "⚡ 一款用于自动语音识别 (ASR)、翻译的高性能异步 API。不需要购买Whisper API，使用本地运行的Whisper模型进行推理，并支持多GPU并发，针对分布式部署进行设计。还内置了包括TikTok、抖音等社交媒体平台的爬虫，可实现来自多个社交平台的无缝媒体处理，为媒体内容数据自动化处理提供了强大且可扩展的解决方案。", "stars": 470, "forks": 58, "watches": 470, "language": "Python", "license": "Apache License 2.0", "topics": [ "asr", "crawler", "douyin-api", "fastapi", "faster-whisper", "openai-whisper", "speech-recognition", "speech-to-text", "speech-to-text-api", "tiktok-analytics", "tiktok-api", "tiktok-crawler", "video-analysis", "whisper-ai", "whisper-api", "whisperbot" ], "owner": { "login": "Evil0ctal", "avatar_url": "https://avatars.githubusercontent.com/u/20760448?v=4", "html_url": "https://github.com/Evil0ctal" } }, { "id": 612537765, "name": "RuntimeSpeechRecognizer", "full_name": "gtreshchev/RuntimeSpeechRecognizer", "url": "https://github.com/gtreshchev/RuntimeSpeechRecognizer", "description": "Cross-platform, real-time, offline speech recognition plugin for Unreal Engine. Based on Whisper OpenAI technology, whisper.cpp.", "stars": 306, "forks": 52, "watches": 306, "language": "C++", "license": "MIT License", "topics": [ "audio-processing", "openai", "speech-detection", "speech-processing", "speech-recognition", "speech-to-text", "ue4", "ue4-plugin", "ue5", "ue5-plugin", "unreal-engine", "unreal-engine-4", "unreal-engine-5", "voice-recognition", "whis", "whisper", "whisper-ai", "whisper-cpp" ], "owner": { "login": "gtreshchev", "avatar_url": "https://avatars.githubusercontent.com/u/69837452?v=4", "html_url": "https://github.com/gtreshchev" } }, { "id": 540843209, "name": "whisper-auto-transcribe", "full_name": "tomchang25/whisper-auto-transcribe", "url": "https://github.com/tomchang25/whisper-auto-transcribe", "description": "Auto transcribe tool based on whisper", "stars": 226, "forks": 17, "watches": 226, "language": "Python", "license": "MIT License", "topics": [ "asr", "deep-learning", "gradio", "gradio-interface", "language-model", "pytorch", "speech-processing", "speech-recognition", "speech-to-text", "text-to-speech", "video-captioning", "voice-activity-detection" ], "owner": { "login": "tomchang25", "avatar_url": "https://avatars.githubusercontent.com/u/31534748?v=4", "html_url": "https://github.com/tomchang25" } }, { "id": 431012514, "name": "vosk-unity-asr", "full_name": "alphacep/vosk-unity-asr", "url": "https://github.com/alphacep/vosk-unity-asr", "description": "Automatic Speech Recognition in Unity using Vosk library", "stars": 125, "forks": 25, "watches": 125, "language": "C#", "license": "Apache License 2.0", "topics": [ "asr", "deepspeech", "speech-recognition", "speech-to-text", "stt", "unity3d" ], "owner": { "login": "alphacep", "avatar_url": "https://avatars.githubusercontent.com/u/26358566?v=4", "html_url": "https://github.com/alphacep" } }, { "id": 612286568, "name": "tiny-openai-whisper-api", "full_name": "morioka/tiny-openai-whisper-api", "url": "https://github.com/morioka/tiny-openai-whisper-api", "description": "OpenAI Whisper API-style local server, runnig on FastAPI", "stars": 86, "forks": 20, "watches": 86, "language": "Python", "license": "MIT License", "topics": [ "speech-recognition", "speech-to-text" ], "owner": { "login": "morioka", "avatar_url": "https://avatars.githubusercontent.com/u/1615546?v=4", "html_url": "https://github.com/morioka" } }, { "id": 827525109, "name": "AdaptiGraph", "full_name": "Boey-li/AdaptiGraph", "url": "https://github.com/Boey-li/AdaptiGraph", "description": "[RSS 2024] AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulation", "stars": 85, "forks": 5, "watches": 85, "language": "C++", "license": "MIT License", "topics": [ "gnn", "robot-learning", "robot-manipulation", "robot-simulation", "robotics", "vision" ], "owner": { "login": "Boey-li", "avatar_url": "https://avatars.githubusercontent.com/u/73146149?v=4", "html_url": "https://github.com/Boey-li" } }, { "id": 713732525, "name": "llm_rules", "full_name": "normster/llm_rules", "url": "https://github.com/normster/llm_rules", "description": "RuLES: a benchmark for evaluating rule-following in language models", "stars": 253, "forks": 16, "watches": 253, "language": "Python", "license": "Apache License 2.0", "topics": [ "ai-safety", "ai-security", "gpt-4" ], "owner": { "login": "normster", "avatar_url": "https://avatars.githubusercontent.com/u/6687910?v=4", "html_url": "https://github.com/normster" } }, { "id": 255656946, "name": "Note", "full_name": "NoteDance/Note", "url": "https://github.com/NoteDance/Note", "description": "Machine learning library, Distributed training, Deep learning, Reinforcement learning, Models, TensorFlow, PyTorch", "stars": 70, "forks": 2, "watches": 70, "language": "Python", "license": "Apache License 2.0", "topics": [ "artificial-intelligence", "deep-learning", "deep-reinforcement-learning", "deeplearning", "deepreinforcementlearning", "distributed-training", "dl", "drl", "machine-learning", "machine-learning-library", "machinelearning", "ml", "neural-network", "neuralnetwork", "parallel-training", "pytorch", "reinforcement-learning", "reinforcementlearning", "rl", "tensorflow" ], "owner": { "login": "NoteDance", "avatar_url": "https://avatars.githubusercontent.com/u/63648431?v=4", "html_url": "https://github.com/NoteDance" } }, { "id": 12320895, "name": "annyang", "full_name": "TalAter/annyang", "url": "https://github.com/TalAter/annyang", "description": "💬 Speech recognition for your site", "stars": 6811, "forks": 1049, "watches": 6811, "language": "TypeScript", "license": "MIT License", "topics": [ "speech", "speech-recognition", "speech-to-text", "voice" ], "owner": { "login": "TalAter", "avatar_url": "https://avatars.githubusercontent.com/u/926653?v=4", "html_url": "https://github.com/TalAter" } }, { "id": 540020892, "name": "whisper-asr-webservice", "full_name": "ahmetoner/whisper-asr-webservice", "url": "https://github.com/ahmetoner/whisper-asr-webservice", "description": "OpenAI Whisper ASR Webservice API", "stars": 3276, "forks": 577, "watches": 3276, "language": "Python", "license": "MIT License", "topics": [ "asr", "automatic-speech-recognition", "docker", "openai-whisper", "speech", "speech-recognition", "speech-to-text" ], "owner": { "login": "ahmetoner", "avatar_url": "https://avatars.githubusercontent.com/u/3612657?v=4", "html_url": "https://github.com/ahmetoner" } }, { "id": 809531280, "name": "Robust-Gymnasium", "full_name": "SafeRL-Lab/Robust-Gymnasium", "url": "https://github.com/SafeRL-Lab/Robust-Gymnasium", "description": "[ICLR 2025] Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning.", "stars": 98, "forks": 10, "watches": 98, "language": "Python", "license": "MIT License", "topics": [ "benchmark", "manipulation", "multi-agent-reinforcement-learning", "multi-agent-systems", "real-world-applications", "reinforcement-learning", "robot-learning", "robotics", "robust-reinforcement-learning", "robustness", "safe-reinforcement-learning", "safety" ], "owner": { "login": "SafeRL-Lab", "avatar_url": "https://avatars.githubusercontent.com/u/113200031?v=4", "html_url": "https://github.com/SafeRL-Lab" } }, { "id": 935254000, "name": "MIKASA-Robo", "full_name": "CognitiveAISystems/MIKASA-Robo", "url": "https://github.com/CognitiveAISystems/MIKASA-Robo", "description": "🔥 [ICLR 2026] Benchmark for robotic tabletop manipulation memory-intensive tasks", "stars": 107, "forks": 12, "watches": 107, "language": "Python", "license": "MIT License", "topics": [ "benchmark", "maniskill", "memory", "pomdp", "reinforcement-learning", "rl", "visual-language-action-models", "vla" ], "owner": { "login": "CognitiveAISystems", "avatar_url": "https://avatars.githubusercontent.com/u/182634102?v=4", "html_url": "https://github.com/CognitiveAISystems" } }, { "id": 732452471, "name": "WhisperS2T", "full_name": "shashikg/WhisperS2T", "url": "https://github.com/shashikg/WhisperS2T", "description": "An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engine", "stars": 572, "forks": 76, "watches": 572, "language": "Jupyter Notebook", "license": "MIT License", "topics": [ "asr", "deep-learning", "speech-recognition", "speech-to-text", "tensorrt", "tensorrt-llm", "vad", "voice-activity-detection", "whisper" ], "owner": { "login": "shashikg", "avatar_url": "https://avatars.githubusercontent.com/u/22556187?v=4", "html_url": "https://github.com/shashikg" } }, { "id": 588677997, "name": "ElevateAIJavaSDK", "full_name": "NICEElevateAI/ElevateAIJavaSDK", "url": "https://github.com/NICEElevateAI/ElevateAIJavaSDK", "description": "Java SDK for ElevateAI", "stars": 122, "forks": 1, "watches": 122, "language": "Java", "license": "MIT License", "topics": [ "asr", "automated-speech-recognition", "free-for-dev", "free-for-developers", "java", "sdk", "sdk-java", "speech-processing", "speech-recognition", "speech-to-text" ], "owner": { "login": "NICEElevateAI", "avatar_url": "https://avatars.githubusercontent.com/u/121960015?v=4", "html_url": "https://github.com/NICEElevateAI" } }, { "id": 139072395, "name": "GammaCV", "full_name": "PeculiarVentures/GammaCV", "url": "https://github.com/PeculiarVentures/GammaCV", "description": "GammaCV is a WebGL accelerated Computer Vision library for browser", "stars": 193, "forks": 23, "watches": 193, "language": "JavaScript", "license": "MIT License", "topics": [ "computer-vision", "feature-extraction", "gpu", "gpu-acceleration", "image-analysis", "image-processing", "machine-learning", "machine-vision", "object-detection", "opencv", "webgl" ], "owner": { "login": "PeculiarVentures", "avatar_url": "https://avatars.githubusercontent.com/u/8702988?v=4", "html_url": "https://github.com/PeculiarVentures" } }, { "id": 627284684, "name": "Awesome-Robot-Learning", "full_name": "RayYoh/Awesome-Robot-Learning", "url": "https://github.com/RayYoh/Awesome-Robot-Learning", "description": "This repo contains a curative list of robot learning (mainly for manipulation) resources.", "stars": 202, "forks": 8, "watches": 202, "language": "", "license": "MIT License", "topics": [ "artificial-intelligence", "awesome-list", "list", "reinforcement-learning", "reinforcement-learning-environments", "robot", "robot-learning", "robotics" ], "owner": { "login": "RayYoh", "avatar_url": "https://avatars.githubusercontent.com/u/35106336?v=4", "html_url": "https://github.com/RayYoh" } }, { "id": 935889002, "name": "ET-SEED", "full_name": "yuechen0614/ET-SEED", "url": "https://github.com/yuechen0614/ET-SEED", "description": "[ICLR 2025🎉] Official implementation for paper \"ET-SEED: Efficient Trajectory-Level SE(3) Equivariant Diffusion Policy\".", "stars": 67, "forks": 7, "watches": 67, "language": "Python", "license": "MIT License", "topics": [ "computer-vision", "imitation-learning", "robot-learning", "robotics" ], "owner": { "login": "yuechen0614", "avatar_url": "https://avatars.githubusercontent.com/u/109053058?v=4", "html_url": "https://github.com/yuechen0614" } }, { "id": 145716955, "name": "konoha", "full_name": "himkt/konoha", "url": "https://github.com/himkt/konoha", "description": "🌿 An easy-to-use Japanese Text Processing tool, which makes it possible to switch tokenizers with small changes of code.", "stars": 261, "forks": 25, "watches": 261, "language": "Python", "license": "MIT License", "topics": [ "janome", "japanese", "kytea", "mecab", "natural-language-processing", "nlp", "sentencepiece", "sudachi", "text-processing" ], "owner": { "login": "himkt", "avatar_url": "https://avatars.githubusercontent.com/u/5164000?v=4", "html_url": "https://github.com/himkt" } }, { "id": 230359479, "name": "muzero-general", "full_name": "werner-duvaud/muzero-general", "url": "https://github.com/werner-duvaud/muzero-general", "description": "MuZero", "stars": 2819, "forks": 670, "watches": 2819, "language": "Python", "license": "MIT License", "topics": [ "alphago", "alphazero", "deep-learning", "deep-reinforcement-learning", "gym", "machine-learning", "mcts", "model-based-rl", "monte-carlo-tree-search", "muzero", "muzero-general", "neural-network", "python3", "pytorch", "reinforcement-learning", "residual-network", "rl", "self-learning", "tensorboard" ], "owner": { "login": "werner-duvaud", "avatar_url": "https://avatars.githubusercontent.com/u/40442230?v=4", "html_url": "https://github.com/werner-duvaud" } }, { "id": 1154876909, "name": "GenRL", "full_name": "ModelTC/GenRL", "url": "https://github.com/ModelTC/GenRL", "description": "Reinforcement Learning Framework for Visual Generation", "stars": 118, "forks": 6, "watches": 118, "language": "Python", "license": "Apache License 2.0", "topics": [ "dpo", "grpo", "imagegeneration", "infra", "reinforcement-learning", "rl", "videogeneration", "wan", "wan-video", "wan21" ], "owner": { "login": "ModelTC", "avatar_url": "https://avatars.githubusercontent.com/u/69665675?v=4", "html_url": "https://github.com/ModelTC" } }, { "id": 1014211327, "name": "AgentFly", "full_name": "Agent-One-Lab/AgentFly", "url": "https://github.com/Agent-One-Lab/AgentFly", "description": "Scalable and extensible reinforcement learning for LM agents.", "stars": 118, "forks": 13, "watches": 118, "language": "Python", "license": "Apache License 2.0", "topics": [ "agent", "agent-rl", "agentfly", "agentic", "agentrl", "chat-template", "framework", "llm", "mcp", "multi-modal", "nlp", "reasoning", "reinforcement-learning", "reward", "rl", "system", "tool", "tool-use", "training", "vision-language" ], "owner": { "login": "Agent-One-Lab", "avatar_url": "https://avatars.githubusercontent.com/u/219401993?v=4", "html_url": "https://github.com/Agent-One-Lab" } }, { "id": 470359673, "name": "TTS-Voice-Wizard", "full_name": "VRCWizard/TTS-Voice-Wizard", "url": "https://github.com/VRCWizard/TTS-Voice-Wizard", "description": "Speech to Text to Speech. Song now playing. Sends text as OSC messages to VRChat to display on avatar. (STTTS) (Speech to TTS) (VRC STT System) (VTuber TTS)", "stars": 788, "forks": 81, "watches": 788, "language": "C#", "license": "MIT License", "topics": [ "chatbox", "discord", "free", "heart-rate", "osc", "speech-recognition", "speech-to-text", "spotify", "stt", "text-to-speech", "tts", "voice", "vrchat", "vtuber" ], "owner": { "login": "VRCWizard", "avatar_url": "https://avatars.githubusercontent.com/u/101527472?v=4", "html_url": "https://github.com/VRCWizard" } }, { "id": 206138137, "name": "vosk-api", "full_name": "alphacep/vosk-api", "url": "https://github.com/alphacep/vosk-api", "description": "Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node", "stars": 14800, "forks": 1725, "watches": 14800, "language": "Jupyter Notebook", "license": "Apache License 2.0", "topics": [ "android", "asr", "deep-learning", "deep-neural-networks", "deepspeech", "google-speech-to-text", "ios", "kaldi", "offline", "privacy", "python", "raspberry-pi", "speaker-identification", "speaker-verification", "speech-recognition", "speech-to-text", "speech-to-text-android", "stt", "voice-recognition", "vosk" ], "owner": { "login": "alphacep", "avatar_url": "https://avatars.githubusercontent.com/u/26358566?v=4", "html_url": "https://github.com/alphacep" } }, { "id": 355441065, "name": "speech_dataset", "full_name": "double22a/speech_dataset", "url": "https://github.com/double22a/speech_dataset", "description": "The dataset of Speech Recognition", "stars": 459, "forks": 81, "watches": 459, "language": "", "license": "Apache License 2.0", "topics": [ "asr", "audio", "automatic-speech-recognition", "dataset", "deep-learning", "deep-neural-networks", "speech", "speech-diarization", "speech-enhancement", "speech-recognition", "speech-segmentation", "speech-separation", "speech-synthesis", "speech-to-text", "speech-translation", "text-to-speech", "tts", "voice-conversion", "wav" ], "owner": { "login": "double22a", "avatar_url": "https://avatars.githubusercontent.com/u/18691173?v=4", "html_url": "https://github.com/double22a" } }, { "id": 215810060, "name": "kaldi-serve", "full_name": "skit-ai/kaldi-serve", "url": "https://github.com/skit-ai/kaldi-serve", "description": "Server framework for Kaldi ASR Toolkit", "stars": 99, "forks": 24, "watches": 99, "language": "C++", "license": "Apache License 2.0", "topics": [ "asr", "grpc", "grpc-server", "kaldi", "kaldi-asr", "kaldi-server", "speech-recognition", "speech-to-text" ], "owner": { "login": "skit-ai", "avatar_url": "https://avatars.githubusercontent.com/u/26162666?v=4", "html_url": "https://github.com/skit-ai" } }, { "id": 578784970, "name": "Talk2GPT", "full_name": "0ut0flin3/Talk2GPT", "url": "https://github.com/0ut0flin3/Talk2GPT", "description": "GPT-3 client for Windows and Unix with memories management that supports both text and speech in any language. Includes a free text2image", "stars": 89, "forks": 6, "watches": 89, "language": "Python", "license": "Apache License 2.0", "topics": [ "ai", "gpt", "gpt3", "openai", "speech-recognition", "speech-to-text", "tts" ], "owner": { "login": "0ut0flin3", "avatar_url": "https://avatars.githubusercontent.com/u/114559605?v=4", "html_url": "https://github.com/0ut0flin3" } }, { "id": 354440018, "name": "GIGA", "full_name": "UT-Austin-RPL/GIGA", "url": "https://github.com/UT-Austin-RPL/GIGA", "description": "Official PyTorch implementation of Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations", "stars": 159, "forks": 31, "watches": 159, "language": "Python", "license": "MIT License", "topics": [ "3d-reconstruction", "affordance", "grasping", "robot-learning", "robot-manipulation", "robotics" ], "owner": { "login": "UT-Austin-RPL", "avatar_url": "https://avatars.githubusercontent.com/u/61921293?v=4", "html_url": "https://github.com/UT-Austin-RPL" } }, { "id": 668722770, "name": "friendli-client", "full_name": "friendliai/friendli-client", "url": "https://github.com/friendliai/friendli-client", "description": "[⛔️ DEPRECATED] Friendli: the fastest serving engine for generative AI", "stars": 50, "forks": 7, "watches": 50, "language": "Python", "license": "Apache License 2.0", "topics": [ "ai", "generative-ai", "gpt", "gpt3", "inference", "inference-engine", "inference-server", "llama2", "llm", "llm-inference", "llm-ops", "llm-serving", "llmops", "llms", "mistral", "ml", "mlops", "serving", "stable-diffusion" ], "owner": { "login": "friendliai", "avatar_url": "https://avatars.githubusercontent.com/u/76214470?v=4", "html_url": "https://github.com/friendliai" } }, { "id": 114990078, "name": "AlphaZero_Gomoku", "full_name": "junxiaosong/AlphaZero_Gomoku", "url": "https://github.com/junxiaosong/AlphaZero_Gomoku", "description": "An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row) ", "stars": 3617, "forks": 1026, "watches": 3617, "language": "Python", "license": "MIT License", "topics": [ "alphago", "alphago-zero", "alphazero", "board-game", "gobang", "gomoku", "mcts", "monte-carlo-tree-search", "pytorch", "reinforcement-learning", "rl", "self-learning", "tensorflow" ], "owner": { "login": "junxiaosong", "avatar_url": "https://avatars.githubusercontent.com/u/4265933?v=4", "html_url": "https://github.com/junxiaosong" } }, { "id": 933133907, "name": "fireredasr-ui", "full_name": "jianchang512/fireredasr-ui", "url": "https://github.com/jianchang512/fireredasr-ui", "description": "一个中文语音转文字项目，封装自FireRedASR", "stars": 86, "forks": 14, "watches": 86, "language": "Python", "license": "Apache License 2.0", "topics": [ "asr", "automation-speech-recognization", "fireredasr", "speech-recognition", "speech-to-text" ], "owner": { "login": "jianchang512", "avatar_url": "https://avatars.githubusercontent.com/u/3378335?v=4", "html_url": "https://github.com/jianchang512" } }, { "id": 1107600765, "name": "DARE", "full_name": "yjyddq/DARE", "url": "https://github.com/yjyddq/DARE", "description": "Official repository of DARE: Diffusion Large Language Models Alignment and Reinforcement Executor", "stars": 202, "forks": 6, "watches": 202, "language": "Python", "license": "Apache License 2.0", "topics": [ "alignment", "block-diffusion-large-language-model", "diffusion-language-models", "diffusion-large-language-model", "dllm", "dllm-infra", "dllm-rl", "dllm-rl-infra", "masked-diffusion-large-language-model", "reinforcement-learning", "rl", "verl" ], "owner": { "login": "yjyddq", "avatar_url": "https://avatars.githubusercontent.com/u/50619850?v=4", "html_url": "https://github.com/yjyddq" } }, { "id": 723896616, "name": "dobb-e", "full_name": "notmahi/dobb-e", "url": "https://github.com/notmahi/dobb-e", "description": "Dobb·E: An open-source, general framework for learning household robotic manipulation", "stars": 621, "forks": 56, "watches": 621, "language": "G-code", "license": "MIT License", "topics": [ "behavior-cloning", "imitation-learning", "robot-learning", "robotics" ], "owner": { "login": "notmahi", "avatar_url": "https://avatars.githubusercontent.com/u/3000253?v=4", "html_url": "https://github.com/notmahi" } }, { "id": 712422394, "name": "explainable-reinforcement-learning", "full_name": "yanzheb/explainable-reinforcement-learning", "url": "https://github.com/yanzheb/explainable-reinforcement-learning", "description": "The most comprehensive XRL paper list: 277 papers (2016–2026) on interpretable and explainable RL. Surveys, saliency, counterfactuals, policy summarization and more.", "stars": 61, "forks": 11, "watches": 61, "language": "", "license": "MIT License", "topics": [ "awesome", "awesome-list", "deep-reinforcement-learning", "explainability", "interpretability", "interpretable-ml", "reinforcement-learning", "rl", "survey", "xai", "xrl" ], "owner": { "login": "yanzheb", "avatar_url": "https://avatars.githubusercontent.com/u/16868894?v=4", "html_url": "https://github.com/yanzheb" } }, { "id": 597214065, "name": "willow-inference-server", "full_name": "toverainc/willow-inference-server", "url": "https://github.com/toverainc/willow-inference-server", "description": "Open source, local, and self-hosted highly optimized language inference server supporting ASR/STT, TTS, and LLM across WebRTC, REST, and WS", "stars": 502, "forks": 60, "watches": 502, "language": "Python", "license": "Apache License 2.0", "topics": [ "cuda", "deep-learning", "llama", "llm", "privacy", "speech-recognition", "speech-to-text", "text-to-speech", "vicuna", "webrtc", "whisper", "willow" ], "owner": { "login": "toverainc", "avatar_url": "https://avatars.githubusercontent.com/u/84786158?v=4", "html_url": "https://github.com/toverainc" } }, { "id": 622164768, "name": "LangHelper", "full_name": "NsLearning/LangHelper", "url": "https://github.com/NsLearning/LangHelper", "description": "Striving to create a great Application with full functions of learning languages by ChatGPT, TTS, STT and other awesome AI models, supports talking, speaking assessment, memorizing words with contexts, Listening test, so on.", "stars": 348, "forks": 22, "watches": 348, "language": "Rust", "license": "MIT License", "topics": [ "ai", "asr", "assessment", "chatgpt", "ielts", "language-learning", "speech", "speech-recognition", "speech-to-text", "stt", "toefl", "tts", "words" ], "owner": { "login": "NsLearning", "avatar_url": "https://avatars.githubusercontent.com/u/126308115?v=4", "html_url": "https://github.com/NsLearning" } }, { "id": 456624068, "name": "UEAzSpeech", "full_name": "lucoiso/UEAzSpeech", "url": "https://github.com/lucoiso/UEAzSpeech", "description": "This plugin integrates Azure Speech Cognitive Services in Unreal Engine.", "stars": 216, "forks": 53, "watches": 216, "language": "C++", "license": "MIT License", "topics": [ "azure", "azure-cognitive-service", "azure-cognitive-services", "speech", "speech-recognition", "speech-synthesis", "speech-to-text", "text-to-speech", "tts", "ue4", "ue5", "unreal", "unreal-engine", "unreal-engine-4", "unreal-engine-5", "unreal-engine-plugin", "unrealengine" ], "owner": { "login": "lucoiso", "avatar_url": "https://avatars.githubusercontent.com/u/77353979?v=4", "html_url": "https://github.com/lucoiso" } }, { "id": 263612259, "name": "LAS_Mandarin_PyTorch", "full_name": "jackaduma/LAS_Mandarin_PyTorch", "url": "https://github.com/jackaduma/LAS_Mandarin_PyTorch", "description": "Listen, attend and spell Model and a Chinese Mandarin Pretrained model (中文-普通话 ASR模型)", "stars": 125, "forks": 17, "watches": 125, "language": "Python", "license": "MIT License", "topics": [ "asr", "chinese-speech-recognition", "deep-learning", "deeplearning", "listen-attend-and-spell", "mandarin", "pytorch-implementation", "speech-recognition", "speech-to-text" ], "owner": { "login": "jackaduma", "avatar_url": "https://avatars.githubusercontent.com/u/1276942?v=4", "html_url": "https://github.com/jackaduma" } }, { "id": 964078137, "name": "conversify", "full_name": "taresh18/conversify", "url": "https://github.com/taresh18/conversify", "description": "🗣️ Real‑time, low‑latency voice, vision, and conversational‑memory AI assistant built on LiveKit and local LLMs ", "stars": 111, "forks": 19, "watches": 111, "language": "Python", "license": "Apache License 2.0", "topics": [ "conversational-ai", "livekit", "llm", "real-time", "speech-recognition", "speech-to-speech", "speech-to-text", "stt", "tts", "webrtc" ], "owner": { "login": "taresh18", "avatar_url": "https://avatars.githubusercontent.com/u/58368119?v=4", "html_url": "https://github.com/taresh18" } }, { "id": 720283992, "name": "whisper-cpp-server", "full_name": "litongjava/whisper-cpp-server", "url": "https://github.com/litongjava/whisper-cpp-server", "description": "whisper-cpp-serve Real-time speech recognition and c+ of OpenAI's Whisper model in C/C++ ", "stars": 74, "forks": 14, "watches": 74, "language": "HTML", "license": "MIT License", "topics": [ "asr", "inference", "opneai", "speech-recognition", "speech-to-text", "transformer", "whisper", "whisper-cpp", "whisper-cpp-server", "whisper-server" ], "owner": { "login": "litongjava", "avatar_url": "https://avatars.githubusercontent.com/u/31761981?v=4", "html_url": "https://github.com/litongjava" } }, { "id": 706125110, "name": "flashbax", "full_name": "instadeepai/flashbax", "url": "https://github.com/instadeepai/flashbax", "description": "⚡ Flashbax: Accelerated Replay Buffers in JAX", "stars": 278, "forks": 23, "watches": 278, "language": "Python", "license": "Apache License 2.0", "topics": [ "buffers", "hpc", "jax", "machine-learning", "off-policy", "reinforcement-learning", "rl" ], "owner": { "login": "instadeepai", "avatar_url": "https://avatars.githubusercontent.com/u/36735093?v=4", "html_url": "https://github.com/instadeepai" } }, { "id": 1116516142, "name": "Fun-ASR", "full_name": "FunAudioLLM/Fun-ASR", "url": "https://github.com/FunAudioLLM/Fun-ASR", "description": "End-to-end speech recognition large model: 31 languages, dialects, accents, lyrics, hotwords, timestamps, speaker diarization. Trained on tens of millions of hours.", "stars": 1194, "forks": 116, "watches": 1194, "language": "Python", "license": "Apache License 2.0", "topics": [ "31-languages", "asr", "audio-language-model", "chinese-dialects", "fun-asr", "llm-asr", "multilingual-asr", "pytorch", "real-time-asr", "speaker-diarization", "speech-recognition", "speech-to-text", "transcription", "whisper-alternative" ], "owner": { "login": "FunAudioLLM", "avatar_url": "https://avatars.githubusercontent.com/u/167062371?v=4", "html_url": "https://github.com/FunAudioLLM" } }, { "id": 278622190, "name": "rnnt_decoder_cuda", "full_name": "iamjanvijay/rnnt_decoder_cuda", "url": "https://github.com/iamjanvijay/rnnt_decoder_cuda", "description": "An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.", "stars": 67, "forks": 10, "watches": 67, "language": "Cuda", "license": "MIT License", "topics": [ "beam-search", "cuda", "handwriting-recognition", "prefix-search", "rnnt", "speech-recognition", "speech-to-text", "transducer" ], "owner": { "login": "iamjanvijay", "avatar_url": "https://avatars.githubusercontent.com/u/17268217?v=4", "html_url": "https://github.com/iamjanvijay" } }, { "id": 810216864, "name": "PointCloudMatters", "full_name": "HaoyiZhu/PointCloudMatters", "url": "https://github.com/HaoyiZhu/PointCloudMatters", "description": "[NeurIPS 2024 D\u0026B] Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning", "stars": 91, "forks": 5, "watches": 91, "language": "Python", "license": "MIT License", "topics": [ "benchmark", "observation-space", "point-cloud", "robot-learning", "robot-manipulation", "robotics" ], "owner": { "login": "HaoyiZhu", "avatar_url": "https://avatars.githubusercontent.com/u/63538191?v=4", "html_url": "https://github.com/HaoyiZhu" } }, { "id": 13956112, "name": "hazm", "full_name": "roshan-research/hazm", "url": "https://github.com/roshan-research/hazm", "description": "Persian NLP Toolkit", "stars": 1398, "forks": 207, "watches": 1398, "language": "Python", "license": "MIT License", "topics": [ "dependency-parser", "embeddings", "farsi", "lemmatization", "natural-language-processing", "nlp", "normalization", "persian", "persian-nlp", "pos-tagging", "python", "text-processing", "tokenizer" ], "owner": { "login": "roshan-research", "avatar_url": "https://avatars.githubusercontent.com/u/1282599?v=4", "html_url": "https://github.com/roshan-research" } }, { "id": 1238830448, "name": "astraflow", "full_name": "Infini-AI-Lab/astraflow", "url": "https://github.com/Infini-AI-Lab/astraflow", "description": "Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs", "stars": 76, "forks": 10, "watches": 76, "language": "Python", "license": "Apache License 2.0", "topics": [ "agentic-ai", "llm", "llm-rl", "mlsys", "reinforcement-learning", "rl" ], "owner": { "login": "Infini-AI-Lab", "avatar_url": "https://avatars.githubusercontent.com/u/149595684?v=4", "html_url": "https://github.com/Infini-AI-Lab" } }, { "id": 638845853, "name": "ComfyUI_Custom_Nodes_AlekPet", "full_name": "AlekPet/ComfyUI_Custom_Nodes_AlekPet", "url": "https://github.com/AlekPet/ComfyUI_Custom_Nodes_AlekPet", "description": "Custom nodes that extend the capabilities of Comfyui", "stars": 1497, "forks": 94, "watches": 1497, "language": "JavaScript", "license": "MIT License", "topics": [ "glm", "ide", "painter", "pose-detection", "speech-recognition", "speech-synthesis", "speech-to-text", "tranlsate" ], "owner": { "login": "AlekPet", "avatar_url": "https://avatars.githubusercontent.com/u/25489996?v=4", "html_url": "https://github.com/AlekPet" } }, { "id": 1195602794, "name": "CrispASR", "full_name": "CrispStrobe/CrispASR", "url": "https://github.com/CrispStrobe/CrispASR", "description": "C++ ggml runtime hub for multilingual ASR models: Cohere Transcribe, Parakeet TDT, Voxtral, Canary 1B v2, etc, plus universal forced alignment via NeMo Forced Aligner-style CTC, and others. Fork of whisper.cpp.", "stars": 241, "forks": 32, "watches": 241, "language": "C++", "license": "MIT License", "topics": [ "cohere-transcribe", "cohere-transcribe-03-2026", "ggml", "parakeet", "speech-recognition", "speech-to-text", "stt", "transcription", "voxtral", "whisper-cpp" ], "owner": { "login": "CrispStrobe", "avatar_url": "https://avatars.githubusercontent.com/u/154636388?v=4", "html_url": "https://github.com/CrispStrobe" } }, { "id": 480999369, "name": "deepgram-rust-sdk", "full_name": "deepgram/deepgram-rust-sdk", "url": "https://github.com/deepgram/deepgram-rust-sdk", "description": "Community Rust SDK for Deepgram.", "stars": 66, "forks": 43, "watches": 66, "language": "Rust", "license": "MIT License", "topics": [ "deepgram", "hacktoberfest", "rust", "speech-recognition", "speech-to-text" ], "owner": { "login": "deepgram", "avatar_url": "https://avatars.githubusercontent.com/u/17422641?v=4", "html_url": "https://github.com/deepgram" } }, { "id": 520357130, "name": "ManiSkill", "full_name": "haosulab/ManiSkill", "url": "https://github.com/haosulab/ManiSkill", "description": "SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark", "stars": 2930, "forks": 489, "watches": 2930, "language": "Python", "license": "Apache License 2.0", "topics": [ "3d-computer-vision", "computer-vision", "embodied-ai", "reinforcement-learning", "robot-learning", "robot-manipulation", "robotics", "robotics-simulation", "simulation-environment" ], "owner": { "login": "haosulab", "avatar_url": "https://avatars.githubusercontent.com/u/43918365?v=4", "html_url": "https://github.com/haosulab" } }, { "id": 875957930, "name": "space_robotics_bench", "full_name": "AndrejOrsula/space_robotics_bench", "url": "https://github.com/AndrejOrsula/space_robotics_bench", "description": "Robot Learning Beyond Earth", "stars": 150, "forks": 23, "watches": 150, "language": "Python", "license": "Apache License 2.0", "topics": [ "benchmark", "robot-learning", "robotics", "simulation", "space", "space-robotics", "space-ros" ], "owner": { "login": "AndrejOrsula", "avatar_url": "https://avatars.githubusercontent.com/u/22929099?v=4", "html_url": "https://github.com/AndrejOrsula" } }, { "id": 937952934, "name": "AReaL", "full_name": "areal-project/AReaL", "url": "https://github.com/areal-project/AReaL", "description": "The RL Bridge for LLM-based Agent Applications. Made Simple \u0026 Flexible.", "stars": 5235, "forks": 508, "watches": 5235, "language": "Python", "license": "Apache License 2.0", "topics": [ "agent", "llm", "llm-agent", "llm-reasoning", "machine-learning-systems", "mlsys", "reinforcement-learning", "rl" ], "owner": { "login": "areal-project", "avatar_url": "https://avatars.githubusercontent.com/u/283073558?v=4", "html_url": "https://github.com/areal-project" } }, { "id": 585215438, "name": "ElevateAIDotNetSDK", "full_name": "NICEElevateAI/ElevateAIDotNetSDK", "url": "https://github.com/NICEElevateAI/ElevateAIDotNetSDK", "description": ".Net core 6 SDK for ElevateAI", "stars": 115, "forks": 2, "watches": 115, "language": "C#", "license": "MIT License", "topics": [ "asr", "automated-speech-recognition", "dotnet", "free-for-dev", "free-for-developers", "sdk", "speech-processing", "speech-recognition", "speech-to-text" ], "owner": { "login": "NICEElevateAI", "avatar_url": "https://avatars.githubusercontent.com/u/121960015?v=4", "html_url": "https://github.com/NICEElevateAI" } }, { "id": 588206595, "name": "ElevateAIPythonSDK", "full_name": "NICEElevateAI/ElevateAIPythonSDK", "url": "https://github.com/NICEElevateAI/ElevateAIPythonSDK", "description": "ElevateAI - Speech-to-text API Python SDK", "stars": 113, "forks": 4, "watches": 113, "language": "Python", "license": "MIT License", "topics": [ "asr", "audio", "automated-speech-recognition", "free-for-dev", "free-for-developers", "python", "sdk", "sdk-python", "speech-processing", "speech-recognition", "speech-to-text" ], "owner": { "login": "NICEElevateAI", "avatar_url": "https://avatars.githubusercontent.com/u/121960015?v=4", "html_url": "https://github.com/NICEElevateAI" } }, { "id": 140010231, "name": "robohive", "full_name": "vikashplus/robohive", "url": "https://github.com/vikashplus/robohive", "description": "A unified framework for robot learning", "stars": 625, "forks": 95, "watches": 625, "language": "Python", "license": "Apache License 2.0", "topics": [ "benchmarks", "environments", "imitation-learning", "mujoco", "mujoco-environments", "python", "reinforcement-learning", "robot-framework", "robot-learning", "robotics", "simulation", "tasks" ], "owner": { "login": "vikashplus", "avatar_url": "https://avatars.githubusercontent.com/u/12837145?v=4", "html_url": "https://github.com/vikashplus" } }, { "id": 713462676, "name": "lobe-tts", "full_name": "lobehub/lobe-tts", "url": "https://github.com/lobehub/lobe-tts", "description": "🎤 Lobe TTS - A high-quality \u0026 reliable TTS/STT library for Server and Browser", "stars": 789, "forks": 99, "watches": 789, "language": "TypeScript", "license": "MIT License", "topics": [ "auzre", "bun", "edge", "lobehub", "microsoft-speech-api", "nodejs", "opeanai", "react", "speech-recognition", "speech-to-text", "stt", "text-to-speech", "tts" ], "owner": { "login": "lobehub", "avatar_url": "https://avatars.githubusercontent.com/u/131470832?v=4", "html_url": "https://github.com/lobehub" } }, { "id": 83158675, "name": "mushroom-rl", "full_name": "MushroomRL/mushroom-rl", "url": "https://github.com/MushroomRL/mushroom-rl", "description": "Python library for Reinforcement Learning.", "stars": 932, "forks": 160, "watches": 932, "language": "Python", "license": "MIT License", "topics": [ "atari", "ddpg", "deep-learning", "deep-reinforcement-learning", "dqn", "mujoco", "openai-gym", "pybullet", "pytorch", "qlearning", "reinforcement-learning", "rl", "sac", "trpo" ], "owner": { "login": "MushroomRL", "avatar_url": "https://avatars.githubusercontent.com/u/59697405?v=4", "html_url": "https://github.com/MushroomRL" } }, { "id": 297155132, "name": "stable-baselines3-contrib", "full_name": "Stable-Baselines-Team/stable-baselines3-contrib", "url": "https://github.com/Stable-Baselines-Team/stable-baselines3-contrib", "description": "Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code", "stars": 718, "forks": 240, "watches": 718, "language": "Python", "license": "MIT License", "topics": [ "experimental", "gsde", "gym", "machine-learning", "openai", "pytorch", "reinforcement-learning", "reinforcement-learning-algorithms", "research", "rl", "robotics", "sde", "stable-baselines" ], "owner": { "login": "Stable-Baselines-Team", "avatar_url": "https://avatars.githubusercontent.com/u/46841238?v=4", "html_url": "https://github.com/Stable-Baselines-Team" } }, { "id": 200468259, "name": "baba-is-auto", "full_name": "utilForever/baba-is-auto", "url": "https://github.com/utilForever/baba-is-auto", "description": "Baba Is You simulator using C++ with some reinforcement learning", "stars": 183, "forks": 25, "watches": 183, "language": "Python", "license": "MIT License", "topics": [ "baba-is-you", "babaisyou", "cplusplus", "cpp", "cpp17", "python-api", "reinforcement-learning", "rl", "rl-environment", "simulator-game" ], "owner": { "login": "utilForever", "avatar_url": "https://avatars.githubusercontent.com/u/5622661?v=4", "html_url": "https://github.com/utilForever" } }, { "id": 1097916347, "name": "asystem-awex", "full_name": "inclusionAI/asystem-awex", "url": "https://github.com/inclusionAI/asystem-awex", "description": "A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL workflows", "stars": 156, "forks": 17, "watches": 156, "language": "Python", "license": "Apache License 2.0", "topics": [ "cuda", "deep-learning", "gpu", "inference", "llm", "machine-learning", "moe", "pytorch", "reasoning", "reinforcement-learning", "rl", "training", "transformers" ], "owner": { "login": "inclusionAI", "avatar_url": "https://avatars.githubusercontent.com/u/199075982?v=4", "html_url": "https://github.com/inclusionAI" } }, { "id": 672339162, "name": "nodejs-whisper", "full_name": "ChetanXpro/nodejs-whisper", "url": "https://github.com/ChetanXpro/nodejs-whisper", "description": "NodeJS Bindings for Whisper - the CPU version of OpenAI's Whisper, as initially crafted in C++ by ggerganov.", "stars": 209, "forks": 40, "watches": 209, "language": "TypeScript", "license": "MIT License", "topics": [ "ai", "cpp", "ml", "nodejs-whisper", "openai", "speech-recognition", "speech-to-text", "timestamp", "whisper", "whisper-nodejs" ], "owner": { "login": "ChetanXpro", "avatar_url": "https://avatars.githubusercontent.com/u/107798155?v=4", "html_url": "https://github.com/ChetanXpro" } }, { "id": 537769847, "name": "lycoris", "full_name": "solaoi/lycoris", "url": "https://github.com/solaoi/lycoris", "description": "Real-time speech recognition \u0026 AI-powered note-taking app for macOS with offline/online modes, multilingual transcription, and Japanese translation support.", "stars": 76, "forks": 3, "watches": 76, "language": "TypeScript", "license": "MIT License", "topics": [ "macos", "mcp", "mcp-client", "openai", "screenshot", "speech-recognition", "speech-to-text", "style-bert-vits2", "tauri", "tauri-v2", "voice-recognition", "vosk", "whisper" ], "owner": { "login": "solaoi", "avatar_url": "https://avatars.githubusercontent.com/u/46414076?v=4", "html_url": "https://github.com/solaoi" } }, { "id": 1214579084, "name": "ArcSub", "full_name": "brucexuego/ArcSub", "url": "https://github.com/brucexuego/ArcSub", "description": "End-to-end subtitle translation workstation with cloud and local OpenVINO model support.", "stars": 57, "forks": 12, "watches": 57, "language": "TypeScript", "license": "MIT License", "topics": [ "cloud-ai", "express", "intel-arc", "intel-gpu", "intel-npu", "local-ai", "media-tools", "openvino", "react", "speech-recognition", "speech-to-text", "subtitle", "subtitle-translation", "subtitles", "transcription", "translation", "video-tools", "whisper" ], "owner": { "login": "brucexuego", "avatar_url": "https://avatars.githubusercontent.com/u/258625112?v=4", "html_url": "https://github.com/brucexuego" } }, { "id": 214133985, "name": "rl-tutorial-jnrr19", "full_name": "araffin/rl-tutorial-jnrr19", "url": "https://github.com/araffin/rl-tutorial-jnrr19", "description": "Stable-Baselines tutorial for Journées Nationales de la Recherche en Robotique 2019 ", "stars": 743, "forks": 140, "watches": 743, "language": "Jupyter Notebook", "license": "MIT License", "topics": [ "colab-notebook", "notebook", "python", "reinforcement-learning", "rl", "stable-baselines", "tutorial" ], "owner": { "login": "araffin", "avatar_url": "https://avatars.githubusercontent.com/u/1973948?v=4", "html_url": "https://github.com/araffin" } }, { "id": 653048276, "name": "navix", "full_name": "epignatelli/navix", "url": "https://github.com/epignatelli/navix", "description": "Accelerated minigrid environments with JAX", "stars": 170, "forks": 21, "watches": 170, "language": "Python", "license": "Apache License 2.0", "topics": [ "deep-reinforcement-learning", "deep-rl", "environment", "gridworld", "gridworld-environment", "minigrid", "reinforcement-learning", "rl" ], "owner": { "login": "epignatelli", "avatar_url": "https://avatars.githubusercontent.com/u/26899347?v=4", "html_url": "https://github.com/epignatelli" } }, { "id": 1127351142, "name": "mlx-tune", "full_name": "ARahim3/mlx-tune", "url": "https://github.com/ARahim3/mlx-tune", "description": "Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.", "stars": 1267, "forks": 83, "watches": 1267, "language": "Python", "license": "Apache License 2.0", "topics": [ "apple-silicon", "deep-learning", "huggingface", "large-language-models", "llm", "llm-finetuning", "local-llm", "lora", "machine-learning", "macos", "mlx", "on-device-ai", "peft", "speech-recognition", "speech-to-text", "text-to-speech", "transformers", "unsloth", "vision-language-model", "whisper" ], "owner": { "login": "ARahim3", "avatar_url": "https://avatars.githubusercontent.com/u/41390319?v=4", "html_url": "https://github.com/ARahim3" } }, { "id": 358203431, "name": "wav2vec2-live", "full_name": "oliverguhr/wav2vec2-live", "url": "https://github.com/oliverguhr/wav2vec2-live", "description": "A live speech recognition using Facebooks wav2vec 2.0 model.", "stars": 378, "forks": 58, "watches": 378, "language": "Python", "license": "MIT License", "topics": [ "asr", "pyaudio", "speech", "speech-recognition", "speech-to-text", "wav2vec", "wav2vec2" ], "owner": { "login": "oliverguhr", "avatar_url": "https://avatars.githubusercontent.com/u/3495355?v=4", "html_url": "https://github.com/oliverguhr" } }, { "id": 1166341098, "name": "parakeet.cpp", "full_name": "Frikallo/parakeet.cpp", "url": "https://github.com/Frikallo/parakeet.cpp", "description": "Ultra fast and portable Parakeet implementation for on-device inference in C++ using Axiom with MPS+Unified Memory", "stars": 275, "forks": 12, "watches": 275, "language": "C++", "license": "MIT License", "topics": [ "asr", "automatic-speech-recognition", "axiom", "nvidia", "parakeet", "speaker-diarization", "speech", "speech-recognition", "speech-to-text" ], "owner": { "login": "Frikallo", "avatar_url": "https://avatars.githubusercontent.com/u/88942100?v=4", "html_url": "https://github.com/Frikallo" } }, { "id": 771797412, "name": "sherpa-ncnn-unity", "full_name": "ssssssilver/sherpa-ncnn-unity", "url": "https://github.com/ssssssilver/sherpa-ncnn-unity", "description": "在Unity环境下，借助sherpa-ncnn框架，实现实时并准确的中英双语语音识别功能。", "stars": 80, "forks": 13, "watches": 80, "language": "C#", "license": "Apache License 2.0", "topics": [ "bilingual", "next-gen-kaldi", "offline-recognition", "sherpa-ncnn", "speech-recognition", "speech-to-text" ], "owner": { "login": "ssssssilver", "avatar_url": "https://avatars.githubusercontent.com/u/16299345?v=4", "html_url": "https://github.com/ssssssilver" } }, { "id": 173138251, "name": "BiaPy", "full_name": "BiaPyX/BiaPy", "url": "https://github.com/BiaPyX/BiaPy", "description": "Open source Python library for building bioimage analysis pipelines", "stars": 200, "forks": 41, "watches": 200, "language": "Jupyter Notebook", "license": "MIT License", "topics": [ "biomedical-image-processing", "classification", "computer-vision", "convolutional-neural-networks", "deep-learning", "denoising", "image-processing", "image-segmentation", "instance-segmentation", "machine-learning", "medical-imaging", "object-detection", "python", "pytorch", "segmentation", "self-supervised-learning", "semantic-segmentation", "super-resolution" ], "owner": { "login": "BiaPyX", "avatar_url": "https://avatars.githubusercontent.com/u/156199480?v=4", "html_url": "https://github.com/BiaPyX" } }, { "id": 190594291, "name": "OSSSpeechKit", "full_name": "AppDevGuy/OSSSpeechKit", "url": "https://github.com/AppDevGuy/OSSSpeechKit", "description": "OSSSpeechKit offers a native iOS Speech wrapper for AVFoundation and Apple's Speech.", "stars": 184, "forks": 43, "watches": 184, "language": "Swift", "license": "MIT License", "topics": [ "avfoundation", "cocoapod", "ios", "pod", "speech", "speech-api", "speech-recognition", "speech-to-text", "swift", "swift5", "text-to-speech" ], "owner": { "login": "AppDevGuy", "avatar_url": "https://avatars.githubusercontent.com/u/14046485?v=4", "html_url": "https://github.com/AppDevGuy" } }, { "id": 195894290, "name": "web-voice-processor", "full_name": "Picovoice/web-voice-processor", "url": "https://github.com/Picovoice/web-voice-processor", "description": "A library for real-time voice processing in web browsers", "stars": 245, "forks": 23, "watches": 245, "language": "TypeScript", "license": "Apache License 2.0", "topics": [ "audio-processing", "browser", "downsampling", "javascript", "microphone", "pcm", "real-time", "realtime", "speech-recognition", "speech-to-text", "voice-commands", "voice-processing", "wake-word-detection", "web-browser", "webaudio-api", "worker" ], "owner": { "login": "Picovoice", "avatar_url": "https://avatars.githubusercontent.com/u/37164515?v=4", "html_url": "https://github.com/Picovoice" } }, { "id": 588019194, "name": "BanglaSpeech2Text", "full_name": "shhossain/BanglaSpeech2Text", "url": "https://github.com/shhossain/BanglaSpeech2Text", "description": "BanglaSpeech2Text: An open-source offline speech-to-text package for Bangla language. Fine-tuned on the latest whisper speech to text model for optimal performance.", "stars": 122, "forks": 19, "watches": 122, "language": "Python", "license": "Apache License 2.0", "topics": [ "bangla", "bangla-asr", "bangla-automatic-speech-recognition", "bangla-speech-recognition", "bangla-speech-to-text", "bangla-voice-recognition", "deep-learning", "hacktoberfest", "machine-learning", "pytorch", "speech", "speech-recognition", "speech-to-text", "transformer", "voice-recognition", "whisper", "whisper-model" ], "owner": { "login": "shhossain", "avatar_url": "https://avatars.githubusercontent.com/u/80335059?v=4", "html_url": "https://github.com/shhossain" } }, { "id": 599580744, "name": "WhisperInput", "full_name": "alex-vt/WhisperInput", "url": "https://github.com/alex-vt/WhisperInput", "description": "Offline voice input panel \u0026 keyboard with punctuation for Android.", "stars": 113, "forks": 20, "watches": 113, "language": "Java", "license": "MIT License", "topics": [ "android-app", "offline", "speech-recognition", "speech-to-text", "whisper-ai" ], "owner": { "login": "alex-vt", "avatar_url": "https://avatars.githubusercontent.com/u/6236091?v=4", "html_url": "https://github.com/alex-vt" } }, { "id": 489349966, "name": "Aniemore", "full_name": "aniemore/Aniemore", "url": "https://github.com/aniemore/Aniemore", "description": "Emotions recognition from audio and text files (only russian language)", "stars": 81, "forks": 8, "watches": 81, "language": "Python", "license": "MIT License", "topics": [ "artificial-intelligence", "deep-learning", "emotion-recognition", "machine-learning", "package", "python", "russian-language", "speech-recognition", "speech-to-text", "text-classification", "voice-classfication" ], "owner": { "login": "aniemore", "avatar_url": "https://avatars.githubusercontent.com/u/105057095?v=4", "html_url": "https://github.com/aniemore" } }, { "id": 999434916, "name": "ai-agents-security", "full_name": "LLAMATOR-Core/ai-agents-security", "url": "https://github.com/LLAMATOR-Core/ai-agents-security", "description": "Инициатива, посвященная безопасности агентов на базе искусственного интеллекта", "stars": 51, "forks": 8, "watches": 51, "language": "Jupyter Notebook", "license": "Apache License 2.0", "topics": [ "agents", "ai", "ai-safety", "ai-security", "chatbot", "crewai", "function-calling", "langchain", "llm", "mcp", "owasp", "rag" ], "owner": { "login": "LLAMATOR-Core", "avatar_url": "https://avatars.githubusercontent.com/u/204762027?v=4", "html_url": "https://github.com/LLAMATOR-Core" } }, { "id": 952406345, "name": "agentic-ai", "full_name": "mahmoudrabie/agentic-ai", "url": "https://github.com/mahmoudrabie/agentic-ai", "description": "Agentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.", "stars": 140, "forks": 4, "watches": 140, "language": "", "license": "MIT License", "topics": [ "agentic-ai", "ai-agents", "ai-benchmarks", "ai-evaluation", "ai-research", "ai-safety", "ai-security", "automation", "autonomous-agents", "awesome-list", "foundation-models", "llm", "llm-agents", "mcp", "model-context-protocol", "multi-agent-systems", "planning", "rag", "reasoning", "software-engineering" ], "owner": { "login": "mahmoudrabie", "avatar_url": "https://avatars.githubusercontent.com/u/2697012?v=4", "html_url": "https://github.com/mahmoudrabie" } }, { "id": 316496258, "name": "lingua-go", "full_name": "pemistahl/lingua-go", "url": "https://github.com/pemistahl/lingua-go", "description": "The most accurate natural language detection library for Go, suitable for short text and mixed-language text", "stars": 1343, "forks": 79, "watches": 1343, "language": "Go", "license": "Apache License 2.0", "topics": [ "go", "golang-library", "language-classification", "language-detection", "language-identification", "language-modeling", "language-processing", "language-recognition", "natural-language-processing", "nlp", "nlp-machine-learning", "text-processing" ], "owner": { "login": "pemistahl", "avatar_url": "https://avatars.githubusercontent.com/u/1145043?v=4", "html_url": "https://github.com/pemistahl" } }, { "id": 398111584, "name": "rliable", "full_name": "google-research/rliable", "url": "https://github.com/google-research/rliable", "description": "[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.", "stars": 870, "forks": 50, "watches": 870, "language": "Jupyter Notebook", "license": "Apache License 2.0", "topics": [ "benchmarking", "evaluation-metrics", "google", "machine-learning", "reinforcement-learning", "rl" ], "owner": { "login": "google-research", "avatar_url": "https://avatars.githubusercontent.com/u/43830688?v=4", "html_url": "https://github.com/google-research" } }, { "id": 684388144, "name": "panopticon", "full_name": "Panopticon-AI-team/panopticon", "url": "https://github.com/Panopticon-AI-team/panopticon", "description": "A wargaming platform compatible with reinforcement learning agents ", "stars": 97, "forks": 21, "watches": 97, "language": "TypeScript", "license": "Apache License 2.0", "topics": [ "agent-based-simulation", "ai", "artificial-intelligence", "game-engine", "machine-learning", "military", "ml", "modeling-and-simulation", "operations-research", "reinforcement-learning", "reinforcement-learning-environments", "rl", "simulation", "simulation-modeling", "wargaming", "wargaming-api" ], "owner": { "login": "Panopticon-AI-team", "avatar_url": "https://avatars.githubusercontent.com/u/180141950?v=4", "html_url": "https://github.com/Panopticon-AI-team" } }, { "id": 621148052, "name": "speech-to-text", "full_name": "reriiasu/speech-to-text", "url": "https://github.com/reriiasu/speech-to-text", "description": "Real-time transcription using faster-whisper", "stars": 615, "forks": 100, "watches": 615, "language": "HTML", "license": "MIT License", "topics": [ "faster-whisper", "openai", "speech-recognition", "speech-to-text", "voice-recognition", "whisper" ], "owner": { "login": "reriiasu", "avatar_url": "https://avatars.githubusercontent.com/u/78286212?v=4", "html_url": "https://github.com/reriiasu" } }, { "id": 703720692, "name": "LLM-Minutes-of-Meeting", "full_name": "inboxpraveen/LLM-Minutes-of-Meeting", "url": "https://github.com/inboxpraveen/LLM-Minutes-of-Meeting", "description": "A tool that transforms audio or video files into text transcripts and generates concise meeting minutes. Stay organized and efficient in your meetings, and get ready for Phase 2 where we'll be open for contributions to enable real-time meeting transcription! ", "stars": 170, "forks": 19, "watches": 170, "language": "HTML", "license": "MIT License", "topics": [ "huggingface", "huggingface-transformers", "llm", "llm-inference", "meeting-minutes", "minutes-of-meeting", "natural-language-processing", "nlp", "python", "speech-recognition", "speech-to-text", "transformers", "translation", "wav2vec2", "web", "web-application", "webapplication", "whisper", "whisper-ai" ], "owner": { "login": "inboxpraveen", "avatar_url": "https://avatars.githubusercontent.com/u/43789050?v=4", "html_url": "https://github.com/inboxpraveen" } }, { "id": 815984855, "name": "whisper-overlay", "full_name": "oddlama/whisper-overlay", "url": "https://github.com/oddlama/whisper-overlay", "description": "A wayland overlay providing speech-to-text functionality for any application via a global push-to-talk hotkey", "stars": 87, "forks": 18, "watches": 87, "language": "Rust", "license": "MIT License", "topics": [ "faster-whisper", "hyprland", "realtime", "speech-recognition", "speech-to-text", "wayland", "whisper", "wlroots" ], "owner": { "login": "oddlama", "avatar_url": "https://avatars.githubusercontent.com/u/31919558?v=4", "html_url": "https://github.com/oddlama" } }, { "id": 574360029, "name": "SpeeQ", "full_name": "msalhab96/SpeeQ", "url": "https://github.com/msalhab96/SpeeQ", "description": "A framework for automatic speech recognition", "stars": 51, "forks": 5, "watches": 51, "language": "Python", "license": "MIT License", "topics": [ "speech", "speech-processing", "speech-recognition", "speech-to-text" ], "owner": { "login": "msalhab96", "avatar_url": "https://avatars.githubusercontent.com/u/61272193?v=4", "html_url": "https://github.com/msalhab96" } }, { "id": 169975410, "name": "leon", "full_name": "leon-ai/leon", "url": "https://github.com/leon-ai/leon", "description": "🧠 Leon is your open-source personal assistant.", "stars": 17281, "forks": 1448, "watches": 17281, "language": "TypeScript", "license": "MIT License", "topics": [ "ai", "ai-agent", "ai-assistant", "artificial-intelligence", "assistant", "automation", "bot", "chatbot", "leon", "nodejs", "offline", "personal-assistant", "privacy", "python", "speech-recognition", "speech-synthesis", "speech-to-text", "text-to-speech", "virtual-assistant", "voice-assistant" ], "owner": { "login": "leon-ai", "avatar_url": "https://avatars.githubusercontent.com/u/35167224?v=4", "html_url": "https://github.com/leon-ai" } }, { "id": 748528018, "name": "argmax-oss-swift", "full_name": "argmaxinc/argmax-oss-swift", "url": "https://github.com/argmaxinc/argmax-oss-swift", "description": "On-device Speech AI for Apple Silicon", "stars": 6153, "forks": 566, "watches": 6153, "language": "Swift", "license": "MIT License", "topics": [ "inference", "ios", "macos", "pyannote", "qwen3-tts", "speaker-diarization", "speakerkit", "speech-recognition", "speech-to-text", "swift", "text-to-speech", "transformers", "ttskit", "whisper", "whisperkit" ], "owner": { "login": "argmaxinc", "avatar_url": "https://avatars.githubusercontent.com/u/150409474?v=4", "html_url": "https://github.com/argmaxinc" } }, { "id": 572996960, "name": "mltu", "full_name": "pythonlessons/mltu", "url": "https://github.com/pythonlessons/mltu", "description": "Machine Learning Training Utilities (for TensorFlow and PyTorch)", "stars": 253, "forks": 146, "watches": 253, "language": "Python", "license": "MIT License", "topics": [ "machine-learning", "object-detection", "ocr", "pytorch", "speech-recognition", "speech-to-text", "tensorflow", "yolov8" ], "owner": { "login": "pythonlessons", "avatar_url": "https://avatars.githubusercontent.com/u/43852392?v=4", "html_url": "https://github.com/pythonlessons" } }, { "id": 763298631, "name": "whisper-clip", "full_name": "gustavostz/whisper-clip", "url": "https://github.com/gustavostz/whisper-clip", "description": "WhisperClip simplifies your life by automatically transcribing audio recordings and saving the text directly to your clipboard. With just a click of a button, you can effortlessly convert spoken words into written text, ready to be pasted wherever you need it. This application harnesses the power of OpenAI’s Whisper for free.", "stars": 137, "forks": 16, "watches": 137, "language": "Python", "license": "MIT License", "topics": [ "audio-processing", "audio-transcription", "clipboard", "openai", "productivity", "productivity-tools", "python", "speech-recognition", "speech-to-text", "whisper", "whisper-ai" ], "owner": { "login": "gustavostz", "avatar_url": "https://avatars.githubusercontent.com/u/48111506?v=4", "html_url": "https://github.com/gustavostz" } }, { "id": 138948548, "name": "web-speech-cognitive-services", "full_name": "compulim/web-speech-cognitive-services", "url": "https://github.com/compulim/web-speech-cognitive-services", "description": "Polyfill Web Speech API with Cognitive Services for both speech-to-text and text-to-speech service.", "stars": 70, "forks": 19, "watches": 70, "language": "JavaScript", "license": "MIT License", "topics": [ "azure", "cognitive-services", "speech-recognition", "speech-synthesis", "speech-to-text", "text-to-speech" ], "owner": { "login": "compulim", "avatar_url": "https://avatars.githubusercontent.com/u/1622400?v=4", "html_url": "https://github.com/compulim" } }, { "id": 833995205, "name": "OCRM_survey", "full_name": "RayYoh/OCRM_survey", "url": "https://github.com/RayYoh/OCRM_survey", "description": "A Survey of Embodied Learning for Object-Centric Robotic Manipulation", "stars": 255, "forks": 14, "watches": 255, "language": "", "license": "MIT License", "topics": [ "embodied-ai", "manipulation", "robot-learning", "robotics" ], "owner": { "login": "RayYoh", "avatar_url": "https://avatars.githubusercontent.com/u/35106336?v=4", "html_url": "https://github.com/RayYoh" } }, { "id": 166540770, "name": "stable-baselines", "full_name": "Stable-Baselines-Team/stable-baselines", "url": "https://github.com/Stable-Baselines-Team/stable-baselines", "description": "Mirror of Stable-Baselines: a fork of OpenAI Baselines, implementations of reinforcement learning algorithms ", "stars": 307, "forks": 61, "watches": 307, "language": "Python", "license": "MIT License", "topics": [ "baselines", "gym", "machine-learning", "openai", "openai-gym", "python", "reinforcement-learning", "rl", "stable-baselines", "toolbox" ], "owner": { "login": "Stable-Baselines-Team", "avatar_url": "https://avatars.githubusercontent.com/u/46841238?v=4", "html_url": "https://github.com/Stable-Baselines-Team" } }, { "id": 39766464, "name": "artyom.js", "full_name": "sdkcarlos/artyom.js", "url": "https://github.com/sdkcarlos/artyom.js", "description": "A voice control - voice commands - speech recognition and speech synthesis javascript library. Create your own siri,google now or cortana with Google Chrome within your website.", "stars": 1268, "forks": 364, "watches": 1268, "language": "JavaScript", "license": "MIT License", "topics": [ "recognition", "speech-recognition", "speech-synthesis", "speech-to-text", "voice-commands" ], "owner": { "login": "sdkcarlos", "avatar_url": "https://avatars.githubusercontent.com/u/11634719?v=4", "html_url": "https://github.com/sdkcarlos" } }, { "id": 992379568, "name": "PreenCut", "full_name": "roothch/PreenCut", "url": "https://github.com/roothch/PreenCut", "description": "AI-Powered Video Retrieval \u0026 Clipping Tool", "stars": 401, "forks": 64, "watches": 401, "language": "Python", "license": "MIT License", "topics": [ "asr", "llm", "speech-recognition", "speech-to-text", "video-analysis", "video-clip", "video-editing", "video-retrieval", "video-search" ], "owner": { "login": "roothch", "avatar_url": "https://avatars.githubusercontent.com/u/49117938?v=4", "html_url": "https://github.com/roothch" } }, { "id": 1076931447, "name": "parakeet-rs", "full_name": "altunenes/parakeet-rs", "url": "https://github.com/altunenes/parakeet-rs", "description": "very fast speech-to-text, diarization, streaming (even in CPU) with NVIDIA Parakeet in Rust", "stars": 294, "forks": 45, "watches": 294, "language": "Rust", "license": "MIT License", "topics": [ "asr", "automatic-speech-recognition", "onnx", "parakeet", "speaker-diarization", "speaker-identification", "speech", "speech-recognition", "speech-to-text" ], "owner": { "login": "altunenes", "avatar_url": "https://avatars.githubusercontent.com/u/54986652?v=4", "html_url": "https://github.com/altunenes" } }, { "id": 938991594, "name": "LiteASR", "full_name": "efeslab/LiteASR", "url": "https://github.com/efeslab/LiteASR", "description": "[EMNLP Main '25] LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation", "stars": 153, "forks": 5, "watches": 153, "language": "Python", "license": "Apache License 2.0", "topics": [ "asr", "speech", "speech-recognition", "speech-to-text", "whisper" ], "owner": { "login": "efeslab", "avatar_url": "https://avatars.githubusercontent.com/u/35610460?v=4", "html_url": "https://github.com/efeslab" } }, { "id": 178269980, "name": "MAX-Speech-to-Text-Converter", "full_name": "IBM/MAX-Speech-to-Text-Converter", "url": "https://github.com/IBM/MAX-Speech-to-Text-Converter", "description": "Converts spoken words into text form.", "stars": 77, "forks": 32, "watches": 77, "language": "Python", "license": "Apache License 2.0", "topics": [ "ai", "codait", "docker-image", "ibm", "machine-learning", "natural-language-processing", "speech-recognition", "speech-to-text" ], "owner": { "login": "IBM", "avatar_url": "https://avatars.githubusercontent.com/u/1459110?v=4", "html_url": "https://github.com/IBM" } }, { "id": 540469444, "name": "whisper_mic", "full_name": "mallorbc/whisper_mic", "url": "https://github.com/mallorbc/whisper_mic", "description": "Project that allows one to use a microphone with OpenAI whisper.", "stars": 789, "forks": 171, "watches": 789, "language": "Python", "license": "MIT License", "topics": [ "microphone", "speech-recognition", "speech-to-text", "whisper", "whisper-ai", "whisper-api" ], "owner": { "login": "mallorbc", "avatar_url": "https://avatars.githubusercontent.com/u/39721523?v=4", "html_url": "https://github.com/mallorbc" } }, { "id": 3026811, "name": "K6nele", "full_name": "Kaljurand/K6nele", "url": "https://github.com/Kaljurand/K6nele", "description": "An Android app that offers speech-to-text user interfaces to other apps", "stars": 290, "forks": 80, "watches": 290, "language": "Java", "license": "Apache License 2.0", "topics": [ "android", "estonian", "input-method-editor", "speech-recognition", "speech-to-text" ], "owner": { "login": "Kaljurand", "avatar_url": "https://avatars.githubusercontent.com/u/490600?v=4", "html_url": "https://github.com/Kaljurand" } }, { "id": 366391110, "name": "discord-speech-recognition", "full_name": "Rei-x/discord-speech-recognition", "url": "https://github.com/Rei-x/discord-speech-recognition", "description": "Speech to text extension for discord.js", "stars": 63, "forks": 22, "watches": 63, "language": "TypeScript", "license": "MIT License", "topics": [ "discord", "discord-bot", "discord-js", "hacktoberfest", "speech-recognition", "speech-to-text" ], "owner": { "login": "Rei-x", "avatar_url": "https://avatars.githubusercontent.com/u/38581479?v=4", "html_url": "https://github.com/Rei-x" } }, { "id": 170161374, "name": "computervision-recipes", "full_name": "microsoft/computervision-recipes", "url": "https://github.com/microsoft/computervision-recipes", "description": "Best Practices, code samples, and documentation for Computer Vision.", "stars": 9856, "forks": 1205, "watches": 9856, "language": "Jupyter Notebook", "license": "MIT License", "topics": [ "artificial-intelligence", "azure", "computer-vision", "convolutional-neural-networks", "data-science", "deep-learning", "image-classification", "image-processing", "jupyter-notebook", "kubernetes", "machine-learning", "microsoft", "object-detection", "operationalization", "python", "similarity", "tutorial" ], "owner": { "login": "microsoft", "avatar_url": "https://avatars.githubusercontent.com/u/6154722?v=4", "html_url": "https://github.com/microsoft" } }, { "id": 79945774, "name": "reinforcement_learning", "full_name": "yrlu/reinforcement_learning", "url": "https://github.com/yrlu/reinforcement_learning", "description": "Implementation of selected reinforcement learning algorithms in Tensorflow. A3C, DDPG, REINFORCE, DQN, etc.", "stars": 154, "forks": 48, "watches": 154, "language": "Python", "license": "MIT License", "topics": [ "openai-gym", "python", "reinforcement-learning", "rl", "tensorflow" ], "owner": { "login": "yrlu", "avatar_url": "https://avatars.githubusercontent.com/u/2658324?v=4", "html_url": "https://github.com/yrlu" } }, { "id": 615270502, "name": "whisper-ctranslate2", "full_name": "Softcatala/whisper-ctranslate2", "url": "https://github.com/Softcatala/whisper-ctranslate2", "description": "Whisper command line client compatible with original OpenAI client based on CTranslate2.", "stars": 1309, "forks": 124, "watches": 1309, "language": "Python", "license": "MIT License", "topics": [ "openai-", "openai-whisper", "speech-recognition", "speech-to-text", "whisper" ], "owner": { "login": "Softcatala", "avatar_url": "https://avatars.githubusercontent.com/u/978352?v=4", "html_url": "https://github.com/Softcatala" } }, { "id": 66981433, "name": "sonus", "full_name": "evancohen/sonus", "url": "https://github.com/evancohen/sonus", "description": ":speech_balloon: /so.nus/ STT (speech to text) for Node with offline hotword detection", "stars": 638, "forks": 77, "watches": 638, "language": "JavaScript", "license": "MIT License", "topics": [ "alexa", "hotword-detection", "keyword-spotting", "node", "speech", "speech-recognition", "speech-to-text", "stt", "voice-control", "voice-recognition" ], "owner": { "login": "evancohen", "avatar_url": "https://avatars.githubusercontent.com/u/1198365?v=4", "html_url": "https://github.com/evancohen" } }, { "id": 683385017, "name": "docker-whisperX", "full_name": "jim60105/docker-whisperX", "url": "https://github.com/jim60105/docker-whisperX", "description": "Dockerfile for WhisperX: Automatic Speech Recognition with Word-Level Timestamps and Speaker Diarization (Dockerfile, CI image build and test)", "stars": 446, "forks": 49, "watches": 446, "language": "Dockerfile", "license": "MIT License", "topics": [ "asr", "docker-image", "dockerfile", "speech", "speech-recognition", "speech-to-text", "whisper" ], "owner": { "login": "jim60105", "avatar_url": "https://avatars.githubusercontent.com/u/16995691?v=4", "html_url": "https://github.com/jim60105" } }, { "id": 1203724189, "name": "mimic-video", "full_name": "mimic-video/mimic-video", "url": "https://github.com/mimic-video/mimic-video", "description": "Video-Action Models for Generalizable Robot Control Beyond VLAs", "stars": 261, "forks": 24, "watches": 261, "language": "Python", "license": "Apache License 2.0", "topics": [ "robot-learning", "robotics", "vam", "video-action-models", "vla" ], "owner": { "login": "mimic-video", "avatar_url": "https://avatars.githubusercontent.com/u/249995274?v=4", "html_url": "https://github.com/mimic-video" } }, { "id": 711655390, "name": "pyRobBot", "full_name": "paulovcmedeiros/pyRobBot", "url": "https://github.com/paulovcmedeiros/pyRobBot", "description": "Chat with GPT LLMs over voice, UI \u0026 terminal, all with access to the internet. Powered by OpenAI.", "stars": 144, "forks": 84, "watches": 144, "language": "Python", "license": "MIT License", "topics": [ "artificial-intelligence", "chatbot", "chatbot-application", "chatgpt", "chatgpt-api", "gpt", "latest-events", "openai-api", "personal-assistant", "python", "python-chat-application", "python-chatbot", "speech-recognition", "speech-to-text", "streamlit", "text-to-speech", "voice-chat-bot", "voice-gpt", "voice-recognition", "websearch" ], "owner": { "login": "paulovcmedeiros", "avatar_url": "https://avatars.githubusercontent.com/u/6304559?v=4", "html_url": "https://github.com/paulovcmedeiros" } }, { "id": 638068295, "name": "Generative_Deep_Learning_2nd_Edition", "full_name": "rickiepark/Generative_Deep_Learning_2nd_Edition", "url": "https://github.com/rickiepark/Generative_Deep_Learning_2nd_Edition", "description": "\u003c만들면서 배우는 생성 AI 2판\u003e의 코드 저장소", "stars": 66, "forks": 36, "watches": 66, "language": "Jupyter Notebook", "license": "Apache License 2.0", "topics": [ "deep-learning", "gan", "generative-ai", "gpt", "multimodal", "stable-diffusion", "transformer", "vae" ], "owner": { "login": "rickiepark", "avatar_url": "https://avatars.githubusercontent.com/u/18256853?v=4", "html_url": "https://github.com/rickiepark" } }, { "id": 641795100, "name": "FunClip", "full_name": "modelscope/FunClip", "url": "https://github.com/modelscope/FunClip", "description": "Open-source, accurate and easy-to-use video speech recognition \u0026 clipping tool. LLM-based AI clipping integrated.", "stars": 5719, "forks": 694, "watches": 5719, "language": "Python", "license": "MIT License", "topics": [ "ai-tools", "ai-video-editing", "content-creation", "gradio", "llm", "speech-recognition", "speech-to-text", "subtitles-generator", "video-clip", "video-editing", "video-processing", "video-subtitles" ], "owner": { "login": "modelscope", "avatar_url": "https://avatars.githubusercontent.com/u/109945100?v=4", "html_url": "https://github.com/modelscope" } }, { "id": 597109271, "name": "whisper.net", "full_name": "sandrohanea/whisper.net", "url": "https://github.com/sandrohanea/whisper.net", "description": "Whisper.net. Speech to text made simple using Whisper Models", "stars": 919, "forks": 134, "watches": 919, "language": "C#", "license": "MIT License", "topics": [ "cross-platform", "dotnet", "dotnetcore", "hacktoberfest", "speech-recognition", "speech-to-text", "translation" ], "owner": { "login": "sandrohanea", "avatar_url": "https://avatars.githubusercontent.com/u/40202887?v=4", "html_url": "https://github.com/sandrohanea" } }, { "id": 143492492, "name": "speech-to-text-benchmark", "full_name": "Picovoice/speech-to-text-benchmark", "url": "https://github.com/Picovoice/speech-to-text-benchmark", "description": "speech to text benchmark framework", "stars": 692, "forks": 73, "watches": 692, "language": "Python", "license": "Apache License 2.0", "topics": [ "aws-transcribe", "cheetah", "deep-learning", "deep-neural-networks", "deepspeech", "edge-ai", "google-speech-to-text", "mozilla-deepspeech", "offline", "picovoice", "pocketsphinx", "privacy", "speech-recognition", "speech-to-text", "voice-recognition" ], "owner": { "login": "Picovoice", "avatar_url": "https://avatars.githubusercontent.com/u/37164515?v=4", "html_url": "https://github.com/Picovoice" } }, { "id": 138575203, "name": "voice-overlay-ios", "full_name": "algolia/voice-overlay-ios", "url": "https://github.com/algolia/voice-overlay-ios", "description": "🗣 An overlay that gets your user’s voice permission and input as text in a customizable UI", "stars": 556, "forks": 59, "watches": 556, "language": "Swift", "license": "MIT License", "topics": [ "chatbots", "conversation", "conversational-bots", "conversational-interface", "conversational-ui", "input", "instant-search", "instantsearch", "ios", "objective-c", "overlay", "permissions", "search", "speech-recognition", "speech-to-text", "swift", "voice", "voice-assistant", "voice-recognition", "voicetext" ], "owner": { "login": "algolia", "avatar_url": "https://avatars.githubusercontent.com/u/2034458?v=4", "html_url": "https://github.com/algolia" } }, { "id": 963929810, "name": "onnx-asr", "full_name": "istupakov/onnx-asr", "url": "https://github.com/istupakov/onnx-asr", "description": "A lightweight Python package for Automatic Speech Recognition using ONNX models", "stars": 325, "forks": 31, "watches": 325, "language": "Python", "license": "MIT License", "topics": [ "asr", "lightweight", "onnx", "parakeet", "python", "speech-recognition", "speech-to-text", "stt", "whisper" ], "owner": { "login": "istupakov", "avatar_url": "https://avatars.githubusercontent.com/u/5564765?v=4", "html_url": "https://github.com/istupakov" } }, { "id": 226546106, "name": "deep_avsr", "full_name": "smeetrs/deep_avsr", "url": "https://github.com/smeetrs/deep_avsr", "description": "A PyTorch implementation of the Deep Audio-Visual Speech Recognition paper.", "stars": 244, "forks": 42, "watches": 244, "language": "Python", "license": "MIT License", "topics": [ "audio-visual-speech-recognition", "automatic-speech-recognition", "lip-reading", "speech-recognition", "speech-to-text", "visual-speech-recognition" ], "owner": { "login": "smeetrs", "avatar_url": "https://avatars.githubusercontent.com/u/29375430?v=4", "html_url": "https://github.com/smeetrs" } }, { "id": 1063408813, "name": "kroko-onnx", "full_name": "kroko-ai/kroko-onnx", "url": "https://github.com/kroko-ai/kroko-onnx", "description": "Kroko ASR - Speech-to-text", "stars": 153, "forks": 11, "watches": 153, "language": "C++", "license": "Apache License 2.0", "topics": [ "ai", "asr", "asr-innovation-tech", "asr-libraries", "asr-model", "cpp", "python", "speech", "speech-recognition", "speech-to-text" ], "owner": { "login": "kroko-ai", "avatar_url": "https://avatars.githubusercontent.com/u/231460289?v=4", "html_url": "https://github.com/kroko-ai" } }, { "id": 519789131, "name": "crx-live-translate", "full_name": "botbahlul/crx-live-translate", "url": "https://github.com/botbahlul/crx-live-translate", "description": "Chrome/Edge BROWSER EXTENSION that can RECOGNIZE any live audio/video streaming then TRANSLATE it for FREE (using unofficial online Google Translate API) then display it as LIVE CAPTION / LIVE SUBTITLE!", "stars": 116, "forks": 12, "watches": 116, "language": "JavaScript", "license": "MIT License", "topics": [ "auto-caption", "auto-subtitle", "browser-extension", "chrome", "edge", "google-translate-api", "javascript", "speech-recognition", "speech-to-text", "voice-recognition", "webkit-speech-recognition", "webkitspeechrecognition" ], "owner": { "login": "botbahlul", "avatar_url": "https://avatars.githubusercontent.com/u/88623122?v=4", "html_url": "https://github.com/botbahlul" } }, { "id": 776527409, "name": "SimplerEnv", "full_name": "simpler-env/SimplerEnv", "url": "https://github.com/simpler-env/SimplerEnv", "description": "Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)", "stars": 1079, "forks": 191, "watches": 1079, "language": "Jupyter Notebook", "license": "MIT License", "topics": [ "computer-vision", "embodied-ai", "real2sim", "reinforcement-learning", "robot-learning", "robot-manipulation", "robotics", "robotics-benchmark", "robotics-simulation" ], "owner": { "login": "simpler-env", "avatar_url": "https://avatars.githubusercontent.com/u/164236909?v=4", "html_url": "https://github.com/simpler-env" } }, { "id": 511682460, "name": "maxvit", "full_name": "google-research/maxvit", "url": "https://github.com/google-research/maxvit", "description": "[ECCV 2022] Official repository for \"MaxViT: Multi-Axis Vision Transformer\". SOTA foundation models for classification, detection, segmentation, image quality, and generative modeling...", "stars": 499, "forks": 39, "watches": 499, "language": "Jupyter Notebook", "license": "Apache License 2.0", "topics": [ "architecture", "classification", "cnn", "computer-vision", "image", "image-processing", "mlp", "object-detection", "resnet", "segmentation", "transformer", "transformer-architecture", "vision-transformer" ], "owner": { "login": "google-research", "avatar_url": "https://avatars.githubusercontent.com/u/43830688?v=4", "html_url": "https://github.com/google-research" } }, { "id": 159752575, "name": "cherry", "full_name": "learnables/cherry", "url": "https://github.com/learnables/cherry", "description": "A PyTorch Library for Reinforcement Learning Research", "stars": 198, "forks": 31, "watches": 198, "language": "Python", "license": "Apache License 2.0", "topics": [ "learning", "pytorch", "reinforcement", "reinforcement-learning", "rl" ], "owner": { "login": "learnables", "avatar_url": "https://avatars.githubusercontent.com/u/54878124?v=4", "html_url": "https://github.com/learnables" } }, { "id": 74182569, "name": "kur", "full_name": "deepgram/kur", "url": "https://github.com/deepgram/kur", "description": "Descriptive Deep Learning", "stars": 822, "forks": 108, "watches": 822, "language": "Python", "license": "Apache License 2.0", "topics": [ "deep-learning", "deep-learning-tutorial", "deep-neural-networks", "image-recognition", "machine-learning", "neural-network", "neural-networks", "speech-recognition", "speech-to-text" ], "owner": { "login": "deepgram", "avatar_url": "https://avatars.githubusercontent.com/u/17422641?v=4", "html_url": "https://github.com/deepgram" } }, { "id": 366871642, "name": "deepgram-python-sdk", "full_name": "deepgram/deepgram-python-sdk", "url": "https://github.com/deepgram/deepgram-python-sdk", "description": "Official Python SDK for Deepgram.", "stars": 436, "forks": 131, "watches": 436, "language": "Python", "license": "MIT License", "topics": [ "asr", "automated-speech-recognition", "deepgram", "python", "speech-recognition", "speech-to-text", "text-to-speech", "voice-agent", "voice-ai" ], "owner": { "login": "deepgram", "avatar_url": "https://avatars.githubusercontent.com/u/17422641?v=4", "html_url": "https://github.com/deepgram" } }, { "id": 346152074, "name": "vid2cleantxt", "full_name": "pszemraj/vid2cleantxt", "url": "https://github.com/pszemraj/vid2cleantxt", "description": "Python API \u0026 command-line tool to easily transcribe speech-based video files into clean text", "stars": 226, "forks": 29, "watches": 226, "language": "Jupyter Notebook", "license": "Apache License 2.0", "topics": [ "audio", "audio-processing", "keyword", "keyword-extraction", "nlp", "python", "sentence", "sentence-boundary-detection", "speech", "speech-recognition", "speech-to-text", "spelling-correction", "transcription", "transformer", "video", "video-processing", "video-summarisation", "video-summarization", "wav2vec2", "whisper" ], "owner": { "login": "pszemraj", "avatar_url": "https://avatars.githubusercontent.com/u/74869040?v=4", "html_url": "https://github.com/pszemraj" } }, { "id": 1137351097, "name": "DeLive", "full_name": "XimilalaXiang/DeLive", "url": "https://github.com/XimilalaXiang/DeLive", "description": "System audio capture + multi-provider ASR + local-first AI review workspace. Floating live captions, 12 ASR backends, 60+ languages, AI summary/chat/mindmap, Open API, MCP server, and Agent Skill.", "stars": 206, "forks": 8, "watches": 206, "language": "TypeScript", "license": "Apache License 2.0", "topics": [ "agent-skill", "ai", "asr", "captions", "desktop-app", "electron", "groq", "linux", "local-first", "mcp", "open-api", "realtime", "soniox", "speech-recognition", "speech-to-text", "stt", "tailwindcss", "transcription", "typescript", "windows" ], "owner": { "login": "XimilalaXiang", "avatar_url": "https://avatars.githubusercontent.com/u/199751282?v=4", "html_url": "https://github.com/XimilalaXiang" } }, { "id": 794050307, "name": "transcribe.js", "full_name": "TranscribeJs/transcribe.js", "url": "https://github.com/TranscribeJs/transcribe.js", "description": "Monorepo for Transcribe.js", "stars": 53, "forks": 4, "watches": 53, "language": "JavaScript", "license": "MIT License", "topics": [ "javascript", "speech", "speech-recognition", "speech-to-text", "transcribe", "wasm", "whisper" ], "owner": { "login": "TranscribeJs", "avatar_url": "https://avatars.githubusercontent.com/u/167979697?v=4", "html_url": "https://github.com/TranscribeJs" } }, { "id": 884096620, "name": "tidybot2", "full_name": "jimmyyhwu/tidybot2", "url": "https://github.com/jimmyyhwu/tidybot2", "description": "TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning", "stars": 591, "forks": 64, "watches": 591, "language": "Python", "license": "MIT License", "topics": [ "holonomic", "imitation-learning", "mobile-manipulation", "robot-learning", "robotics" ], "owner": { "login": "jimmyyhwu", "avatar_url": "https://avatars.githubusercontent.com/u/6546428?v=4", "html_url": "https://github.com/jimmyyhwu" } }, { "id": 973184191, "name": "EasyCarla-RL", "full_name": "silverwingsbot/EasyCarla-RL", "url": "https://github.com/silverwingsbot/EasyCarla-RL", "description": "A simple and easy-to-use autonomous driving environment for reinforcement learning, based on the CARLA simulator.", "stars": 252, "forks": 23, "watches": 252, "language": "Python", "license": "Apache License 2.0", "topics": [ "autonomous-driving", "autonomous-vehicles", "carla", "carla-simulator", "decision-making", "gym", "offline-reinforcement-learning", "reinforcement-learning", "rl", "self-driving" ], "owner": { "login": "silverwingsbot", "avatar_url": "https://avatars.githubusercontent.com/u/206585040?v=4", "html_url": "https://github.com/silverwingsbot" } }, { "id": 926285456, "name": "chaplin", "full_name": "amanvirparhar/chaplin", "url": "https://github.com/amanvirparhar/chaplin", "description": "A real-time silent speech recognition tool.", "stars": 735, "forks": 84, "watches": 735, "language": "Python", "license": "MIT License", "topics": [ "auto-avsr", "avsr", "llm", "ollama", "speech-recognition", "speech-to-text", "vsr" ], "owner": { "login": "amanvirparhar", "avatar_url": "https://avatars.githubusercontent.com/u/46307450?v=4", "html_url": "https://github.com/amanvirparhar" } }, { "id": 340475238, "name": "vosk-browser", "full_name": "ccoreilly/vosk-browser", "url": "https://github.com/ccoreilly/vosk-browser", "description": "A speech recognition library running in the browser thanks to a WebAssembly build of Vosk", "stars": 517, "forks": 87, "watches": 517, "language": "JavaScript", "license": "Apache License 2.0", "topics": [ "asr", "kaldi", "speech-recognition", "speech-to-text", "stt", "typescript", "vosk", "wasm", "webassembly" ], "owner": { "login": "ccoreilly", "avatar_url": "https://avatars.githubusercontent.com/u/11149784?v=4", "html_url": "https://github.com/ccoreilly" } }, { "id": 454479855, "name": "rl", "full_name": "pytorch/rl", "url": "https://github.com/pytorch/rl", "description": "A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.", "stars": 3450, "forks": 456, "watches": 3450, "language": "Python", "license": "MIT License", "topics": [ "ai", "control", "decision-making", "distributed-computing", "machine-learning", "marl", "model-based-reinforcement-learning", "multi-agent-reinforcement-learning", "pytorch", "reinforcement-learning", "rl", "robotics", "torch" ], "owner": { "login": "pytorch", "avatar_url": "https://avatars.githubusercontent.com/u/21003710?v=4", "html_url": "https://github.com/pytorch" } }, { "id": 895253710, "name": "mlx-audio", "full_name": "Blaizzy/mlx-audio", "url": "https://github.com/Blaizzy/mlx-audio", "description": "A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.", "stars": 7148, "forks": 612, "watches": 7148, "language": "Python", "license": "MIT License", "topics": [ "apple-silicon", "audio-processing", "mlx", "multimodal", "speech-recognition", "speech-synthesis", "speech-to-text", "text-to-speech", "transformers" ], "owner": { "login": "Blaizzy", "avatar_url": "https://avatars.githubusercontent.com/u/23445657?v=4", "html_url": "https://github.com/Blaizzy" } }, { "id": 1202535739, "name": "feros", "full_name": "ferosai/feros", "url": "https://github.com/ferosai/feros", "description": "Open-source voice agent OS. Rust runtime, AI-driven builder, sub second latency. Self-host everything.", "stars": 93, "forks": 16, "watches": 93, "language": "Rust", "license": "Apache License 2.0", "topics": [ "agent-framework", "agentic-ai", "automation-platform", "conversational-ai", "enterprise-ai", "multi-language", "open-source", "real-time", "self-hosted", "speech-recognition", "speech-to-text", "text-to-speech", "vapi-alternative", "voice-agent", "voice-ai", "voice-orchestration" ], "owner": { "login": "ferosai", "avatar_url": "https://avatars.githubusercontent.com/u/273923828?v=4", "html_url": "https://github.com/ferosai" } }, { "id": 635012996, "name": "whisper_ros", "full_name": "mgonzs13/whisper_ros", "url": "https://github.com/mgonzs13/whisper_ros", "description": "Speech-to-Text based on SileroVAD + whisper.cpp (GGML Whisper) for ROS 2", "stars": 92, "forks": 24, "watches": 92, "language": "C++", "license": "MIT License", "topics": [ "asr", "automatic-speech-recognition", "ggml", "ros2", "speech-recognition", "speech-to-text", "vad", "voice-activity-detection", "whisper", "whisper-cpp" ], "owner": { "login": "mgonzs13", "avatar_url": "https://avatars.githubusercontent.com/u/25979134?v=4", "html_url": "https://github.com/mgonzs13" } }, { "id": 272269260, "name": "SIFTImageSimilarity", "full_name": "adumrewal/SIFTImageSimilarity", "url": "https://github.com/adumrewal/SIFTImageSimilarity", "description": "Interactive code for image similarity using SIFT algorithm", "stars": 230, "forks": 40, "watches": 230, "language": "Python", "license": "MIT License", "topics": [ "closeness", "comparison", "computer-vision", "duplicate-detection", "duplicate-images", "feature-extraction", "feature-mapping", "feature-matching", "homography", "image-analysis", "image-processing", "image-similarity", "object-detection", "opencv", "python", "resemblance", "sift", "sift-algorithm", "sift-descriptors", "sift-features" ], "owner": { "login": "adumrewal", "avatar_url": "https://avatars.githubusercontent.com/u/8917620?v=4", "html_url": "https://github.com/adumrewal" } }, { "id": 1238694393, "name": "mobilegym", "full_name": "Purewhiter/mobilegym", "url": "https://github.com/Purewhiter/mobilegym", "description": "MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training", "stars": 229, "forks": 31, "watches": 229, "language": "TypeScript", "license": "Apache License 2.0", "topics": [ "agent", "agents", "ai", "android", "automation", "benchmark", "gym", "llm", "llm-agents", "mobile-agent", "online-rl", "react", "reinforcement-learning", "rl", "rl-environment", "sim-to-real", "simulator", "typescript", "vlm" ], "owner": { "login": "Purewhiter", "avatar_url": "https://avatars.githubusercontent.com/u/54441452?v=4", "html_url": "https://github.com/Purewhiter" } }, { "id": 460867737, "name": "huggingsound", "full_name": "jonatasgrosman/huggingsound", "url": "https://github.com/jonatasgrosman/huggingsound", "description": "HuggingSound: A toolkit for speech-related tasks based on Hugging Face's tools", "stars": 470, "forks": 46, "watches": 470, "language": "Python", "license": "MIT License", "topics": [ "asr", "audio", "automatic-speech-recognition", "speech", "speech-recognition", "speech-to-text", "transformers" ], "owner": { "login": "jonatasgrosman", "avatar_url": "https://avatars.githubusercontent.com/u/5097052?v=4", "html_url": "https://github.com/jonatasgrosman" } }, { "id": 429978592, "name": "deepgram-dotnet-sdk", "full_name": "deepgram/deepgram-dotnet-sdk", "url": "https://github.com/deepgram/deepgram-dotnet-sdk", "description": "Official .NET SDK for Deepgram.", "stars": 53, "forks": 45, "watches": 53, "language": "C#", "license": "MIT License", "topics": [ "asr", "automated-speech-recognition", "deepgram", "dotnet", "hacktoberfest", "microsoft", "speech-recognition", "speech-to-text", "text-to-speech", "voice-agent", "voice-ai" ], "owner": { "login": "deepgram", "avatar_url": "https://avatars.githubusercontent.com/u/17422641?v=4", "html_url": "https://github.com/deepgram" } }, { "id": 992630802, "name": "ReinFlow", "full_name": "ReinFlow/ReinFlow", "url": "https://github.com/ReinFlow/ReinFlow", "description": "[NeurIPS 2025] Flow x RL. \"ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning\". Support VLAs e.g., Pi0, Pi0.5, GR00TN1.5. Fully open-sourced. ", "stars": 323, "forks": 30, "watches": 323, "language": "Python", "license": "MIT License", "topics": [ "actorcritic", "fine-tuning", "finetuning-rl", "finetuning-vision-models", "flow", "flowmatching", "locomotion", "manipulation", "onlinerl", "pi0", "policygradient", "post-training", "rl", "robot-learning", "robotics", "visuomotor", "vla" ], "owner": { "login": "ReinFlow", "avatar_url": "https://avatars.githubusercontent.com/u/212894921?v=4", "html_url": "https://github.com/ReinFlow" } }, { "id": 1179619512, "name": "shellward", "full_name": "jnMetaCode/shellward", "url": "https://github.com/jnMetaCode/shellward", "description": "AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + MCP server for Claude Code, Cursor, LangChain, Hermes Agent \u0026 more.", "stars": 100, "forks": 16, "watches": 100, "language": "TypeScript", "license": "Apache License 2.0", "topics": [ "agent-security", "ai-agent", "ai-firewall", "ai-safety", "ai-security", "claude-code", "cursor", "data-exfiltration", "dlp", "guardrails", "hermes-agent", "langchain", "llm-security", "mcp", "mcp-security", "openclaw", "pii-detection", "prompt-injection", "security", "shellward" ], "owner": { "login": "jnMetaCode", "avatar_url": "https://avatars.githubusercontent.com/u/12096460?v=4", "html_url": "https://github.com/jnMetaCode" } }, { "id": 299899780, "name": "gym-rs", "full_name": "MathisWellmann/gym-rs", "url": "https://github.com/MathisWellmann/gym-rs", "description": "OpenAI's Gym written in pure Rust for blazingly fast performance", "stars": 131, "forks": 19, "watches": 131, "language": "Rust", "license": "MIT License", "topics": [ "ai", "ml", "openai-gym", "reinforcement-learning", "rl" ], "owner": { "login": "MathisWellmann", "avatar_url": "https://avatars.githubusercontent.com/u/26856233?v=4", "html_url": "https://github.com/MathisWellmann" } }, { "id": 858357620, "name": "reverb", "full_name": "revdotcom/reverb", "url": "https://github.com/revdotcom/reverb", "description": "Open source inference code for Rev's model", "stars": 437, "forks": 27, "watches": 437, "language": "Python", "license": "Apache License 2.0", "topics": [ "asr", "asr-model", "canary", "deeplearning", "diarization", "docker", "huggingface", "neural-network", "open-source", "opensource", "pyannote", "rev", "revai", "speaker-diarization", "speech-recognition", "speech-to-text", "speechrecognition", "wenet", "whisper" ], "owner": { "login": "revdotcom", "avatar_url": "https://avatars.githubusercontent.com/u/2295433?v=4", "html_url": "https://github.com/revdotcom" } }, { "id": 488803183, "name": "deepgram-go-sdk", "full_name": "deepgram/deepgram-go-sdk", "url": "https://github.com/deepgram/deepgram-go-sdk", "description": "Official Go SDK for Deepgram.", "stars": 84, "forks": 52, "watches": 84, "language": "Go", "license": "MIT License", "topics": [ "asr", "deepgram", "go", "hacktoberfest", "speech-recognition", "speech-to-text", "text-to-speech", "voice-agent", "voice-ai" ], "owner": { "login": "deepgram", "avatar_url": "https://avatars.githubusercontent.com/u/17422641?v=4", "html_url": "https://github.com/deepgram" } }, { "id": 369632674, "name": "real-time-language-translator", "full_name": "gunarakulangunaretnam/real-time-language-translator", "url": "https://github.com/gunarakulangunaretnam/real-time-language-translator", "description": "A voice recognition-based tool for translating languages in real-time.", "stars": 61, "forks": 22, "watches": 61, "language": "Python", "license": "Apache License 2.0", "topics": [ "language-translation", "speech-recognition", "speech-to-text", "streamlit", "text-to-speech" ], "owner": { "login": "gunarakulangunaretnam", "avatar_url": "https://avatars.githubusercontent.com/u/45822509?v=4", "html_url": "https://github.com/gunarakulangunaretnam" } }, { "id": 261373023, "name": "rl-baselines3-zoo", "full_name": "DLR-RM/rl-baselines3-zoo", "url": "https://github.com/DLR-RM/rl-baselines3-zoo", "description": "A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.", "stars": 2815, "forks": 598, "watches": 2815, "language": "Python", "license": "MIT License", "topics": [ "deep-reinforcement-learning", "gym", "hyperparameter-optimization", "hyperparameter-search", "hyperparameter-tuning", "lab", "openai", "optimization", "pybullet", "pybullet-environments", "pytorch", "reinforcement-learning", "rl", "robotics", "sde", "stable-baselines", "tuning-hyperparameters" ], "owner": { "login": "DLR-RM", "avatar_url": "https://avatars.githubusercontent.com/u/25227811?v=4", "html_url": "https://github.com/DLR-RM" } }, { "id": 711888465, "name": "expo-speech-recognition", "full_name": "jamsch/expo-speech-recognition", "url": "https://github.com/jamsch/expo-speech-recognition", "description": "Speech Recognition for React Native Expo projects", "stars": 626, "forks": 46, "watches": 626, "language": "TypeScript", "license": "MIT License", "topics": [ "expo", "react-native", "speech-recognition", "speech-to-text", "voice-recognition" ], "owner": { "login": "jamsch", "avatar_url": "https://avatars.githubusercontent.com/u/12927717?v=4", "html_url": "https://github.com/jamsch" } }, { "id": 916630987, "name": "speech-to-text-finetune", "full_name": "mozilla-ai/speech-to-text-finetune", "url": "https://github.com/mozilla-ai/speech-to-text-finetune", "description": "Blueprint by Mozilla.ai for finetuning a Speech-To-Text model in your own language", "stars": 67, "forks": 9, "watches": 67, "language": "Python", "license": "Apache License 2.0", "topics": [ "automatic-speech-recognition", "common-voice", "local-ai", "speech-recognition", "speech-to-text" ], "owner": { "login": "mozilla-ai", "avatar_url": "https://avatars.githubusercontent.com/u/129804596?v=4", "html_url": "https://github.com/mozilla-ai" } }, { "id": 878272507, "name": "judgeval", "full_name": "JudgmentLabs/judgeval", "url": "https://github.com/JudgmentLabs/judgeval", "description": "The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.", "stars": 1034, "forks": 92, "watches": 1034, "language": "Python", "license": "Apache License 2.0", "topics": [ "agent", "agentic-ai", "agents", "grpo", "langchain", "langgraph", "llama-index", "llm", "llm-evaluation", "llm-observability", "open-source", "openai", "prompt-engineering", "reinforcement-learning", "rl" ], "owner": { "login": "JudgmentLabs", "avatar_url": "https://avatars.githubusercontent.com/u/186249420?v=4", "html_url": "https://github.com/JudgmentLabs" } }, { "id": 621844557, "name": "willow", "full_name": "HeyWillow/willow", "url": "https://github.com/HeyWillow/willow", "description": "Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative", "stars": 3044, "forks": 119, "watches": 3044, "language": "C", "license": "Apache License 2.0", "topics": [ "alexa", "deep-learning", "echo", "esp-adf", "esp-idf", "esp32", "google-home", "home-assistant", "home-automation", "privacy", "speech-recognition", "speech-to-text", "whisper" ], "owner": { "login": "HeyWillow", "avatar_url": "https://avatars.githubusercontent.com/u/206060000?v=4", "html_url": "https://github.com/HeyWillow" } }, { "id": 421821883, "name": "CIF-PyTorch", "full_name": "MingLunHan/CIF-PyTorch", "url": "https://github.com/MingLunHan/CIF-PyTorch", "description": "[ICASSP 2020] CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition (A PyTorch implementation of Continuous Integrate-and-Fire mechanism).", "stars": 79, "forks": 6, "watches": 79, "language": "Python", "license": "Apache License 2.0", "topics": [ "alignment", "asr", "automatic-speech-recognition", "cif", "continuous-integrate-and-fire", "integrate-and-fire", "pytorch", "soft-alignment", "speech", "speech-recognition", "speech-to-text" ], "owner": { "login": "MingLunHan", "avatar_url": "https://avatars.githubusercontent.com/u/33624754?v=4", "html_url": "https://github.com/MingLunHan" } }, { "id": 957479413, "name": "all-rl-algorithms", "full_name": "FareedKhan-dev/all-rl-algorithms", "url": "https://github.com/FareedKhan-dev/all-rl-algorithms", "description": "Implementation of all RL algorithms in a simpler way", "stars": 1578, "forks": 289, "watches": 1578, "language": "Jupyter Notebook", "license": "MIT License", "topics": [ "agent", "llm", "openai", "python", "reinforcement-learning", "rl" ], "owner": { "login": "FareedKhan-dev", "avatar_url": "https://avatars.githubusercontent.com/u/63067900?v=4", "html_url": "https://github.com/FareedKhan-dev" } }, { "id": 660921882, "name": "VRCT", "full_name": "misyaguziya/VRCT", "url": "https://github.com/misyaguziya/VRCT", "description": "VRCT(VRChat Chatbox Translator \u0026 Transcription)", "stars": 384, "forks": 40, "watches": 384, "language": "Python", "license": "MIT License", "topics": [ "osc", "speech-recognition", "speech-to-text", "vrchat" ], "owner": { "login": "misyaguziya", "avatar_url": "https://avatars.githubusercontent.com/u/53165965?v=4", "html_url": "https://github.com/misyaguziya" } }, { "id": 94351749, "name": "B.E.N.J.I.", "full_name": "dhruvapte26/B.E.N.J.I.", "url": "https://github.com/dhruvapte26/B.E.N.J.I.", "description": "B.E.N.J.I.- The Impossible Missions Force's digital assistant", "stars": 89, "forks": 92, "watches": 89, "language": "Python", "license": "MIT License", "topics": [ "digital-assistant", "python3", "speech-recognition", "speech-to-text" ], "owner": { "login": "dhruvapte26", "avatar_url": "https://avatars.githubusercontent.com/u/20641565?v=4", "html_url": "https://github.com/dhruvapte26" } }, { "id": 826386564, "name": "genima", "full_name": "MohitShridhar/genima", "url": "https://github.com/MohitShridhar/genima", "description": "Official Code Repo for GENIMA ", "stars": 77, "forks": 4, "watches": 77, "language": "Python", "license": "Apache License 2.0", "topics": [ "behavioral-cloning", "diffusion", "diffusion-models", "image-generation", "imitation-learning", "manipulation", "rlbench", "robot-learning", "robotics", "stable-diffusion" ], "owner": { "login": "MohitShridhar", "avatar_url": "https://avatars.githubusercontent.com/u/6535354?v=4", "html_url": "https://github.com/MohitShridhar" } }, { "id": 946178371, "name": "ART", "full_name": "OpenPipe/ART", "url": "https://github.com/OpenPipe/ART", "description": "Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!", "stars": 9870, "forks": 876, "watches": 9870, "language": "Python", "license": "Apache License 2.0", "topics": [ "agent", "agentic-ai", "grpo", "llms", "lora", "qwen", "qwen3", "reinforcement-learning", "rl" ], "owner": { "login": "OpenPipe", "avatar_url": "https://avatars.githubusercontent.com/u/139012218?v=4", "html_url": "https://github.com/OpenPipe" } }, { "id": 951932591, "name": "rag-with-rl", "full_name": "FareedKhan-dev/rag-with-rl", "url": "https://github.com/FareedKhan-dev/rag-with-rl", "description": "Maximizing the Performance of a Simple RAG using RL", "stars": 92, "forks": 23, "watches": 92, "language": "Jupyter Notebook", "license": "MIT License", "topics": [ "llm", "openai", "python", "rag", "reinforcement-learning", "rl" ], "owner": { "login": "FareedKhan-dev", "avatar_url": "https://avatars.githubusercontent.com/u/63067900?v=4", "html_url": "https://github.com/FareedKhan-dev" } }, { "id": 630052479, "name": "quillman", "full_name": "modal-labs/quillman", "url": "https://github.com/modal-labs/quillman", "description": "A voice chat app ", "stars": 1205, "forks": 157, "watches": 1205, "language": "Python", "license": "MIT License", "topics": [ "ai", "language-model", "python", "serverless", "speech-recognition", "speech-to-text" ], "owner": { "login": "modal-labs", "avatar_url": "https://avatars.githubusercontent.com/u/88658467?v=4", "html_url": "https://github.com/modal-labs" } }, { "id": 681603891, "name": "BenchMARL", "full_name": "facebookresearch/BenchMARL", "url": "https://github.com/facebookresearch/BenchMARL", "description": "BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.", "stars": 628, "forks": 130, "watches": 628, "language": "Python", "license": "MIT License", "topics": [ "benchmark", "machine-learning", "marl", "multi-agent", "multi-agent-reinforcement-learning", "pytorch", "reinforcement-learning", "rl", "robotics", "torch" ], "owner": { "login": "facebookresearch", "avatar_url": "https://avatars.githubusercontent.com/u/16943930?v=4", "html_url": "https://github.com/facebookresearch" } }, { "id": 735874755, "name": "VoiceStreamAI", "full_name": "alesaccoia/VoiceStreamAI", "url": "https://github.com/alesaccoia/VoiceStreamAI", "description": "Near-Realtime audio transcription using self-hosted Whisper and WebSocket in Python/JS", "stars": 959, "forks": 142, "watches": 959, "language": "Python", "license": "MIT License", "topics": [ "ai", "speech-recognition", "speech-to-text", "websocket" ], "owner": { "login": "alesaccoia", "avatar_url": "https://avatars.githubusercontent.com/u/1385023?v=4", "html_url": "https://github.com/alesaccoia" } }, { "id": 265961360, "name": "speech2text", "full_name": "shenasa-ai/speech2text", "url": "https://github.com/shenasa-ai/speech2text", "description": "A Deep-Learning-Based Persian Speech Recognition System ", "stars": 237, "forks": 32, "watches": 237, "language": "Jupyter Notebook", "license": "MIT License", "topics": [ "attention", "attention-mechanism", "ctc", "keras", "mozilla-deepspeech", "python", "speech-recognition", "speech-to-text", "teacher-forcing", "tensorflow2" ], "owner": { "login": "shenasa-ai", "avatar_url": "https://avatars.githubusercontent.com/u/65737334?v=4", "html_url": "https://github.com/shenasa-ai" } }, { "id": 793969272, "name": "whisply", "full_name": "tsmdt/whisply", "url": "https://github.com/tsmdt/whisply", "description": "💬 Fast, cross-platform CLI and GUI for batch transcription, translation, speaker annotation and subtitle generation using OpenAI’s Whisper on CPU, Nvidia GPU and Apple MLX.", "stars": 132, "forks": 20, "watches": 132, "language": "Python", "license": "MIT License", "topics": [ "asr", "automatic-speech-recognition", "mlx", "mlx-audio", "speech-recognition", "speech-to-text", "subtitles", "transcription-tool", "whisper-ai" ], "owner": { "login": "tsmdt", "avatar_url": "https://avatars.githubusercontent.com/u/86777463?v=4", "html_url": "https://github.com/tsmdt" } }, { "id": 906729087, "name": "MisterWhisper", "full_name": "openconcerto/MisterWhisper", "url": "https://github.com/openconcerto/MisterWhisper", "description": "Push to talk voice recognition using Whisper", "stars": 115, "forks": 7, "watches": 115, "language": "Java", "license": "MIT License", "topics": [ "openai", "speech-recognition", "speech-to-text", "whisper" ], "owner": { "login": "openconcerto", "avatar_url": "https://avatars.githubusercontent.com/u/1234263?v=4", "html_url": "https://github.com/openconcerto" } }, { "id": 222960340, "name": "furniture", "full_name": "clvrai/furniture", "url": "https://github.com/clvrai/furniture", "description": "IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks", "stars": 562, "forks": 63, "watches": 562, "language": "Python", "license": "MIT License", "topics": [ "furniture-assembly", "imitation-learning", "reinforcement-learning-environments", "robot-learning", "robotics" ], "owner": { "login": "clvrai", "avatar_url": "https://avatars.githubusercontent.com/u/29267020?v=4", "html_url": "https://github.com/clvrai" } }, { "id": 936986786, "name": "EasyR1", "full_name": "hiyouga/EasyR1", "url": "https://github.com/hiyouga/EasyR1", "description": "EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL", "stars": 4968, "forks": 373, "watches": 4968, "language": "Python", "license": "Apache License 2.0", "topics": [ "ai", "deepseek", "gpt", "llm", "nlp", "qwen", "reinforcement-learning", "rl" ], "owner": { "login": "hiyouga", "avatar_url": "https://avatars.githubusercontent.com/u/16256802?v=4", "html_url": "https://github.com/hiyouga" } }, { "id": 578022358, "name": "jsbgym", "full_name": "sryu1/jsbgym", "url": "https://github.com/sryu1/jsbgym", "description": "An JSBSim environment for reinforcement learning, original from https://github.com/Gor-Ren/gym-jsbsim", "stars": 50, "forks": 9, "watches": 50, "language": "Python", "license": "MIT License", "topics": [ "ai", "flightgear", "gymnasium", "jsbsim", "ml", "reinforcement-learning", "rl" ], "owner": { "login": "sryu1", "avatar_url": "https://avatars.githubusercontent.com/u/95025816?v=4", "html_url": "https://github.com/sryu1" } }, { "id": 155038875, "name": "cheetah", "full_name": "Picovoice/cheetah", "url": "https://github.com/Picovoice/cheetah", "description": "On-device streaming speech-to-text engine powered by deep learning ", "stars": 663, "forks": 77, "watches": 663, "language": "Python", "license": "Apache License 2.0", "topics": [ "asr", "automatic-speech-recognition", "online-speech-recognition", "speech-recognition", "speech-to-text", "streaming-speech-to-text", "stt", "transcription", "voice-recognition" ], "owner": { "login": "Picovoice", "avatar_url": "https://avatars.githubusercontent.com/u/37164515?v=4", "html_url": "https://github.com/Picovoice" } }, { "id": 288532253, "name": "sova-asr", "full_name": "sovaai/sova-asr", "url": "https://github.com/sovaai/sova-asr", "description": "SOVA ASR (Automatic Speech Recognition)", "stars": 171, "forks": 23, "watches": 171, "language": "Python", "license": "Apache License 2.0", "topics": [ "asr", "asr-model", "automatic-speech-recognition", "speech", "speech-recognition", "speech-to-text", "stt", "wav2letter" ], "owner": { "login": "sovaai", "avatar_url": "https://avatars.githubusercontent.com/u/59205514?v=4", "html_url": "https://github.com/sovaai" } }, { "id": 752954314, "name": "Indic-Subtitler", "full_name": "kurianbenoy/Indic-Subtitler", "url": "https://github.com/kurianbenoy/Indic-Subtitler", "description": "Open source subtitling platform 💻 for transcribing and translating videos/audios in Indic languages.", "stars": 93, "forks": 16, "watches": 93, "language": "Jupyter Notebook", "license": "MIT License", "topics": [ "asr", "deep-learning", "fastapi", "faster-whisper", "inference", "nextjs", "openai", "quantization", "speech-recognition", "speech-to-text", "transformers", "vegam-whisper", "webapp", "whisper", "whisperx" ], "owner": { "login": "kurianbenoy", "avatar_url": "https://avatars.githubusercontent.com/u/24592806?v=4", "html_url": "https://github.com/kurianbenoy" } }, { "id": 1115581942, "name": "qwed-verification", "full_name": "QWED-AI/qwed-verification", "url": "https://github.com/QWED-AI/qwed-verification", "description": "AISecOps (AI Security Operations) framework for deterministic verification of AI systems. QWED verifies LLM outputs using math, logic, and symbolic execution — creating an auditable trust boundary for agentic AI systems. Not generation. Verification.", "stars": 57, "forks": 9, "watches": 57, "language": "Python", "license": "Apache License 2.0", "topics": [ "ai-accuracy", "ai-safety", "ai-security", "aisecops", "code-security", "deterministic-ai", "enterprise-ai", "formal-verification", "generative-ai", "hallucination", "hallucination-detection", "llm-safety", "llm-verification", "machine-learning", "neurosymbolic-ai", "nlp", "python", "smt-solver", "sympy", "z3-prover" ], "owner": { "login": "QWED-AI", "avatar_url": "https://avatars.githubusercontent.com/u/250389197?v=4", "html_url": "https://github.com/QWED-AI" } }, { "id": 342512505, "name": "PPASR", "full_name": "yeyupiaoling/PPASR", "url": "https://github.com/yeyupiaoling/PPASR", "description": "基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型", "stars": 875, "forks": 130, "watches": 875, "language": "Python", "license": "Apache License 2.0", "topics": [ "asr", "chinese", "conformer", "deep-learning", "deepspeech2", "paddlepaddle", "speech", "speech-recognition", "speech-to-text", "squeezeformer", "streaming-asr" ], "owner": { "login": "yeyupiaoling", "avatar_url": "https://avatars.githubusercontent.com/u/26297768?v=4", "html_url": "https://github.com/yeyupiaoling" } }, { "id": 1159447558, "name": "open-bias", "full_name": "open-bias/open-bias", "url": "https://github.com/open-bias/open-bias", "description": "Open Source Reliability Harness: Make your agents follow rules. One line of code to‎ ‎enforce, trace, and improve. ‎ ‎ ", "stars": 123, "forks": 4, "watches": 123, "language": "Python", "license": "Apache License 2.0", "topics": [ "agentic-ai", "ai-audit", "ai-compliance", "ai-firewall", "ai-governance", "ai-guardrails", "ai-policy", "ai-safety", "ai-security", "content-safety", "guardrails", "llm-guardrails", "llm-monitoring", "llm-proxy", "llm-safety", "llm-security", "policy-engine", "prompt-injection", "responsible-ai", "rule-engine" ], "owner": { "login": "open-bias", "avatar_url": "https://avatars.githubusercontent.com/u/270147414?v=4", "html_url": "https://github.com/open-bias" } }, { "id": 263622079, "name": "PyCameraServer", "full_name": "alexfcoding/PyCameraServer", "url": "https://github.com/alexfcoding/PyCameraServer", "description": "Online web-editor of video / images / Youtube / IP Camera frames using Flask, OpenCV and neural networks", "stars": 77, "forks": 15, "watches": 77, "language": "Python", "license": "MIT License", "topics": [ "computer-vision", "image-processing", "object-detection", "opencv" ], "owner": { "login": "alexfcoding", "avatar_url": "https://avatars.githubusercontent.com/u/46035835?v=4", "html_url": "https://github.com/alexfcoding" } }, { "id": 789219662, "name": "rl", "full_name": "benbaarber/rl", "url": "https://github.com/benbaarber/rl", "description": "A rust reinforcement learning library", "stars": 50, "forks": 12, "watches": 50, "language": "Rust", "license": "MIT License", "topics": [ "burn", "deep-learning", "machine-learning", "ml", "reinforcement-learning", "rl", "rust" ], "owner": { "login": "benbaarber", "avatar_url": "https://avatars.githubusercontent.com/u/6320364?v=4", "html_url": "https://github.com/benbaarber" } }, { "id": 874118351, "name": "wtm", "full_name": "JosefAlbers/wtm", "url": "https://github.com/JosefAlbers/wtm", "description": "Blazing fast whisper turbo for ASR (speech-to-text) tasks", "stars": 225, "forks": 13, "watches": 225, "language": "Python", "license": "MIT License", "topics": [ "asr", "deep-learning", "mlx", "speech-recognition", "speech-to-text", "whisper", "whisper-turbo" ], "owner": { "login": "JosefAlbers", "avatar_url": "https://avatars.githubusercontent.com/u/146810011?v=4", "html_url": "https://github.com/JosefAlbers" } }, { "id": 390150068, "name": "asrecognition", "full_name": "jonatasgrosman/asrecognition", "url": "https://github.com/jonatasgrosman/asrecognition", "description": "ASRecognition: just an easy-to-use library for Automatic Speech Recognition.", "stars": 50, "forks": 5, "watches": 50, "language": "Python", "license": "MIT License", "topics": [ "asr", "audio", "automatic-speech-recognition", "speech", "speech-recognition", "speech-to-text", "voice-recognition" ], "owner": { "login": "jonatasgrosman", "avatar_url": "https://avatars.githubusercontent.com/u/5097052?v=4", "html_url": "https://github.com/jonatasgrosman" } }, { "id": 884967673, "name": "torchtrade", "full_name": "TorchTrade/torchtrade", "url": "https://github.com/TorchTrade/torchtrade", "description": "Modular reinforcement learning framework for algorithmic trading", "stars": 386, "forks": 50, "watches": 386, "language": "Python", "license": "MIT License", "topics": [ "algorithmic-trading", "crypto-trading-system", "llm", "pytorch", "quantitative-finance", "reinforcement-learning", "rl", "torchrl", "trading-bot-" ], "owner": { "login": "TorchTrade", "avatar_url": "https://avatars.githubusercontent.com/u/228354952?v=4", "html_url": "https://github.com/TorchTrade" } }, { "id": 42082724, "name": "adapt", "full_name": "MycroftAI/adapt", "url": "https://github.com/MycroftAI/adapt", "description": "Adapt Intent Parser", "stars": 722, "forks": 161, "watches": 722, "language": "Python", "license": "Apache License 2.0", "topics": [ "intent-parser", "intents", "open-source", "opensource", "speech-recognition", "speech-to-text" ], "owner": { "login": "MycroftAI", "avatar_url": "https://avatars.githubusercontent.com/u/14171097?v=4", "html_url": "https://github.com/MycroftAI" } }, { "id": 1065046261, "name": "ManySpeech", "full_name": "manyeyes/ManySpeech", "url": "https://github.com/manyeyes/ManySpeech", "description": "AI Speech Solutions for Tasks such as ASR, Vocal Extraction, Accompaniment Extraction, Audio Denoising, and Enhancement, Support models such as paraformer, sensevoice, fireredasr, zipformer, moonshine, wenet, whisper, fsmn-vad, silero-vad, CT Transformer punc, Spleeter, Uvr5, etc, apply ONNX models in various scenarios.", "stars": 79, "forks": 11, "watches": 79, "language": "C#", "license": "Apache License 2.0", "topics": [ "asr", "ct-transformer-punc", "fireredasr", "fsmn-vad", "maui", "moonshine", "onnx", "onnxruntime", "paraformer", "sensevoice", "silero-vad", "speech-recognition", "speech-to-text", "spleeter", "uvr5", "wenet", "whisper", "zipformer" ], "owner": { "login": "manyeyes", "avatar_url": "https://avatars.githubusercontent.com/u/32889020?v=4", "html_url": "https://github.com/manyeyes" } }, { "id": 1119587116, "name": "VoiceSnap", "full_name": "vorojar/VoiceSnap", "url": "https://github.com/vorojar/VoiceSnap", "description": "Open-source offline voice dictation — a free alternative to Typeless. 100% local, zero internet, ideal for air-gapped \u0026 classified environments. SenseVoice + DirectML GPU, ~34MB, hotkey-driven. 纯离线语音输入，Typeless 免费平替，数据永不出设备，适合党政机关等涉密场景。", "stars": 73, "forks": 3, "watches": 73, "language": "Go", "license": "MIT License", "topics": [ "air-gapped", "dictation", "directml", "local-ai", "offline", "privacy", "secure", "sensevoice", "sherpa-onnx", "speech-recognition", "speech-to-text", "typeless-alternative", "voice-dictation", "voice-input", "voice-typing" ], "owner": { "login": "vorojar", "avatar_url": "https://avatars.githubusercontent.com/u/130814500?v=4", "html_url": "https://github.com/vorojar" } }, { "id": 727142514, "name": "SafeGen_CCS2024", "full_name": "LetterLiGo/SafeGen_CCS2024", "url": "https://github.com/LetterLiGo/SafeGen_CCS2024", "description": "[CCS'24] SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models", "stars": 137, "forks": 12, "watches": 137, "language": "Python", "license": "Apache License 2.0", "topics": [ "ai-safety", "ai-security", "generative-ai", "text-to-image", "thrustworthy-ai" ], "owner": { "login": "LetterLiGo", "avatar_url": "https://avatars.githubusercontent.com/u/42758655?v=4", "html_url": "https://github.com/LetterLiGo" } }, { "id": 867680919, "name": "LS-Imagine", "full_name": "qiwang067/LS-Imagine", "url": "https://github.com/qiwang067/LS-Imagine", "description": "[ICLR 2025 Oral] PyTorch code for the paper \"Open-World Reinforcement Learning over Long Short-Term Imagination\"", "stars": 218, "forks": 11, "watches": 218, "language": "Python", "license": "Apache License 2.0", "topics": [ "dreamer", "dreamerv2", "dreamerv3", "minecraft", "minedojo", "reinforcement-learning", "rl", "visual-reinforcement-learning", "visual-rl", "world-model", "world-models" ], "owner": { "login": "qiwang067", "avatar_url": "https://avatars.githubusercontent.com/u/22296010?v=4", "html_url": "https://github.com/qiwang067" } }, { "id": 1054771290, "name": "meta-agents-research-environments", "full_name": "facebookresearch/meta-agents-research-environments", "url": "https://github.com/facebookresearch/meta-agents-research-environments", "description": "Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges.", "stars": 505, "forks": 66, "watches": 505, "language": "Python", "license": "MIT License", "topics": [ "agents", "ai", "autonomous-agents", "benchmark", "evaluation", "large-language-models", "llm", "meta", "multi-agent-systems", "natural-language-processing", "reinforcement-learning", "rl", "simulation" ], "owner": { "login": "facebookresearch", "avatar_url": "https://avatars.githubusercontent.com/u/16943930?v=4", "html_url": "https://github.com/facebookresearch" } }, { "id": 687372462, "name": "whisper-gui", "full_name": "Pikurrot/whisper-gui", "url": "https://github.com/Pikurrot/whisper-gui", "description": "A simple GUI to use Whisper.", "stars": 436, "forks": 41, "watches": 436, "language": "Python", "license": "MIT License", "topics": [ "gradio", "gui", "huggingface", "interface", "speech-recognition", "speech-to-text", "transformers", "whisper", "whisper-ai", "whisperx" ], "owner": { "login": "Pikurrot", "avatar_url": "https://avatars.githubusercontent.com/u/90217719?v=4", "html_url": "https://github.com/Pikurrot" } }, { "id": 573134410, "name": "go-whisper", "full_name": "mutablelogic/go-whisper", "url": "https://github.com/mutablelogic/go-whisper", "description": "Speech-to-Text in golang", "stars": 186, "forks": 24, "watches": 186, "language": "Go", "license": "Apache License 2.0", "topics": [ "golang", "speech-recognition", "speech-to-text", "whisper" ], "owner": { "login": "mutablelogic", "avatar_url": "https://avatars.githubusercontent.com/u/5088221?v=4", "html_url": "https://github.com/mutablelogic" } }, { "id": 600368121, "name": "faster-whisper", "full_name": "SYSTRAN/faster-whisper", "url": "https://github.com/SYSTRAN/faster-whisper", "description": "Faster Whisper transcription with CTranslate2", "stars": 23263, "forks": 1906, "watches": 23263, "language": "Python", "license": "MIT License", "topics": [ "deep-learning", "inference", "openai", "quantization", "speech-recognition", "speech-to-text", "transformer", "whisper" ], "owner": { "login": "SYSTRAN", "avatar_url": "https://avatars.githubusercontent.com/u/1520500?v=4", "html_url": "https://github.com/SYSTRAN" } }, { "id": 174949753, "name": "Chinese-automatic-speech-recognition", "full_name": "chenmingxiang110/Chinese-automatic-speech-recognition", "url": "https://github.com/chenmingxiang110/Chinese-automatic-speech-recognition", "description": "Chinese speech recognition", "stars": 160, "forks": 23, "watches": 160, "language": "Jupyter Notebook", "license": "MIT License", "topics": [ "chinese-nlp", "chinese-speech-recognition", "chinese-speech-to-text", "deep-learning", "machine-learning", "signal-processing", "speech-recognition", "speech-to-text" ], "owner": { "login": "chenmingxiang110", "avatar_url": "https://avatars.githubusercontent.com/u/25835726?v=4", "html_url": "https://github.com/chenmingxiang110" } }, { "id": 878183712, "name": "robots-pretrain-robots", "full_name": "luccachiang/robots-pretrain-robots", "url": "https://github.com/luccachiang/robots-pretrain-robots", "description": "[ICLR 2025🎉] This is the official implementation of paper \"Robots Pre-Train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets\".", "stars": 95, "forks": 5, "watches": 95, "language": "Python", "license": "MIT License", "topics": [ "computer-vision", "imitation-learning", "robot-learning", "robotics" ], "owner": { "login": "luccachiang", "avatar_url": "https://avatars.githubusercontent.com/u/92565797?v=4", "html_url": "https://github.com/luccachiang" } }, { "id": 1001011932, "name": "so101_ros2", "full_name": "nimiCurtis/so101_ros2", "url": "https://github.com/nimiCurtis/so101_ros2", "description": "A ROS2 Bridge for Lerobot so101 manipulator", "stars": 50, "forks": 8, "watches": 50, "language": "Python", "license": "MIT License", "topics": [ "imitation-learning", "isaac-sim", "lerobot", "robot-learning", "robotics", "ros2", "teleoperation", "vla" ], "owner": { "login": "nimiCurtis", "avatar_url": "https://avatars.githubusercontent.com/u/89691558?v=4", "html_url": "https://github.com/nimiCurtis" } }, { "id": 573820339, "name": "QReader", "full_name": "Eric-Canas/QReader", "url": "https://github.com/Eric-Canas/QReader", "description": "Robust and Straight-Forward solution for reading difficult and tricky QR codes within images in Python. Powered by YOLOv8", "stars": 413, "forks": 39, "watches": 413, "language": "Python", "license": "MIT License", "topics": [ "computer-vision", "easy-to-use", "image-processing", "object-detection", "pip", "python", "pytorch", "pyzbar", "qr", "qrcode", "qrcode-reader", "qrcode-scanner", "yolov8" ], "owner": { "login": "Eric-Canas", "avatar_url": "https://avatars.githubusercontent.com/u/32014366?v=4", "html_url": "https://github.com/Eric-Canas" } }, { "id": 709248558, "name": "top-100-computer-vision-projects-idea-for-2024", "full_name": "farukalamai/top-100-computer-vision-projects-idea-for-2024", "url": "https://github.com/farukalamai/top-100-computer-vision-projects-idea-for-2024", "description": "Welcome to the \"Top 100 Computer Vision Projects Idea for 2024\" repository! This repository contains a curated list of computer vision project ideas that you can explore, implement, and experiment with in 2024", "stars": 121, "forks": 17, "watches": 121, "language": "", "license": "MIT License", "topics": [ "ai-robot", "computer-vision", "deep-learning", "image-classification", "image-processing", "image-recognition", "image-segmentation", "object-detection", "object-tracking", "opencv", "pose-estimation", "real-time-processing", "text-classification", "yolov8" ], "owner": { "login": "farukalamai", "avatar_url": "https://avatars.githubusercontent.com/u/92469073?v=4", "html_url": "https://github.com/farukalamai" } }, { "id": 283377873, "name": "MASR", "full_name": "yeyupiaoling/MASR", "url": "https://github.com/yeyupiaoling/MASR", "description": "Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。", "stars": 723, "forks": 116, "watches": 723, "language": "Python", "license": "Apache License 2.0", "topics": [ "asr", "conformer", "deep-learning", "deepspeech", "pytorch", "speech", "speech-recognition", "speech-to-text", "squeezeformer" ], "owner": { "login": "yeyupiaoling", "avatar_url": "https://avatars.githubusercontent.com/u/26297768?v=4", "html_url": "https://github.com/yeyupiaoling" } }, { "id": 1028684768, "name": "voiceai", "full_name": "mahimairaja/voiceai", "url": "https://github.com/mahimairaja/voiceai", "description": "Set of 📝 with 🔗 to help those building Voice AI agents 🎙️🤖", "stars": 274, "forks": 18, "watches": 274, "language": "", "license": "MIT License", "topics": [ "ai-agents", "asr", "awesome", "awesome-list", "beginners", "conversational-ai", "learning-resources", "livekit", "llm", "pipecat", "realtime-ai", "speech-recognition", "speech-synthesis", "speech-to-text", "text-to-speech", "tts", "voice-agents", "voice-ai", "voice-assistant", "webrtc" ], "owner": { "login": "mahimairaja", "avatar_url": "https://avatars.githubusercontent.com/u/81288263?v=4", "html_url": "https://github.com/mahimairaja" } }, { "id": 904099083, "name": "advanced-homeassistant-mcp", "full_name": "jango-blockchained/advanced-homeassistant-mcp", "url": "https://github.com/jango-blockchained/advanced-homeassistant-mcp", "description": "An advanced MCP server for Home Assistant. 🔋 Batteries included.", "stars": 52, "forks": 23, "watches": 52, "language": "JavaScript", "license": "Apache License 2.0", "topics": [ "home-assistant", "llm", "mcp-server", "speech-recognition", "speech-to-text" ], "owner": { "login": "jango-blockchained", "avatar_url": "https://avatars.githubusercontent.com/u/16127070?v=4", "html_url": "https://github.com/jango-blockchained" } }, { "id": 307222796, "name": "Papers-in-100-Lines-of-Code", "full_name": "MaximeVandegar/Papers-in-100-Lines-of-Code", "url": "https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code", "description": "Implementation of papers in 100 lines of code.", "stars": 2791, "forks": 251, "watches": 2791, "language": "Python", "license": "MIT License", "topics": [ "3d", "aes", "artificial-intelligence", "deep-learning", "diffusion-models", "educational", "gans", "generative-model", "implementation-of-research-paper", "inverse-rendering", "machine-learning", "meta-learning", "nerf", "neural-radiance-fields", "papers", "python", "pytorch", "reinforcement-learning", "research", "rl" ], "owner": { "login": "MaximeVandegar", "avatar_url": "https://avatars.githubusercontent.com/u/45870423?v=4", "html_url": "https://github.com/MaximeVandegar" } }, { "id": 810195157, "name": "StreamSpeech", "full_name": "ictnlp/StreamSpeech", "url": "https://github.com/ictnlp/StreamSpeech", "description": "StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.", "stars": 1270, "forks": 103, "watches": 1270, "language": "Python", "license": "MIT License", "topics": [ "all-in-one", "asr", "audio-processing", "machine-translation", "non-autoregressive", "seamless", "simultaneous-translation", "speech", "speech-enhancement", "speech-processing", "speech-recognition", "speech-synthesis", "speech-to-text", "speech-translation", "streaming-audio", "text-to-audio", "text-to-speech", "translation", "tts", "voice" ], "owner": { "login": "ictnlp", "avatar_url": "https://avatars.githubusercontent.com/u/45630465?v=4", "html_url": "https://github.com/ictnlp" } }, { "id": 224633111, "name": "speechmatics-python", "full_name": "speechmatics/speechmatics-python", "url": "https://github.com/speechmatics/speechmatics-python", "description": "Python library and CLI for Speechmatics", "stars": 75, "forks": 23, "watches": 75, "language": "Python", "license": "MIT License", "topics": [ "cli", "speech-recognition", "speech-to-text", "transcription" ], "owner": { "login": "speechmatics", "avatar_url": "https://avatars.githubusercontent.com/u/15156030?v=4", "html_url": "https://github.com/speechmatics" } }, { "id": 780688408, "name": "consistency-policy", "full_name": "Aaditya-Prasad/consistency-policy", "url": "https://github.com/Aaditya-Prasad/consistency-policy", "description": "[RSS 2024] Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation", "stars": 202, "forks": 16, "watches": 202, "language": "Python", "license": "MIT License", "topics": [ "imitation-learning", "robot-learning", "robotics" ], "owner": { "login": "Aaditya-Prasad", "avatar_url": "https://avatars.githubusercontent.com/u/50385321?v=4", "html_url": "https://github.com/Aaditya-Prasad" } }, { "id": 1152033589, "name": "deterministic-agent-control-protocol", "full_name": "elliot35/deterministic-agent-control-protocol", "url": "https://github.com/elliot35/deterministic-agent-control-protocol", "description": "Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy \u0026 HTTP API. Works with Cursor, Claude Code, Codex, and any MCP-compatible agent.", "stars": 87, "forks": 6, "watches": 87, "language": "TypeScript", "license": "MIT License", "topics": [ "agent-control", "agent-governance", "ai-agent", "ai-governance", "ai-safety", "ai-security", "ai-tools", "audit-log", "claude-code", "codex", "cursor", "deterministic", "gateway", "llm", "mcp", "mcp-server", "model-context-protocol", "nodejs", "policy-engine", "typescript" ], "owner": { "login": "elliot35", "avatar_url": "https://avatars.githubusercontent.com/u/41864818?v=4", "html_url": "https://github.com/elliot35" } } ]