#asr Repositories
Discover 100 active open source GitHub repositories tagged with #asr, accumulating 289,141 total stars (averaging 2,891 stars per project). Leading this topic is m-bain/whisperX with 25,556 stars.
101 repositories total
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.
This is a python API which allows you to get the transcript/subtitles for a given YouTube video. It also works for automatically generated subtitles and it does not require an API key nor a headless browser, like other selenium based solutions do!
๐ค wukong-robot is a simple, flexible, and elegant Chinese voice conversation robot/smart speaker project that supports ChatGPT's multi-turn conversation capabilities, and it may be the first open-source smart speaker project to support brain-computer interaction.
FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
HTML5 JS recording MP3 WAV OGG WebM AMR G711A G711U formats, supports PC and Android, iOS some Web browsers, Hybrid App (provides Android iOS App source code), WeChat, provides ASR speech recognition to text H5 version voice call chat example DTMF encoding/decoding
The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
Hold a key, speak, release โ AI-polished text appears at your cursor in any app. Open-source voice input for macOS & Windows.
Streamer-Sales Sales Champion -- Sales Streamer LLM Large Model ๐๐, a sales streamer LLM large model that can provide product commentary from the perspective of stimulating user purchase intent based on given product characteristics. ๐โญ Contains detailed data generation processes โ ๐ฆ Also integrates LMDeploy for accelerated inference ๐, RAG Retrieval Augmented Generation ๐, TTS Text-to-Speech ๐, Digital Human Generation ๐ฆธ, Agent use for real-time web information queries ๐, ASR Speech-to-Text ๐๏ธ, Vue ecosystem construction frontend ๐, FastAPI construction backend ๐๏ธ, Docker-compose packaging and deployment ๐
Frontier CoreML audio models in your apps โ text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.
Whisper & Faster-Whisper standalone executables for those who don't want to bother with Python.
[AutoArk] GPA (General Purpose Audio) can do ASR, TTS and voice conversion with one tiny model!
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
Quickly extract audio and video content, organizing it into a structured markdown note
๐ธSTT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.
Next-gen AI+IoT framework for T2/T3/T5AI/ESP32/and more โ Fast IoT and AI Agent hardware integration
High-Performance Serving Runtime for Interactive Superintelligence Systems
Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, LicheePi4A etc.
Bailing is a voice conversation robot similar to GPT-4o, implemented via ASR+LLM+TTS, integrated with excellent large models like DeepSeek R1, connected to openClaw, a true personal voice assistant with latency as low as 800ms, runnable on low-spec devices like Mac, supports interruption
Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.
All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine
Free, open-source voice typing for macOS and Windows. Local speech-to-text with Whisper and Parakeet, also works offline.
Fun-ASR speech recognition models, with native Hugging Face Transformers support for Fun-ASR-Nano and separate FunASR, vLLM and llama.cpp deployment paths.
DELTA is a deep learning based natural language and speech processing platform. LF AI & DATA Projects: https://lfaidata.foundation/projects/delta/
Controllable Transcription. Verbatim (every filler, pause, stutter, and vocal sound), or intended (what the speaker meant to say, optimized for readability), with word-level timestamps.
๐ฆ Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.
Real-time voice interactive digital human, customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.
Native speech-to-text for Linux - Fast, accurate, private, and hackable system-wide dictation
AI speech toolkit for Apple Silicon โ ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML
StreamSpeech is an โAll in Oneโ seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
WebSocket, gRPC and WebRTC speech recognition server based on Vosk and Kaldi libraries
The open-source AI engine for AMD Strix Halo. Text, embeddings, speech, image and video models in one binary, with OpenAI-compatible APIs, caching for coding agents and model extensions. Linux and Windows.
Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment
Frequently Asked Questions
What is the most popular #asr repository on GitHub?
The top ranked open source #asr project on GitHub is m-bain/whisperX with 25,556 stars. WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
Which programming languages are most used in #asr repositories?
Among the top ranked #asr projects on GitHub, the most common programming languages are Python, C++, C, Jupyter Notebook.
How is the #asr repository ranking calculated?
We track 100 active open source repositories tagged with #asr (500+ stars), totaling 289,141 stars with an average of 2,891 stars per repository. Rankings update daily from the GitHub API.