#automatic-speech-recognition Repositories
Discover 42 active open source GitHub repositories tagged with #automatic-speech-recognition, accumulating 118,799 total stars (averaging 2,828 stars per project). Leading this topic is Vaibhavs10/insanely-fast-whisper with 13,052 stars.
42 repositories total
Foundational Models for State-of-the-Art Speech and Text Translation
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
[NO LONGER MAINTAINED] Command-line utility for auto-generating subtitles for any video file
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.
Intelligent Video Multilingual AI Dubbing/Translation Tool - Linly-Dubbing โ โAI Empowered, Language Without Bordersโ
[AutoArk] GPA (General Purpose Audio) can do ASR, TTS and voice conversion with one tiny model!
Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages
๐ธSTT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.
Voice Activity Detector (VAD) : low-latency, high-performance and lightweight
A 0.9B model for long-form transcription in 50+ languages with speaker diarization, timestamps, and acoustic event awareness
The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.
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.
Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation.
Autogenerate subtitles using OpenAI Whisper Model via Jellyfin, Plex, Emby, Tautulli, or Bazarr
Official Python toolkit for the Qwen3-ASR API. Parallel highโthroughput calls, robust longโaudio transcription, multiโsampleโrate support.
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords
An implementation of the Nvidia's Parakeet models for Apple Silicon using MLX.
Evaluate your speech-to-text system with similarity measures such as word error rate (WER)
Omni SenseVoice: High-Speed Speech Recognition with words timestamps ๐ฃ๏ธ๐ฏ
Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.
Collection of resources on the applications of Large Language Models (LLMs) in Audio AI.
A SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandarin, 20+ dialects/accents), English, code-switching, and both speech and singing ASR. FireRedVAD supports speech/singing/music in 100+ langs. FireRedLID supports 100+ langs and 20+ zh dialects. FireRedPunc supports zh and en.
Real Time Speech Transcription with FastRTC โก๏ธand Local Whisper ๐ค
Offline Speech Recognition with OpenAI Whisper and TensorFlow Lite for Android
โจโจ[NeurIPS 2025] VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
It is possible to start recording by pressing the Option button and end recording by releasing the button, then calling the Groq Whisper Large V3 Turbo model for transcription. Since Groq is very fast, most voice inputs are fed back within 1-2s. And thanks to whisper's powerful capabilities, the transcription effect is very good.
A lightweight client-server system for real-time audio processing with voice activity detection (VAD) and automatic speech recognition (ASR).
Frequently Asked Questions
What is the most popular #automatic-speech-recognition repository on GitHub?
The top ranked open source #automatic-speech-recognition project on GitHub is Vaibhavs10/insanely-fast-whisper with 13,052 stars.
Which programming languages are most used in #automatic-speech-recognition repositories?
Among the top ranked #automatic-speech-recognition projects on GitHub, the most common programming languages are Python, Jupyter Notebook, C++, Swift.
How is the #automatic-speech-recognition repository ranking calculated?
We track 42 active open source repositories tagged with #automatic-speech-recognition (500+ stars), totaling 118,799 stars with an average of 2,828 stars per repository. Rankings update daily from the GitHub API.