FunASR
by modelscope (organization)
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving. (description from the project’s GitHub page)
Repository facts
- Stars
- 20,745
- Forks
- 2,085
- Open issues and pull requests
- 45
- Primary language
- Python
- License
- MIT License (MIT)
- Owner
- modelscope · Organization
- Created
- Nov 24, 2022
- Last push
- Oct 18, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 4,436: QwenAudio/Fun-ASR
Fun-ASR speech recognition models, with native Hugging Face Transformers support for Fun-ASR-Nano and separate FunASR, vLLM and llama.cpp deployment paths.
1,577 starsCApache-2.0Last push Oct 12, 2026
Rank 1,256: modelscope/FunClip
FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.
6,418 starsPythonMITLast push Oct 8, 2026
Rank 864: QwenAudio/SenseVoice
Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.
9,529 starsCMITLast push Sep 30, 2026
Rank 681: speechbrain/speechbrain
A PyTorch-based Speech Toolkit
11,887 starsPythonApache-2.0Last push Oct 14, 2026
Rank 2,753: linto-ai/whisper-timestamped
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
2,855 starsPythonAGPL-3.0Last push Sep 28, 2026
Rank 3,425: OpenMOSS/MOSS-Transcribe-Diarize
A 0.9B model for long-form transcription in 50+ languages with speaker diarization, timestamps, and acoustic event awareness
2,179 starsPythonApache-2.0Last push Oct 10, 2026