Back to List
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
Pythonmodelscope/FunASR

FunASR

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

90.5/100
17.6KForks: 1.8K
View on GitHubHomepage →
Loading report...

Similar Projects

SenseVoice

82

Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.

Python8.5K

transformers

98

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Python161.5K

FunClip

80

Open-source, accurate and easy-to-use video speech recognition & clipping tool. LLM-based AI clipping integrated.

Python5.8K

ml-road

64

Machine Learning and Agentic AI Resources, Practice and Research

Python4.8K
Back to List