Navigation Menu
FunAudioLLM/SenseVoice
2 BranchesTagsFolders and files
| Name | ||
|---|---|---|
Latest commit LauraGPT
OmniSenseVoice
de00f2b · last week
History85 Commits |
||
| .github/ISSUE_TEMPLATE | docs | 3 months ago |
| data | update | 3 months ago |
| deepspeed_conf | update | 3 months ago |
| image | Third-Party Work | last week |
| utils | update onnx codes | 3 months ago |
| .gitignore | update | 3 months ago |
| LICENSE | dingding | 3 months ago |
| README.md | OmniSenseVoice | last week |
| README_ja.md | OmniSenseVoice | last week |
| README_zh.md | OmniSenseVoice | last week |
| api.py | fix api torchaudio.load bug | 3 months ago |
| demo1.py | docs | 3 months ago |
| demo2.py | docs | 3 months ago |
| demo_libtorch.py | python runtime | 3 months ago |
| demo_onnx.py | python runtime | 3 months ago |
| export.py | update onnx codes | 3 months ago |
| export_meta.py | ONNX support | 3 months ago |
| finetune.sh | sensevoice | 3 months ago |
| model.py | bugfix memory leak | last month |
| requirements.txt | Update requirements.txt | 2 months ago |
| webui.py | sensevoice | 3 months ago |
Repository files navigation
Introduction
SenseVoice is a speech foundation model with multiple speech understanding capabilities, including automatic speech recognition (ASR), spoken language identification (LID), speech emotion recognition (SER), and audio event detection (AED).
Homepage ｜ What's News ｜ Benchmarks ｜ Install ｜ Usage ｜ Community
Model Zoo: modelscope, huggingface
Online Demo: modelscope demo, huggingface space