https://github.com/FunAudioLLM/SenseVoice

Multilingual Voice Understanding Model
https://github.com/FunAudioLLM/SenseVoice

ai aigc asr audio-event-classification cross-lingual gpt-4o llm multilingual python pytorch speech-emotion-recognition speech-recognition speech-to-text

Last synced: about 1 month ago
JSON representation

Multilingual Voice Understanding Model

• Host: GitHub
• URL: https://github.com/FunAudioLLM/SenseVoice
• Owner: FunAudioLLM
• License: other
• Created: 2024-07-03T02:56:46.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2024-08-02T05:47:30.000Z (about 2 months ago)
• Last Synced: 2024-08-02T06:47:55.971Z (about 2 months ago)
• Topics: ai, aigc, asr, audio-event-classification, cross-lingual, gpt-4o, llm, multilingual, python, pytorch, speech-emotion-recognition, speech-recognition, speech-to-text
• Language: Python
• Homepage: https://funaudiollm.github.io/
• Size: 6.46 MB
• Stars: 1,828
• Watchers: 27
• Forks: 174
• Open Issues: 20
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• ai-game-devtools - SenseVoice
• StarryDivineSky - FunAudioLLM/SenseVoice - Small 模型利用非自回归端到端框架，可实现极低的推理延迟。只需 70 毫秒即可处理 10 秒的音频，比 Whisper-Large 快 15 倍。方便的微调：提供便捷的微调脚本和策略，让用户根据自己的业务场景，轻松解决长尾样本问题。服务部署：提供服务部署管道，支持多并发请求，客户端语言包括 Python、C++、HTML、Java 和 C# 等。 (语音识别与合成_其他 / 网络服务_其他)
• my-awesome - FunAudioLLM/SenseVoice - event-classification,cross-lingual,gpt-4o,llm,multilingual,python,pytorch,speech-emotion-recognition,speech-recognition,speech-to-text pushed_at:2024-09 star:2.5k fork:0.2k Multilingual Voice Understanding Model (Python)