deepseek-ai / deepseek-ai/DeepSeek-V2
功能建议：添加FunASR语音识别集成示例
Open
- Dominant language
- No language data
- Stars
- 5k
- Forks
- 550
- PR merge metrics
- No merged PRs in 30d
Description
DeepSeek models are excellent for text understanding and generation. Adding speech-to-text integration would enable voice-enabled DeepSeek applications. FunASR (17.8K+ stars, https://github.com/modelscope/FunASR) from the same Chinese AI ecosystem provides:
- **SenseVoice**: 超快速多语言语音识别（比Whisper-large快50倍，中文/英文/日韩 + 粤语）
- **Paraformer**: 非流式语音识别，带时间戳和标点恢复
- **OpenAI兼容API**: POST /v1/audio/transcriptions
DeepSeek + FunASR 组合可以构建完全本地部署的语音对话系统：
语音输入 → FunASR转录 → DeepSeek理解/生成 → 语音合成输出
两个都是国产开源项目，自然互补。FunASR的中文识别能力远超Whisper，配合DeepSeek的中文理解能力，效果更佳。
建议添加FunASR集成示例到DeepSeek文档中。
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.