[GH-ISSUE #120] 功能建议:添加FunASR语音识别集成示例 #111

Open
opened 2026-10-26 21:07:59 +00:00 by bsakaguchi · 0 comments
Owner

Originally created by @LauraGPT on GitHub (Jun 12, 2026).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-V2/issues/120

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。

Originally created by @LauraGPT on GitHub (Jun 12, 2026). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-V2/issues/120 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。
Sign in to join this conversation.
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/DeepSeek-V2#111
No description provided.