feat: add FunASR (SenseVoice) STT plugin#603
Conversation
Self-hosted, in-process speech-to-text via FunASR's SenseVoice model, mirroring the fast_whisper plugin. Runs with no external API or per-minute cost, supports 50+ languages with auto-detection, and surfaces the detected language and emotion on each transcript. Registers the funasr extra, workspace member, and a CHANGELOG entry.
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughA new Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Actionable comments posted: 3
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 84b92fe9-cb60-43ad-a4e2-f102147c6e86
⛔ Files ignored due to path filters (1)
uv.lockis excluded by!**/*.lock
📒 Files selected for processing (12)
CHANGELOG.mdagents-core/pyproject.tomlplugins/funasr/README.mdplugins/funasr/example/__init__.pyplugins/funasr/example/funasr_example.pyplugins/funasr/example/pyproject.tomlplugins/funasr/py.typedplugins/funasr/pyproject.tomlplugins/funasr/tests/test_funasr_stt.pyplugins/funasr/vision_agents/plugins/funasr/__init__.pyplugins/funasr/vision_agents/plugins/funasr/stt.pypyproject.toml
Self-hosted, in-process speech-to-text via FunASR's SenseVoice model, mirroring the fast_whisper plugin. Runs with no external API or per-minute cost, supports 50+ languages with auto-detection, and surfaces the detected language and emotion on each transcript.
Registers the funasr extra, workspace member, and a CHANGELOG entry.
Changes
funasrplugin: in-processSTTviafunasr.AutoModel(SenseVoice),mirroring the
fast_whisperpluginTranscriptResponsefunasrextra, workspace member, and a CHANGELOG entryNote: the integration test downloads the ~900 MB SenseVoice model, so the
scheduled integration job may need model caching or a longer timeout.