Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
Commits on main
test(site): align homepage patrol with product build (#3442)
90110b9 zhifu gao committed 3 months ago
ci: publish MCP server images with SBOM attestations (#3437)
6570924 Kobi Hikri committed 3 months ago
Decode container-formatted audio bytes before inference (#3435)
763ee06 zhifu gao committed 3 months ago
fix(auto-model): preserve VAD segments on punctuation mismatch (#3434)
0a9cc00 zhifu gao committed 3 months ago
fix(server): return speaker labels for spk requests (#3433)
cbed336 zhifu gao committed 3 months ago
docs(site): surface Orca SenseVoice desktop integration (#3431)
1e02009 zhifu gao committed 3 months ago
feat(site): launch the FunASR deployment product hub (#3424)
84e049e zhifu gao committed 3 months ago