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
fix: add try-import guards for optional deps (fastapi, humanfriendly, transformers)
d06a93f 游雁 committed 5 months ago
docs: rewrite English vLLM guide with high-quality manual translation
8325d5e 游雁 committed 5 months ago
docs: rename to '离线 SDK 推理' + add design principles, sync zh/en/v2
0f780ce 游雁 committed 5 months ago
docs: add vllm_guide_zh_v2.md — merged batch inference + streaming SDK into service guide
8ca7fb2 游雁 committed 5 months ago
docs: restore vLLM guide — add English version and Chinese (vllm_guide_zh.md)
bb92a77 游雁 committed 5 months ago
feat: WebSocket SPK as client-controlled param (SPK:true/false, default off)
7d3c216 游雁 committed 5 months ago
docs: fix offline service - split by protocol with per-protocol clients, add WebSocket, note OpenAI no SPK
800bd2c 游雁 committed 5 months ago
docs: final vllm_guide - benchmark first, architecture section, clear service separation
ba2a3ac 游雁 committed 5 months ago
docs: rewrite vllm_guide - separate offline/streaming services, full protocol + client examples
4cc2b75 游雁 committed 5 months ago
docs: rewrite vllm_guide.md - unified structure, dynamic VAD only, stream/offline separation
e46abeb 游雁 committed 5 months ago
feat: update non-streaming dynamic VAD schedule + unified vLLM server
7e2c3f4 xiaoyunchong.xyc committed 5 months ago