Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

Commits on main

llama.cpp: add srt output (#3480)
Dingyuan Wang committed 3 months ago
b0d44bd
docs(vllm): clarify official model paths (#3476)
zhifu gao committed 3 months ago
680b1b3
test(site): refresh ecosystem contract (#3474)
zhifu gao committed 3 months ago
ea21a7e
docs(site): refresh ecosystem evidence (#3473)
zhifu gao committed 3 months ago
1e6ec0c
6829ba7
chore: prepare FunASR 1.4.1 release
LauraGPT committed 3 months ago
7a97401
187dc73
5405b74
9987990
6408aaa
feat(runtime): add JSONL timestamp output (#3462)
zhifu gao committed 3 months ago
4dc8e5b
76e5927
test(nano): make LoRA tests deterministic (#3459)
张思远 (ZhangSiYuan) committed 3 months ago
a2a9f67
feat(nano): support LoRA finetuning of the Qwen3 LLM (#3456)
张思远 (ZhangSiYuan) committed 3 months ago
0738581
docs: publish FunASR v1.4.0 release guide (#3452)
zhifu gao committed 3 months ago
d1007c3
fix(runtime): give AudioFrame deep-copy ownership
wangxiuwen committed 3 months ago
62037b1
fix(runtime): free custom AVIO buffers on all exits
wangxiuwen committed 3 months ago
c3c6606
b8c60ae
feat(site): add audio.cpp deployment path (#3447)
zhifu gao committed 3 months ago
5f17769
fix: include runtime package data (#3445)
zhifu gao committed 3 months ago
1359151
chore: prepare FunASR 1.4.0 release (#3444)
zhifu gao committed 3 months ago
e65f6ba