分支列表

默认分支

486b4b7ceb · docs: connect native Transformers guides to tested CUDA recipe (#3697) · 最后更新于 2026-09-10 10:58:26 +00:00

分支列表

31a4e64987 · docs(README): restructure into a clean get-started flow (rebased on main) · 最后更新于 2026-06-23 09:40:41 +00:00    frostbyte_neo

777
1

10901caec8 · fix(sense_voice): remove docstring between @triton.jit and def (SyntaxError) · 最后更新于 2026-06-23 08:09:23 +00:00    frostbyte_neo

778
1

ea70f8d1d6 · docs(README_ko.md): align benchmark with canonical (add Chinese CER, flagship Fun-ASR-Nano vLLM 340x) · 最后更新于 2026-06-23 06:40:08 +00:00    frostbyte_neo

779
3

2ab542dc94 · docs(README): add Chinese CER to benchmark (canonical micro-avg, consistent with funasr.com) · 最后更新于 2026-06-23 05:44:21 +00:00    frostbyte_neo

780
1

6a43ab1765 · docs(README): benchmark shows flagship Fun-ASR-Nano vLLM speed (340x), not the torch number · 最后更新于 2026-06-23 05:39:06 +00:00    frostbyte_neo

781
1

3adfd9facb · docs(README): de-duplicate Quick Start (remove repeated Fun-ASR-Nano section, fix double generate + model flags) · 最后更新于 2026-06-23 02:43:26 +00:00    frostbyte_neo

782
1

d00dc72ef9 · docs(model_selection_zh.md): lead with flagship Fun-ASR-Nano (SenseVoice for CPU) · 最后更新于 2026-06-22 15:40:14 +00:00    frostbyte_neo

783
2

60bf286a21 · docs(README): lead Quick Start with the flagship Fun-ASR-Nano (SenseVoice kept as the CPU/multilingual option) · 最后更新于 2026-06-22 14:39:32 +00:00    frostbyte_neo

784
1

5f0737a48d · docs(README): use canonical iic/ ModelScope namespace (was legacy damo/) · 最后更新于 2026-06-22 02:55:48 +00:00    frostbyte_neo

787
1

91f91770d7 · docs(README): fix broken quickstart (missing input=), remove internal growth-plan link, drop empty docker block, align vLLM speedup · 最后更新于 2026-06-22 02:50:39 +00:00    frostbyte_neo

788
1

ed3d7c3492 · docs(README): update What's New with June updates (llama.cpp/GGUF runtime, q8, releases) · 最后更新于 2026-06-22 02:47:29 +00:00    frostbyte_neo

789
1

0c303f1709 · feat: q8_0 export option (--wtype q8_0) for SenseVoice/Paraformer/Nano encoder GGUF · 最后更新于 2026-06-21 18:20:16 +00:00    frostbyte_neo

790
1

3c7f00098a · docs(README): promote llama.cpp/GGUF runtime to a first-class Deploy section · 最后更新于 2026-06-21 16:47:52 +00:00    frostbyte_neo

791
1

83748a09be · docs(README): make the quickstart runnable (add missing model.generate() call + CPU note) · 最后更新于 2026-06-21 03:59:19 +00:00    frostbyte_neo

795
1

15cd76f1f6 · docs(vllm_guide): drop stale repetition_penalty=1.3 hardcode note (removed in #2974) · 最后更新于 2026-06-20 15:40:50 +00:00    frostbyte_neo

797
3

3e49658bcd · fix: detok review findings (null gguf_get_arr_str guard + utf-8 tokens.json read) · 最后更新于 2026-06-20 08:49:17 +00:00    frostbyte_neo

801
1

9860954c1c · test: fix sensevoice golden (correct transcription text) · 最后更新于 2026-06-20 08:11:49 +00:00    frostbyte_neo

804
3

33155eef01 · feat: print transcription text in the binaries (embed vocab, in-binary detok) · 最后更新于 2026-06-20 08:10:09 +00:00    frostbyte_neo

803
1

34aa4c6a3f · fix: B1 script portability (Hugging Face CLI fallback + friendly missing-dep error) · 最后更新于 2026-06-20 06:52:14 +00:00    frostbyte_neo

805
1

cb6bf7448c · ci: cross-platform prebuilt binary release for llama.cpp runtime · 最后更新于 2026-06-20 06:21:11 +00:00    frostbyte_neo

809
1