modelscope/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR.git synced 2026-10-12 02:19:18 +00:00
Code Issues Packages Projects Releases Wiki Activity
5,949 Commits 468 Branches 66 Tags
f950854db3379e80a986e779da4e7208f54c0adb
Commit Graph
395 Commits
Author SHA1 Message Date
LauraGPT f950854db3 fix(website): correct LiteLLM transcription route and guards 
Signed-off-by: LauraGPT <[email protected]>
 2026-09-29 03:10:14 +00:00
LauraGPT 99ef3b727b feat(benchmark): report first nonempty transcript latency 
Signed-off-by: LauraGPT <[email protected]>
 2026-09-28 13:36:31 +00:00
LauraGPT e7006a9315 fix: count speaker overlap once per diarization segment 
Signed-off-by: LauraGPT <[email protected]>
 2026-09-28 12:50:06 +00:00
Bruce-YiiandBruce-Yii 41778c45de fix(nano): correct punctuation timestamps across VAD merges (#3703) 
* fix(nano): correct punctuation timestamps across VAD merges

Anchor zero-acoustic-mass punctuation at the preceding spoken token end (FunASR #3702). Reviewed patch only.

* fix(nano): keep byte-fragment spoken timestamps

* test(nano): cover byte-fragment timestamp preservation

* fix(nano): preserve semantic symbol timestamp spans

* test(nano): preserve semantic symbol timestamp spans

---------

Signed-off-by: Bruce-Yii <[email protected]>
Co-authored-by: Bruce-Yii <[email protected]>
 2026-09-25 10:16:47 +08:00
li-lizhe bad0781a2e fix: use y.device instead of hardcoded .cuda() in data2vec compute_var (#3710) 
* fix: use y.device instead of hardcoded .cuda() in data2vec compute_var

In compute_var(), zc = torch.tensor(y.size(0)).cuda() unconditionally
calls .cuda() which raises RuntimeError: Torch not compiled with CUDA
enabled on non-CUDA accelerators (Ascend NPU, XPU, HPU, MPS).

Use device=y.device to respect the input tensor's current device.

Signed-off-by: li-lizhe <[email protected]>

* test: add CPU/Gloo regression tests for data2vec compute_var

Cover both the uninitialized (no process group) branch and a real
2-rank Gloo process group with unequal local row counts, pinning the
device-agnostic contract introduced in the parent commit (PR #3710).

Signed-off-by: li-lizhe <[email protected]>

* fix(test): resolve compute_var import and f32_worker spawn pickle

* fix(test): ensure Manager and workers are cleaned up on failure paths

join(timeout) does not terminate a still-running worker, so a crashed or
hung rank could leak a subprocess on test failure. Wrap the two-rank
runner in try/finally that terminate()+join()s any alive worker and shuts
down the Manager.

Signed-off-by: li-lizhe <[email protected]>

---------

Signed-off-by: li-lizhe <[email protected]>
 2026-09-21 10:28:58 +08:00
Hexu Zhao 782a7a99d5 [perf] Fun-ASR-Nano fine-tuning on B200: 0.244 s to 0.068 s per step at 1 GPU, mostly from cuDNN SDPA plan builds on every new batch shape (#3705) 
* fun_asr_nano: opt-in scoped SDPA backends and compiled decoder for fine-tuning

* tests: FunASRNano opt-ins leave defaults untouched

* fun_asr_nano: declare the torch 2.3 floor the fine-tuning recipe needs
 2026-09-21 10:20:05 +08:00
Xu Xiang 1878d61dbe fix(paraformer): correct timestamp alpha and peak argument order (#3716) 
Pass CIF alpha weights and peak indices to the timestamp helper in its declared order and add boundary/content regressions. Fixes #3723.
 2026-09-19 10:42:09 +08:00
Gmgge b096b7950f fix(campplus): bound clustering thread usage and spectrum work (#3699) 
Apply ncpu to BLAS without rolling back torch OpenMP settings, compute only the required leading spectral pairs, and add regression coverage for repeated AutoModel construction and process-wide thread limits.
 2026-09-19 10:32:10 +08:00
zhifu gao 904cd18681 Release FunASR 1.4.16 (#3719) 
Prepare the 1.4.16 Python release, synchronize four-language release entry points, and make the native Transformers site contract follow the current package version.

Signed-off-by: LauraGPT <[email protected]>
 2026-09-18 12:03:34 +08:00
zhifu gao 4d8e08748c Merge pull request #3706 from damnwenxi/fix/submodel-device-placement 
fix: honor submodel device placement across inference calls
 2026-09-16 10:27:29 +08:00
LauraGPT 1605ad20a3 test: isolate optional clustering dependency 
Signed-off-by: LauraGPT <[email protected]>
 2026-09-16 02:21:55 +00:00
zhifu gao fc98a60342 docs: correct strict ecosystem growth target 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-15 23:34:51 +00:00
zhifu gao 8181a0225e docs: align bilingual roadmap with delivered milestones 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-15 17:47:50 +00:00
zhifu gao 42a7f02d93 test(punctuation): guard SenseVoice documentation on exact PR heads 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-15 14:30:57 +00:00
damnwenxi eee63614f0 test: avoid Python 3.11-only unittest cleanup API 2026-09-14 18:42:44 +08:00
damnwenxi aa353d6d22 fix: honor submodel device placement across inference calls 2026-09-14 09:20:40 +08:00
zhifu gao a111c75059 docs: clarify SenseVoice word timestamp alignment 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-10 08:33:18 +00:00
zhifu gao 1d2307b1ab docs: distinguish native Transformers model downloads 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-10 06:39:10 +00:00
zhifu gao b71671cd2a release(onnx): prepare 0.4.3 with installed artifact regressions 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-09 22:58:58 +00:00
zhifu gao 0f370234a4 test(docs): derive current release checks from package version 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-09 03:42:38 +00:00
zhifu gao 386e51cc15 release: prepare FunASR 1.4.15 with verified NumPy 2 compatibility 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-09 03:23:15 +00:00
hylin 28fa5a4d64 fix: support NumPy 2 with verified scientific-stack compatibility (#3674) 
Retain the contributor alias cleanup and remove the NumPy cap with verified CPU dependency, frontend, masking and clustering coverage.

NumPy 1.26.4 and 2.4.0 each pass 23 exact-head CI tests and 77 local tests plus 184 subtests. Existing EEND mel calls now use keyword arguments for modern librosa.

The related installation issue remains open pending published-package and reporter re-test.

Co-authored-by: linhongyu510 <[email protected]>
Signed-off-by: zhifu gao <[email protected]>
 2026-09-09 10:59:37 +08:00
zhifu gao 4abb706cd5 feat(examples): add MOSS diarization to offline vLLM sample 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-08 22:11:20 +00:00
zhifu gao cad08344f6 fix(training): rank checkpoints only with valid validation metrics 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-08 21:07:19 +00:00
zhifu gao 2df180c636 fix(vad): exclude idle time from dynamic silence schedule 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-08 20:15:17 +00:00
zhifu gao 53fbe89b65 test: keep rendering checks in the product-site suite 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-08 18:41:03 +00:00
zhifu gao 5a2b449d3e docs: distinguish model checkpoints and serving interfaces 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-08 18:28:55 +00:00
zhifu gao cdb6683516 docs: align deployment matrix recipes and fix copy icon contrast 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 22:10:59 +00:00
zhifu gao 387e3f8782 docs: fix Kubernetes recipes and connect Gradio website guides 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 21:18:26 +00:00
zhifu gao 0ae8a84832 docs: align root deployment recipes and CLI help with service contracts 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 20:30:40 +00:00
zhifu gao 11198050ce docs: align Gradio guides with isolated MOSS serving profiles 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 19:53:23 +00:00
zhifu gao d91d961e37 feat: add explicit MOSS serving profiles to Gradio client 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 19:12:22 +00:00
zhifu gao 49150dd091 docs: harden authenticated gateway boundaries in security guides 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 18:18:47 +00:00
zhifu gao 6627977d95 docs: harden JavaScript integration recipes and response contracts 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 17:20:48 +00:00
zhifu gao 160494c4c4 docs: clarify low-code workflow deployment and response contracts 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 16:08:47 +00:00
zhifu gao 8d1f5b64db docs: align four-language HTTP service setup and response contracts 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 15:03:23 +00:00
zhifu gao 564c4d91a3 docs: align English vLLM installation and native validation contracts 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 11:02:41 +00:00
zhifu gao 893bb068ed docs: consolidate Chinese vLLM guides with checked compatibility mirror 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 10:21:57 +00:00
zhifu gao f4c5d9385b docs: add speaker and emotion task guides 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 08:53:08 +00:00
zhifu gao 391174c38f docs(kws): add bilingual task guides and tested session examples 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 08:13:07 +00:00
zhifu gao d83a92475d fix(kws): preserve streaming frames across packet and EOS boundaries 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 07:39:13 +00:00
zhifu gao beb92d9f43 fix(kws): honor optional output directory on every call 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 07:01:26 +00:00
zhifu gao 3ac13e5049 docs: add bilingual streaming VAD task guide 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 05:53:40 +00:00
zhifu gao f0728b758c docs: preserve API signatures and discover AutoModelVLLM 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-07 03:38:20 +00:00
zhifu gao 2d2d385545 Merge pull request #3651 from modelscope/codex/cli-documentation-contract-20260907 
docs: align bilingual CLI guide with parser and output contracts
 2026-09-07 06:56:08 +08:00
zhifu gao 0ccbc82469 docs: align bilingual CLI guide with parser and output contracts 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-06 22:37:12 +00:00
zhifu gao 1aff355786 docs: make multilingual README entrypoints task-oriented 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-06 22:22:43 +00:00
zhifu gao 2dfe391936 docs: finish reference navigation and correct model and vLLM contracts 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-06 17:43:37 +00:00
zhifu gao c75338c995 docs: resolve repository links in legacy Sphinx output 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-06 15:20:07 +00:00
zhifu gao f958aab5b8 docs: rebuild the learning, model and serving documentation system 
Signed-off-by: zhifu gao <[email protected]>
 2026-09-06 14:11:58 +00:00