futo-org
/

asr4all-m

Automatic Speech Recognition

feature-extraction

Eval Results (legacy)

Model card Files Files and versions

asr4all-m / executorch /asr4all_executorch.py

Commit History

Sep 24 27 days ago

17:49
asr4all_executorch.py: hold back ExecuTorch's own open_text deprecation warning

lee-futo

Verified signature
2b56699
17:29
asr4all_executorch.py: hold only the selected tier's methods (medium fp32 1.24 GB -> 0.62 GB)

lee-futo

Verified signature
1811966
16:56
asr4all_executorch.py: --tier takes a name or an index

lee-futo

Verified signature
f72914e
16:55
ONNX: one graph per component over one shared weights file; hardened scripts and modeling file

lee-futo

Verified signature
1766e0d
14:38
PCEC keep input: refreshed reference scripts (feed 0 by default), self-contained modeling file, merges in ONNX metadata

lee-futo

Verified signature
fe33a25

Sep 14

20:06
Update release: trimmed VAD section in the model card, schema_version added to onnx/metadata.json (all metadata now v8)

lee-futo

Verified signature
7d39f7b

Sep 7

16:04
medium v2: FINAL_finL_soup5 trunk + PCEC v16 6k pause_do soup_9500_20000⁠

lee-futo

Verified signature
15c9688

Aug 8

01:00
asr4all-m: PCEC in-bundle (transformers + ExecuTorch), GPTQ int8, 32 s windows, new card

lee-futo

Verified signature
5f8d268

Jul 16

19:40
Add files using upload-large-folder tool

lee-futo

Verified signature
cd7d1fd