Hugging Face's logo

futo-org
/
asr4all-m-plus

Automatic Speech Recognition
Transformers
ONNX
Safetensors
ExecuTorch
English
asr4all
feature-extraction
speech
ctc
streaming
on-device
edge
custom_code
Eval Results (legacy)
Model card Files
xet
 Community
asr4all-m-plus / executorch /asr4all_executorch.py

Commit History

27 days ago

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

    lee-futo
    Verified signature
    3e15eea

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

    lee-futo
    Verified signature
    8a1361f

  3. asr4all_executorch.py: --tier takes a name or an index

    lee-futo
    Verified signature
    ea37e3d

  4. ONNX: one graph per component over one shared weights file; hardened scripts and modeling file

    lee-futo
    Verified signature
    36c4b70

  5. PCEC keep input: refreshed reference scripts (feed 0 by default), self-contained modeling file, merges in ONNX metadata

    lee-futo
    Verified signature
    f3bf13b

  1. asr4all+ m: full GPTQ coverage on the speaker heads, sv rung ladder, FSMN VAD on all surfaces, Diarizer-first card with through-.pte EER/DER (rel-2026-09-18)

    lee-futo
    Verified signature
    216bd23