Hugging Face's logo

futo-org
/
asr4all-s

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

Commit History

28 days ago

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

    lee-futo
    Verified signature
    745a98f

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

    lee-futo
    Verified signature
    b913645

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

    lee-futo
    Verified signature
    39c37d7

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

    lee-futo
    Verified signature
    e0efc2e

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

    lee-futo
    Verified signature
    729d7ca

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

    lee-futo
    Verified signature
    88bb29d

  1. card: reduce semicolons/em-dashes, rename to Streaming tiers, fix right_ctx range wording + validation

    lee-futo
    Verified signature
    c26b6ea

  2. reference scripts: natural-language comments, drop card-covered detail (onnx + executorch)

    lee-futo
    Verified signature
    567d5fc

  3. fir25 release: card overhaul + session(commit_chunk, right_ctx) tier-aligned API

    lee-futo
    Verified signature
    e53aa54