Hugging Face's logo

ttslab
/
chatterbox-turbo-webgpu

Text-to-Speech
Transformers.js
ONNX
Chatterbox
tts
webgpu
Model card Files
xet
 Community
chatterbox-turbo-webgpu

Commit History

  1. revert: upload unmodified spacekaren/chatterbox-turbo-webgpu models (our INT64 fix was breaking them)

    MbBrainz
    Verified signature
    bf19996

  2. Fix: detect literal tensor(int64) type strings, not just type constraint params — fixes Unsqueeze/Reshape/Squeeze/Expand/Pad/ReduceSum/ReduceMean/Resize/ScatterND

    MbBrainz
    Verified signature
    4a0c481

  3. Schema-driven fix: ConstantOfShape/Tile INT64 constraints + comprehensive type validation

    MbBrainz
    Verified signature
    02b5b8c

  1. Fix: forward type propagation resolves unknown tensor types; fixes Concat/Reshape cascade errors

    MbBrainz
    Verified signature
    da6970a

  2. Fix structural inputs with unknown types: safety Cast(->INT64) for Concat/Unsqueeze outputs feeding Reshape/Expand/Slice

    MbBrainz
    Verified signature
    30e73aa

  3. Fix Range type mismatches: switch to schema-based type detection covering all ONNX operators

    MbBrainz
    Verified signature
    a3bcb19

  4. Fix all WebGPU type issues: Shape dtype, structural INT64, Cast insertion for type mismatches

    MbBrainz
    Verified signature
    9e30c11

  5. fix: restore INT64 for structural inputs (axes/shape/starts) + remove Shape dtype + regenerate value_info

    MbBrainz
    Verified signature
    19e5b24

  6. fix: minimal fix - only remove Shape dtype + regenerate value_info via shape inference

    MbBrainz
    Verified signature
    492c7cb

  7. fix: use shape inference for correct value_info types (fixes Shape/Gather INT64 mismatches)

    MbBrainz
    Verified signature
    b62334a

  8. fix: preserve INT64 on Shape outputs + remove dtype attr for WebGPU EP

    MbBrainz
    Verified signature
    bf9235b

  9. fix: remove Shape dtype attribute + INT64→INT32 for WebGPU EP compatibility

    MbBrainz
    Verified signature
    cce102d

  1. Fix all int64→int32 type annotations for WebGPU compatibility

    MbBrainz
    Verified signature
    796ab40

  2. initial commit

    MbBrainz
    Verified signature
    dbee32a