Hugging Face's logo

Dupaja
/
speecht5_tts

Text-to-Speech
Transformers
PyTorch
speecht5
text-to-audio
audio
Model card Files
xet
 Community
1
speecht5_tts / handler.py

Commit History

  1. Add handling for fractions and hopefully other number uses

    Dupaja
    5f8cefd

  1. Increase max length to 400

    Dupaja
    e641a54

  2. Added function to convert digits to written numbers, for handling with SpeechT5

    Dupaja
    279f06b

  3. Update handler.py

    Dupaja
    1e92b35

  4. Rewrite to handle larger text

    Dupaja
    c5c6476

  5. Update handler.py

    Dupaja
    fc3317e

  6. Update handler.py

    Dupaja
    c0208f8

  7. Update handler.py

    Dupaja
    3b62ecd

  8. Update handler.py

    Dupaja
    4fd4826

  9. Added device map

    Dupaja
    4577e7e

  10. Update handler.py

    Dupaja
    617d2a4

  11. Update handler.py

    Dupaja
    9cf2190

  12. Attempt to speed up

    Dupaja
    bd9bb8e

  13. Revert direct file send.

    Dupaja
    d16558b

  14. Update handler.py

    Dupaja
    910abc8

  15. Try sending wav file directly

    Dupaja
    d734a73

  16. Update handler.py

    Dupaja
    be0ef80

  17. Remove unused file write

    Dupaja
    2349229

  18. Add trust_remote_code=True to dataset

    Dupaja
    9594309

  19. Attempt to reduce latency by moving more to init

    Dupaja
    9277202

  1. Update handler.py

    Dupaja
    0824f3c

  2. Update to personal repos

    Dupaja
    5e7a614

  3. Updating using SpeechT5 Article⁠

    Dupaja
    9f940c9

  4. Update handler.py

    Dupaja
    8869945

  5. Update handler.py

    Dupaja
    a4c5e15

  6. Update handler.py

    Dupaja
    402e7d8

  7. Update handler.py

    Dupaja
    9f3bcf5

  8. Update handler.py

    Dupaja
    7b5f670

  9. Update handler.py

    Dupaja
    d65f95a

  10. Fixes

    Dupaja
    74cf751

  11. Create handler.py

    Dupaja
    aaf0168