Commit History

  1. Upload 2 files

    Verified signature
    767a55c

  1. Modify app.py

    04dfe4a
  2. Change V2A demo

    3c0f174
  3. Fix phonemize.py

    e233d72
  4. Fix constants.py

    f548c0d
  5. Fix phonemization

    cdd790d
  6. Fix g2p

    33c7909
  7. Fix parameter error

    f1d7a89
  8. Debug app.py

    1bd1428
  9. Debug app.py

    c52b837
  10. Update requirements.txt

    61d0be0
  11. Add third_party

    fcfa970
  12. Modify modeling_uniflow_audio.py

    e4807fe
  13. Upload models/mmdit

    c2c5dcf
  14. Update requirements.txt

    9601a70
  15. Update requirements.txt

    ddf6553
  16. Update to v1.1

    29e2213
  17. Update to v1.1

    6e6f7d1

  1. Change TTS ref speech

    55fea3f

  1. Unify duration scale: use latent token count for both training and inference

    51bd0e0

  1. Change to g2p_en

    2d1110f
  2. Merge branch 'main' of https://huggingface.co/spaces/wsntxxn/UniFlow-Audio into hf_space

    b3f4baa
  3. Fix g2p issue

    37f392f

  1. Update app.py

    ef6f342
  2. Update app.py

    6e2601b

  1. Fix requirements.txt

    b929107
  2. Merge branch 'main' of https://huggingface.co/spaces/wsntxxn/UniFlow-Audio into hf_space

    6117d23
  3. Adjust tabs

    53eaf02

  1. Update README.md

    864d5c0
  2. Modify minimum steps

    79d437c
  3. Modify app.py

    e192bff
  4. Add LICENSE

    9a2d33b
  5. Modify app.py

    4703c64
  6. Fix errors.

    2ba71a4
  7. Init commit

    b4bbb92