Commit History

9 days ago

  1. fix: keep API parameter names, reject unknown voices, and stop cloned Chatterbox voices reaching other users Running

    Michael Hu
    4d9637e
  2. refactor: build the Gradio tabs from shared TTS and STT tab builders in src/ui.py

    Michael Hu
    9a0aa93
  3. refactor: move model loading and WAV output into shared TTS and STT base classes

    Michael Hu
    cf1c514
  4. feat: add Cactus Whistle speech recognition tab with telemetry turned off

    Michael Hu
    c829773
  5. refactor: delete the unused Dia TTS source files

    Michael Hu
    bde42b3
  6. fix: pin the Space to Python 3.10, which kokoro and misaki require

    Michael Hu
    8e9dfc5
  7. refactor: remove the dead Dia TTS tab and its factory entry

    Michael Hu
    7de9251
  8. fix: guard KittenTTS 2 reference transcription and pin gradio 6.8.0 explicitly

    Michael Hu
    666bdaf
  9. feat: add KittenTTS 2 tab with built-in voices, voice cloning and expression presets

    Michael Hu
    d8fa107
  10. fix: repair Piper, KittenTTS, Kokoro and Whisper wrappers and show errors in the UI

    Michael Hu
    19f22b1
  11. fix(deps): pin chatterbox-tts 0.1.7 and switch to kittenml so the Space builds

    Michael Hu
    1f0e503

  1. fix: update Kokoro TTS model to use new pipeline interface and 24 kHz sample rate

    Michael Hu
    3ab544b
  2. fix: replace Kokoro model's TTS call with direct waveform generation

    Michael Hu
    97fe901
  3. fix: ensure Kokoro TTS model is initialized before use and handle missing audio file edge case

    Michael Hu
    9b4a9ad
  4. refactor(tts): simplify gradio component update calls

    Michael Hu
    ba9d64e
  5. refactor: replace inline model definitions with ModelFactory and remove unused imports⁠

    Michael Hu
    ef4db28
  6. feat: add jieba for Chinese text segmentation

    Michael Hu
    b5ac4eb
  7. feat: add cn2an dependency for Chinese number conversion

    Michael Hu
    36e3e87
  8. feat: add pypinyin dependency and update voice mapping in app.py

    Michael Hu
    087b567
  9. refactor(kokoro): update Kokoro voice list with comprehensive options⁠

    Michael Hu
    5ac76d6
  10. feat: add Kokoro TTS voice selection for different languages

    Michael Hu
    885153e
  11. chore(deps): add ordered_set to requirements

    Michael Hu
    33602fd
  12. fix: remove pinned version for kokoro in requirements.txt

    Michael Hu
    9ad16e1
  13. fix: remove version constraint on transformers package

    Michael Hu
    c6d95a9
  14. refactor: remove DiaTTS integration and related UI elements

    Michael Hu
    3d5e706
  15. chore(deps): update transformers to version 4.53.0 or higher

    Michael Hu
    51e5e89
  16. feat: add Piper TTS UI components and remove duplicate Dia TTS UI

    Michael Hu
    d293a11
  17. chore(deps): update transformers and kokoro dependencies

    Michael Hu
    3f1d4fe
  18. feat: add support for Dia-1.6B TTS model in TTS Gallery

    Michael Hu
    b68dcac

  1. feat: add Kokoro-82M TTS model support⁠

    Michael Hu
    8829e6c
  2. implement faster whisper

    Michael Hu
    6c4b49c
  3. remove vibevoice

    Michael Hu
    d77f8ff

  1. fix: ensure tensor dtype consistency in VibeVoice inference pipeline⁠

    Michael Hu
    dda48cd
  2. refactor: remove debug print statements from VibeVoice generation pipeline

    Michael Hu
    fa35900
  3. fix: remove debug prints from VibeVoice generation pipeline

    Michael Hu
    c5bfdf4
  4. fix: remove debug prints and unused generation parameter⁠

    Michael Hu
    0942f7f
  5. fix bug

    Michael Hu
    9c4aeaa

  1. add debug info

    Michael Hu
    76a7cf4
  2. fix: correct path to voice presets directory

    Michael Hu
    3a5c31e
  3. fix: correct path to voice presets directory⁠

    Michael Hu
    dc7d687
  4. fix: correct import path for BaseStreamer in streamer.py

    Michael Hu
    6dad813
  5. fix: remove unused import of FlashAttentionKwargs

    Michael Hu
    385cf36
  6. fix: correct path reference for vibe-voice module

    Michael Hu
    351a248
  7. Upload 9 files

    Verified signature
    c926ea8
  8. rename directory

    Michael Hu
    a9828ff
  9. Delete src/vibe-voice/vibe_voices

    Verified signature
    584a954
  10. fix: remove unused import of FlashAttentionKwargs

    Michael Hu
    a02d5d3
  11. fix import path for vibe voice

    Michael Hu
    fa748d0
  12. upload voices

    Verified signature
    5ce7e4b
  13. remove voices

    Michael Hu
    717e58d