fix: update Kokoro TTS model to use new pipeline interface and 24 kHz sample rate
3ab544b
Running
Michael Hu
commited on
Spaces:
Running
Running
Commit History
fix: replace Kokoro model's TTS call with direct waveform generation
97fe901
Michael Hu
commited on
fix: ensure Kokoro TTS model is initialized before use and handle missing audio file edge case
9b4a9ad
Michael Hu
commited on
refactor(tts): simplify gradio component update calls
ba9d64e
Michael Hu
commited on
refactor: replace inline model definitions with ModelFactory and remove unused imports
ef4db28
Michael Hu
commited on
feat: add jieba for Chinese text segmentation
b5ac4eb
Michael Hu
commited on
feat: add cn2an dependency for Chinese number conversion
36e3e87
Michael Hu
commited on
feat: add pypinyin dependency and update voice mapping in app.py
087b567
Michael Hu
commited on
refactor(kokoro): update Kokoro voice list with comprehensive options
5ac76d6
Michael Hu
commited on
feat: add Kokoro TTS voice selection for different languages
885153e
Michael Hu
commited on
chore(deps): add ordered_set to requirements
33602fd
Michael Hu
commited on
fix: remove pinned version for kokoro in requirements.txt
9ad16e1
Michael Hu
commited on
fix: remove version constraint on transformers package
c6d95a9
Michael Hu
commited on
refactor: remove DiaTTS integration and related UI elements
3d5e706
Michael Hu
commited on
chore(deps): update transformers to version 4.53.0 or higher
51e5e89
Michael Hu
commited on
feat: add Piper TTS UI components and remove duplicate Dia TTS UI
d293a11
Michael Hu
commited on
chore(deps): update transformers and kokoro dependencies
3f1d4fe
Michael Hu
commited on
feat: add support for Dia-1.6B TTS model in TTS Gallery
b68dcac
Michael Hu
commited on
feat: add Kokoro-82M TTS model support
8829e6c
Michael Hu
commited on
implement faster whisper
6c4b49c
Michael Hu
commited on
remove vibevoice
d77f8ff
Michael Hu
commited on
fix: ensure tensor dtype consistency in VibeVoice inference pipeline
dda48cd
Michael Hu
commited on
refactor: remove debug print statements from VibeVoice generation pipeline
fa35900
Michael Hu
commited on
fix: remove debug prints from VibeVoice generation pipeline
c5bfdf4
Michael Hu
commited on
fix: remove debug prints and unused generation parameter
0942f7f
Michael Hu
commited on
fix bug
9c4aeaa
Michael Hu
commited on
add debug info
76a7cf4
Michael Hu
commited on
fix: correct path to voice presets directory
3a5c31e
Michael Hu
commited on
fix: correct path to voice presets directory
dc7d687
Michael Hu
commited on
fix: correct import path for BaseStreamer in streamer.py
6dad813
Michael Hu
commited on
fix: remove unused import of FlashAttentionKwargs
385cf36
Michael Hu
commited on
fix: correct path reference for vibe-voice module
351a248
Michael Hu
commited on
Upload 9 files
c926ea8
verified
rename directory
a9828ff
Michael Hu
commited on
Delete src/vibe-voice/vibe_voices
584a954
verified
fix: remove unused import of FlashAttentionKwargs
a02d5d3
Michael Hu
commited on
fix import path for vibe voice
fa748d0
Michael Hu
commited on
upload voices
5ce7e4b
verified
remove voices
717e58d
Michael Hu
commited on
move folder
bee6679
Michael Hu
commited on
feat: add missing import for sys module
7431fb0
Michael Hu
commited on
update path
856b0cf
Michael Hu
commited on
add vibevoice voices
47f3e8a
verified
update gitignore
375f2db
Michael Hu
commited on
adopt vibe voice demo impl
5e75590
try workaround in https://huggingface.co/microsoft/VibeVoice-1.5B/discussions/30#68ba11712f03525b46636e7e
9da23cb
Michael Hu
commited on
add support for microsoft vibevoice
315ec3a
Michael Hu
commited on
add description
a7713a8
Michael Hu
commited on
refactor: rename generate_speech to generate_chatterbox_speech and add generation kwargs
1561c93
Michael Hu
commited on
feat: add language and voice selection to Piper
a9213f0
Michael Hu
commited on