Spaces:
Running
Running
Commit History
9 days ago
-
fix: keep API parameter names, reject unknown voices, and stop cloned Chatterbox voices reaching other users Running
Michael Hu4d9637e -
refactor: build the Gradio tabs from shared TTS and STT tab builders in src/ui.py
Michael Hu9a0aa93 -
refactor: move model loading and WAV output into shared TTS and STT base classes
Michael Hucf1c514 -
feat: add Cactus Whistle speech recognition tab with telemetry turned off
Michael Huc829773 -
refactor: delete the unused Dia TTS source files
Michael Hubde42b3 -
fix: pin the Space to Python 3.10, which kokoro and misaki require
Michael Hu8e9dfc5 -
refactor: remove the dead Dia TTS tab and its factory entry
Michael Hu7de9251 -
fix: guard KittenTTS 2 reference transcription and pin gradio 6.8.0 explicitly
Michael Hu666bdaf -
feat: add KittenTTS 2 tab with built-in voices, voice cloning and expression presets
Michael Hud8fa107 -
fix: repair Piper, KittenTTS, Kokoro and Whisper wrappers and show errors in the UI
Michael Hu19f22b1 -
fix(deps): pin chatterbox-tts 0.1.7 and switch to kittenml so the Space builds
Michael Hu1f0e503
-
fix: update Kokoro TTS model to use new pipeline interface and 24 kHz sample rate
Michael Hu3ab544b -
fix: replace Kokoro model's TTS call with direct waveform generation
Michael Hu97fe901 -
fix: ensure Kokoro TTS model is initialized before use and handle missing audio file edge case
Michael Hu9b4a9ad -
refactor(tts): simplify gradio component update calls
Michael Huba9d64e -
refactor: replace inline model definitions with ModelFactory and remove unused imports
Michael Hu- Remove all hard-coded model definitions and import the new factory - Delete unused imports (torchaudio, sys, soundfile, transformers, etc.) - Eliminate duplicate code for model discovery and voice handling - Delete unused utility functions and duplicate code paths - Remove unused dependency on librosa and soundfileef4db28 -
feat: add jieba for Chinese text segmentation
Michael Hub5ac4eb -
feat: add cn2an dependency for Chinese number conversion
Michael Hu36e3e87 -
feat: add pypinyin dependency and update voice mapping in app.py
Michael Hu087b567 -
refactor(kokoro): update Kokoro voice list with comprehensive options
Michael Hu- Updated voice mapping with expanded options for all supported languages - Changed reference URL from GitHub to HuggingFace documentation - Improved code organization with better comments and structure - Added more voice variants including male voices for certain languages5ac76d6 -
feat: add Kokoro TTS voice selection for different languages
Michael Hu885153e -
chore(deps): add ordered_set to requirements
Michael Hu33602fd -
fix: remove pinned version for kokoro in requirements.txt
Michael Hu9ad16e1 -
fix: remove version constraint on transformers package
Michael Huc6d95a9 -
refactor: remove DiaTTS integration and related UI elements
Michael Hu3d5e706 -
chore(deps): update transformers to version 4.53.0 or higher
Michael Hu51e5e89 -
feat: add Piper TTS UI components and remove duplicate Dia TTS UI
Michael Hud293a11 -
chore(deps): update transformers and kokoro dependencies
Michael Hu3f1d4fe -
feat: add support for Dia-1.6B TTS model in TTS Gallery
Michael Hub68dcac
-
feat: add Kokoro-82M TTS model support
Michael Hu- Add Kokoro-82M TTS model support to the app - Update README to mention Kokoro model - Add Kokoro-82M to the list of supported models - Add Kokoro-82M to the list of supported models in the app8829e6c -
implement faster whisper
Michael Hu6c4b49c -
remove vibevoice
Michael Hud77f8ff
-
fix: ensure tensor dtype consistency in VibeVoice inference pipeline
Michael Hu- Ensure speech tensors match model's data type before processing - Ensure voice samples are properly typed before processor - Ensure model dtype is used for all tensor operations - Remove redundant device/dtype conversions in VibeVoice inferencedda48cd -
refactor: remove debug print statements from VibeVoice generation pipeline
Michael Hufa35900 -
fix: remove debug prints from VibeVoice generation pipeline
Michael Huc5bfdf4 -
fix: remove debug prints and unused generation parameter
Michael Hu- Remove leftover debug prints in generate_vibevoice_speech - Remove unused max_new_tokens parameter in vibevoice generation0942f7f -
fix bug
Michael Hu9c4aeaa
-
add debug info
Michael Hu76a7cf4 -
fix: correct path to voice presets directory
Michael Hu3a5c31e -
fix: correct path to voice presets directory
Michael HuThe path to the voice preset directory was updated to match the new project structure.dc7d687 -
fix: correct import path for BaseStreamer in streamer.py
Michael Hu6dad813 -
fix: remove unused import of FlashAttentionKwargs
Michael Hu385cf36 -
fix: correct path reference for vibe-voice module
Michael Hu351a248 -
Upload 9 files
Verified signaturec926ea8 -
rename directory
Michael Hua9828ff -
Delete src/vibe-voice/vibe_voices
Verified signature584a954 -
fix: remove unused import of FlashAttentionKwargs
Michael Hua02d5d3 -
fix import path for vibe voice
Michael Hufa748d0 -
upload voices
Verified signature5ce7e4b -
remove voices
Michael Hu717e58d