Update model version to v1.0.0 and adjust initialization logic for voice selection d0c45ea Remsky commited on about 1 month ago
Refactor TTSModelV1 to remove JSON voice mappings and load voices from the voices_v1 directory 9aea310 Remsky commited on about 1 month ago
Refactor TTSModelV1 to load voice mappings from JSON and simplify voice selection 80c0dbf Remsky commited on about 1 month ago
Update TTSModelV1 to use v1 voices from Kokoro-82M repository bb43905 Remsky commited on about 1 month ago
Refactor TTS model initialization and add support for multiple versions 372ebd3 Remsky commited on about 1 month ago
Update TTSModel to verify local voice files and handle missing downloads 3a912ba Remsky commited on about 1 month ago
Update voice file download paths in TTSModel to use v0.19 directory 47dfb0a Remsky commited on about 1 month ago
Enhance voice loading process in TTSModel with error handling and initialization checks 439e117 Remsky commited on about 1 month ago
Add fallback mechanism for loading voicepack in TTSModel 0f830fe Remsky commited on about 1 month ago
Update TTSModel to load modules and model files from v0.19 directory 1b3eebf Remsky commited on about 1 month ago
Adjust label styling and reduce max lines for text input in TTS demo a6f09f7 Remsky commited on Jan 7
Increase max lines for text input and update header content for clarity bb36488 Remsky commited on Jan 7
Remove static text from labels in TTS demo and update label formatting bf1c3fd Remsky commited on Jan 7
Add .gitignore, update requirements, and implement book processing utilities 9a2b6d1 Remsky commited on Jan 7
Set default voice to 'af_sky' if available when updating voice choices 58d7f44 Remsky commited on Jan 3
Refactor app.py to improve UI structure and modularize header content; add ui_content.py for HTML and Markdown components c6b98ce Remsky commited on Jan 3
Update README to reflect project name change, enhance description, and adjust pinned status 3d786a0 Remsky commited on Jan 3
Enhance performance metrics visualization in app.py and update plot saving format in tts_model.py 4468500 Remsky commited on Jan 3
Add audio and text utility modules, update requirements, and revise README cb7f5d0 Remsky commited on Jan 3
Refactor README and app.py to streamline voice descriptions and remove outdated dependency information 6a9df48 Remsky commited on Jan 3
Add initial implementation of Kokoro TTS Demo Space with Gradio interface and dependencies 13eb4ae Remsky commited on Jan 3
