Refactor Unsloth model loading to support dynamic loading for ZeroGPU optimization 2b8f9ac mrrtmob commited on Oct 3, 2025
Update Unsloth model loading to check for CUDA availability before importing 01b3444 mrrtmob commited on Oct 3, 2025
Integrate Unsloth for optimized model loading and inference in app.py 6fb0ff5 mrrtmob commited on Oct 3, 2025
Enhance audio format conversion in speech generation for improved compatibility and normalization d36c6eb mrrtmob commited on Oct 3, 2025
Refactor input preparation and token handling in zero-shot TTS for improved audio generation d704f9a mrrtmob commited on Oct 3, 2025
Update model name and voice options in app.py for improved TTS functionality 8c357e5 mrrtmob commited on Oct 2, 2025
Update model name and enhance audio processing in zero-shot TTS 3d13a46 mrrtmob commited on Oct 2, 2025
Refactor inference function and improve audio processing for zero-shot TTS d288914 mrrtmob commited on Oct 2, 2025
Remove example2.mp3 and update examples in app.py to use example2.wav 9a50097 mrrtmob commited on Oct 2, 2025
Increase temperature parameter in inference function for more diverse outputs 5d07488 mrrtmob commited on Oct 2, 2025
Update example text for .mp3 file in app.py to enhance clarity 8b5f782 mrrtmob commited on Oct 2, 2025
Add support for .mp3 files in examples and update label in app.py b5f46eb mrrtmob commited on Oct 2, 2025
Normalize audio samples to int16 format to prevent Gradio warnings cb33cc1 mrrtmob commited on Oct 2, 2025
Add .wav file support to Git LFS for improved asset management 076ec23 mrrtmob commited on Oct 2, 2025
Refactor audio processing in app.py for improved tensor handling and update example inputs in the UI 5f8fcc3 mrrtmob commited on Oct 2, 2025
Add zero-shot TTS functionality and update character limit to 300 b193542 mrrtmob commited on Oct 2, 2025