Update process_input function in app.py to handle audio generation output more robustly, introducing a fallback mechanism for text generation in case of unexpected output formats. Improve error handling during audio and text generation processes. Additionally, update requirements.txt to include flash-attn for enhanced performance.

Add accelerate dependency to requirements.txt

Update requirements.txt to add torchvision and torchaudio dependencies.

Update app.py to change torch data type to float16 and comment out attention implementation; modify requirements.txt to reorder dependencies and remove flash-attn.

Refactor app.py to import 'spaces' and add GPU decorator; update requirements.txt to remove no-build-isolation flag from flash-attn

Add application file