Add support for audio input upload in demo interface 1b0acf6 Running MohamedRashad commited on 13 days ago
Enhance audio processing in generate_response by adding prepend and append silence to improve model response timing b840b20 MohamedRashad commited on 15 days ago
Add warmup function to initialize CUDA graphs and improve performance in get_models d96db07 MohamedRashad commited on 15 days ago
Refine sine wave token usage in generate_response function to simulate user silence with official PersonaPlex constants d3a0030 MohamedRashad commited on 15 days ago
Reset streaming state within context in generate_response function 4b1918b MohamedRashad commited on 15 days ago
Enhance response generation by adding silence continuation and simulating user input with sine wave tokens 7e8f6df MohamedRashad commited on 15 days ago
Reorganize imports for moshi models and streamline text tokenizer loading in get_models function a3b50ab MohamedRashad commited on 15 days ago
Implement lazy loading for models in get_models function to optimize GPU resource usage 8c0b009 MohamedRashad commited on 15 days ago
Refactor model loading to initialize on startup and streamline response generation a4b11f0 MohamedRashad commited on 15 days ago
Add initial implementation of PersonaPlex application with Gradio interface e080af3 MohamedRashad commited on 15 days ago
Add main application logic and requirements for PersonaPlex 77e6a0d MohamedRashad commited on 15 days ago
