Commit History

  1. Add support for audio input upload in demo interface Running

    1b0acf6

  1. Enhance audio processing in generate_response by adding prepend and append silence to improve model response timing

    b840b20
  2. Add warmup function to initialize CUDA graphs and improve performance in get_models

    d96db07
  3. Refine sine wave token usage in generate_response function to simulate user silence with official PersonaPlex constants

    d3a0030
  4. Reset streaming state within context in generate_response function

    4b1918b
  5. Enhance response generation by adding silence continuation and simulating user input with sine wave tokens

    7e8f6df
  6. Reorganize imports for moshi models and streamline text tokenizer loading in get_models function

    a3b50ab
  7. Implement lazy loading for models in get_models function to optimize GPU resource usage

    8c0b009
  8. Refactor model loading to initialize on startup and streamline response generation

    a4b11f0
  9. Add initial implementation of PersonaPlex application with Gradio interface

    e080af3
  10. Add main application logic and requirements for PersonaPlex

    77e6a0d
  11. initial commit

    Verified signature
    77728be