Update generate_speech function to accept max_new_tokens as a parameter and adjust default slider value to 1200 1f2a815 Running mrrtmob commited on 5 days ago
Update generate_speech function to accept max_new_tokens as a parameter and adjust default slider value to 1200 fb01dbf mrrtmob commited on 5 days ago
Increase max_new_tokens slider range to 2000 for extended audio generation length ad55e53 mrrtmob commited on 5 days ago
Increase max_new_tokens in speech generation function to enhance output length b2f975e mrrtmob commited on 5 days ago
Refactor text validation to a character counter; streamline speech generation process and improve UI feedback 54096db mrrtmob commited on 5 days ago
Refactor code structure for improved readability and maintainability deb01cb mrrtmob commited on 5 days ago
Implement rate limiting for speech generation and enhance text validation; improve UI with character count and custom CSS 3d2ce0a mrrtmob commited on 5 days ago
Refactor authentication and model loading; simplify UI and reduce resource usage e173776 mrrtmob commited on 5 days ago
Refactor model loading to remove device_map and manually move model to device 731d214 mrrtmob commited on 5 days ago
Add Hugging Face authentication and improve speech generation settings 2938eff mrrtmob commited on 6 days ago
Integrate OpenAI API for enhanced LLM functionality and update configuration settings ecf63b4 mrrtmob commited on 7 days ago
Add new dependencies: openai-whisper, requests, and gradio to requirements.txt 4b72318 mrrtmob commited on 7 days ago
Refactor generate_speech function to change default voice parameter from "tara" to "Elise" 399c1c4 mrrtmob commited on 7 days ago
Enhance Khmer TTS UI with advanced settings and improve code clarity 319cfac mrrtmob commited on 7 days ago
Update Khmer TTS model to version 2 and simplify UI components 0100eae mrrtmob commited on 7 days ago
mrrtmob
commited on
