An interactive notebook with audio to audio LLM, built with Gradio WebUI.
For anyone interested in talking to an AI Large Language Model in your browser.
This is a very simple implementation that runs in Colab using the Gradio interface that combines Speech to Text, a Language Model, and Text To Speech.
The below is a links to source models
Speech to Text - openai/whisper-base https://huggingface.co/openai/whisper-base
Language Model - smallcloudai/Refact-1_6B-fim https://huggingface.co/smallcloudai/Refact-1_6B-fim
Text To Speech "microsoft/speecht5_tts" https://huggingface.co/microsoft/speecht5_tts
