Stars
Real-time Speech-Text Foundation Model Toolkit (wip)
Control your computer with a voice interface
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A complete WYSIWYG-texteditor built from scratch based on pygame for pygame.
Simple Timeline Plot In Python with Matplotlib
Retrieves your activation data (activation_bytes) from Audible servers. Using https://github.com/inAudible-NG/tables project instead is recommended.