aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)
$ git clone https://github.com/readbeyond/aeneas.git🤗 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.
Open-source offline translation library written in Python
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
the open-source virtual assistant for Ubuntu based Linux distributions
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
The fastest way to build and start training your own LLM. CLI tool that scaffolds production-ready PyTorch training projects in seconds. Like create-next-app but for language models.
Data from GitHub · snapshot Sep 24, 2026