Pinned Loading

1. vid2cleantxt vid2cleantxt Public

   Python API & command-line tool to easily transcribe speech-based video files into clean text

   Jupyter Notebook 218 29

2. textsum textsum Public

   CLI & Python API to easily summarize text-based files with transformers

   Python 132 9

3. megalodon-hf megalodon-hf Public

   Pure PyTorch + 🤗Transformers reimplementation of the Megalodon language-model arch

   Python 1

4. UL2_5 UL2_5 Public

   data collation for encoder-decoder models (T5, FLAN, etc.) implementing + improving the UL2 mixture-of-denoisers obj

   Python

5. NeoBERT NeoBERT Public

   Forked from chandar-lab/NeoBERT

   fork of NeoBERT refactored for easier experimentation, WIP

   Python

6. rehuman rehuman Public

   Unicode-safe text cleaning & typographic normalization for Rust

   Rust