Reproducing Speech-to-Text Translation Results

This artifact contains the code and methodology used to reproduce the S2TT results from the studies "SeamlessM4T: Massively Multilingual & Multimodal Machine Translation" and "Robust Speech Recognition via Large-Scale Weak Supervision". It provides various notebooks for users to evaluate model translations over the CoVoST 2 and FLEURS dataset.

It can also be accessed on GitHub at :

1 1 1 1 May. 7, 2024, 4:41 PM


Launch on Chameleon

Launching this artifact will open it within Chameleon’s shared Jupyter experiment environment, which is accessible to all Chameleon users with an active allocation.

Download Archive

Download an archive containing the files of this artifact.

Download with git

Clone the git repository for this artifact, and checkout the version's commit

git clone
# cd into the created directory
git checkout 83fce6067e53900e4f351d3163f38c9d46ffb279

Submit feedback through GitHub issues

Version Stats

1 1 1