SpiRit-LM: Interleaved Spoken and Written Language Model
Paper โข 2402.05755 โข Published โข 14
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
This repository contains the model weights, inference code and evaluation scripts for the Spirit LM paper. You can find more generation samples on our demo page.
conda env create -f env.yml
pip install -e '.[eval]'
pip install -e '.[eval]'
(Optionally, use only if you want to run the tests.)
pip install -e '.[dev]'
See spiritlm/speech_tokenizer/README.md
More details of the model can be found in MODEL_CARD.md.
The present code is provided under the FAIR Noncommercial Research License found in LICENSE.
@misc{nguyen2024spiritlminterleavedspokenwritten,
title={SpiRit-LM: Interleaved Spoken and Written Language Model},
author={Tu Anh Nguyen and Benjamin Muller and Bokai Yu and Marta R. Costa-jussa and Maha Elbayad and Sravya Popuri and Paul-Ambroise Duquenne and Robin Algayres and Ruslan Mavlyutov and Itai Gat and Gabriel Synnaeve and Juan Pino and Benoit Sagot and Emmanuel Dupoux},
year={2024},
eprint={2402.05755},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2402.05755},
}