metadata

language: fr
thumbnail: null
tags:
  - wav2vec2
license: apache-2.0

LeBenchmark: wav2vec2 base model trained on 1K hours of French female-only speech

LeBenchmark provides an ensemble of pretrained wav2vec2 models on different French datasets containing spontaneous, read, and broadcasted speech.

For more information about our gender study for SSL moddels, please refer to our paper at: A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems

Model and data descriptions

We release four gender-specific models trained on 1K hours of speech.

Intended uses & limitations

Pretrained wav2vec2 models are distributed under the Apache-2.0 license. Hence, they can be reused extensively without strict limitations. However, benchmarks and data may be linked to corpora that are not completely open-sourced.

Referencing our gender-specific models

Referencing LeBenchmark

@article{Evain2021LeBenchmarkAR,
  title={LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech},
  author={Sol{\`e}ne Evain and Ha Nguyen and Hang Le and Marcely Zanon Boito and Salima Mdhaffar and Sina Alisamir and Ziyi Tong and N. Tomashenko and Marco Dinarelli and Titouan Parcollet and A. Allauzen and Y. Est{\`e}ve and B. Lecouteux and F. Portet and S. Rossato and F. Ringeval and D. Schwab and L. Besacier},
  journal={ArXiv},
  year={2021},
  volume={abs/2104.11462}
}