Spanish Wav2Vec2 model pre-trained using the Spanish portion of the Common Voice dataset.

Part of the Flax x Hugging Face community event.

Team: @mariagrandury, @mrm8488, @edugp and @pcuenq.

The model used for training is [Wav2Vec2] by FacebookAI. It was introduced in the paper "wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations" by Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, and Michael Auli (https://arxiv.org/abs/2006.11477).

This model is available in the 🤗 Model Hub.

Spanish portion of Common Voice. Common Voice is an open source, multi-language dataset of voices part of Mozilla's initiative to help teach machines how real people speak.

The dataset is also available in the 🤗 Datasets library.

The script used for training (train.sh) is based on this training script and was modified as explained in setup_modifications.md.