Wav2vec2 Spanish

🚀 Wav2Vec2 Spanish

A pre - trained Wav2Vec2 model using the Spanish portion of the Common Voice dataset, trained with Flax on Google - sponsored TPUs as part of the Flax/Jax Community Week.

🚀 Quick Start

The Wav2Vec2 Spanish model is pre - trained on the Spanish part of the Common Voice dataset. It's trained with Flax on Google - sponsored TPUs as part of the Flax/Jax Community Week organized by HuggingFace.

✨ Features

• Pre - trained on Spanish: Utilizes the Spanish portion of the Common Voice dataset.
• Flax - based: Trained with the Flax framework.
• TPU - powered: Trained on Google - sponsored TPUs.

📚 Documentation

Model description

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.

Training data

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

The dataset is also available in the 🤗 Datasets library.

Team members

• María Grandury (@mariagrandury)
• Manuel Romero (@mrm8488)
• Eduardo González Ponferrada (@edugp)
• pcuenq (@pcuenq)