Wav2vec2 Base Fr Voxpopuli V2

🚀 Wav2Vec2-base-VoxPopuli-V2

This is a base model of Facebook's Wav2Vec2, pretrained only in French on 22.8k unlabeled data from the VoxPopuli corpus, aiming to solve the problem of speech recognition and provide a foundation for related tasks.

🚀 Quick Start

The model is pretrained on 16kHz sampled speech audio. When using the model, make sure that your speech input is also sampled at 16kHz.

⚠️ Important Note

This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model for speech recognition, a tokenizer should be created and the model should be fine-tuned on labeled text data in French. Check out this blog for a more in-detail explanation of how to fine-tune the model.

📚 Documentation

Model Details

Paper Reference

Paper: VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation

Authors: Changhan Wang, Morgane Riviere, Ann Lee, Anne Wu, Chaitanya Talnikar, Daniel Haziza, Mary Williamson, Juan Pino, Emmanuel Dupoux from Facebook AI

More Information

See the official website for more information, here.

📄 License

This model is licensed under the cc-by-nc-4.0 license.