Wav2vec2 Large Romance Voxpopuli V2

🚀 Wav2Vec2-large-VoxPopuli-V2

This is a large model of Facebook's Wav2Vec2, which is pretrained only in romance on 101.5 unlabeled data of the VoxPopuli corpus. It provides a powerful solution for audio-related tasks, especially automatic speech recognition.

🚀 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.

✨ Features

• Pretrained only in romance on 101.5 unlabeled data of the VoxPopuli corpus.
• Suitable for 16kHz sampled speech audio.

📚 Documentation

Model Information

Important Notes

⚠️ 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 romance. Check out this blog for a more in-detail explanation of how to fine-tune the model.

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 released under the cc-by-nc-4.0 license.