Wav2vec2 Base Cs Voxpopuli V2

🚀 Wav2Vec2-base-VoxPopuli-V2

This is a base model of Facebook's Wav2Vec2, pretrained only in Czech on 18.7k unlabeled data from the VoxPopuli corpus, aiming to provide a powerful tool for 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 cs on 18.7k unlabeled data of the VoxPopuli corpus.
• Suitable for speech input sampled at 16kHz.

📚 Documentation

Model Details

This model is a base model of Facebook's Wav2Vec2, pretrained only in cs on 18.7k unlabeled data of the VoxPopuli corpus.

Usage 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 cs. 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

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.

📦 Metadata