Wav2vec2 Base En Voxpopuli V2

🚀 Wav2Vec2-base-VoxPopuli-V2

This is a base model of Facebook's Wav2Vec2, pretrained only in English on 24.1k unlabeled data from the VoxPopuli corpus, aiming to facilitate automatic speech recognition tasks.

🚀 Quick Start

This model is pretrained on speech audio sampled at 16kHz. When using the model, ensure that your speech input is also sampled at 16kHz.

Note: This model does not have a tokenizer as it was pretrained on audio alone. To use this model for speech recognition, you need to create a tokenizer and fine - tune the model on labeled text data in English. Check out this blog for a more detailed explanation of how to fine - tune the model.

✨ Features

• Pretrained on the VoxPopuli corpus, which provides rich and diverse speech data.
• Based on the Wav2Vec2 architecture, leveraging the power of Transformer for speech processing.

📦 Information

📚 Documentation

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.

⚠️ Important Note

This model was pretrained on audio alone and does not have a tokenizer. To use it for speech recognition, you need to create a tokenizer and fine - tune it on labeled text data in English.

💡 Usage Tip

Refer to this blog for a more detailed guide on fine - tuning the model.