Wav2vec2 Base Pl Voxpopuli V2

🚀 Wav2Vec2-base-VoxPopuli-V2

A pre - trained base model from Facebook's Wav2Vec2, trained solely on 21.2k unlabeled Polish data from the VoxPopuli corpus. It's designed for audio and automatic speech - recognition tasks.

🚀 Quick Start

The Facebook's Wav2Vec2 base model is pre - trained only in Polish on 21.2k unlabeled data from the VoxPopuli corpus.

The model is pre - trained on speech audio sampled at 16kHz. When using the model, ensure that your speech input is also sampled at 16kHz.

⚠️ Important Note

This model does not have a tokenizer as it was pre - trained on audio alone. To use this model for speech recognition, a tokenizer should be created, and the model should be fine - tuned on labeled Polish text data. Check out [this blog](https://huggingface.co/blog/fine - tune - xlsr - wav2vec2) for a more detailed explanation of how to fine - tune the model.

📚 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.

📄 License

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