Wav2vec2 Large Mt Voxpopuli V2

🚀 Wav2Vec2-large-VoxPopuli-V2

This is a large model based on Facebook's Wav2Vec2, which is pretrained only in Maltese (mt) on 9.1 hours of unlabeled data from the VoxPopuli corpus, aiming to provide high - quality automatic speech recognition capabilities.

🚀 Quick Start

This model is pretrained on 16kHz sampled speech audio. 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, a tokenizer should be created, and the model should be fine - tuned on labeled text data in Maltese (mt). Check out [this blog](https://huggingface.co/blog/fine - tune-xlsr - wav2vec2) for a more in - detail explanation of how to fine - tune the model.

📚 Documentation

Model Information

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.

Official Website

See the official website for more information, here.

📄 License

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