Wav2Vec2-Large-VoxPopuli

Facebook's Wav2Vec2 large model pretrained on the 100k unlabeled subset of VoxPopuli corpus .

Note : This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model speech recognition , a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model.

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

See the official website for more information, here

Fine-Tuning

Please refer to this blog on how to fine-tune this model on a specific language. Note that you should replace "facebook/wav2vec2-large-xlsr-53" with this checkpoint for fine-tuning.