From the source
To fine-tune XLS-R, a multilingual speech representation model, for automatic speech recognition using the Hugging Face Transformers library, with a focus on low-resource languages.
Fine-Tune XLSR-Wav2Vec2 for low-resource ASR with 🤗 Transformers
Story of the weekResearch paper
From the source
Wav2Vec2 is a pretrained model for Automatic Speech Recognition (ASR) and was released in September 2020 by Alexei Baevski, Michael Auli, and Alex Conneau.
huggingface.co
