# Hugging Face — Fine-Tune XLSR-Wav2Vec2 for low-resource ASR with 🤗 Transformers

- Company: Hugging Face (huggingface.co)
- Announced: 2021-11-15
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://huggingface.co/blog/fine-tune-xlsr-wav2vec2
- Record: https://forck.live/items/2241-fine-tune-xlsr-wav2vec2-for-low-resource-asr-with-transformers
- Subject: Platform
- Models affected: Wav2Vec2, XLSR, XLS-R, Wav2Vec2-XLS-R-300M, Wav2Vec2-XLS-R-1B, Wav2Vec2-XLS-R-2B

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.

## Evidence

Verbatim from https://huggingface.co/blog/fine-tune-xlsr-wav2vec2:

> Wav2Vec2 is a pretrained model for Automatic Speech Recognition (ASR) and was released in September 2020 by Alexei Baevski, Michael Auli, and Alex Conneau.

---

Record: https://forck.live/items/2241-fine-tune-xlsr-wav2vec2-for-low-resource-asr-with-transformers
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md