wav2vec2-large-xlsr-53-chinese-zh-cn

Downloads
Hugging Face
1.9M
121
License
license:apache-2.0
Updated
11/4/2025
by
jonatasgrosman

Wav2Vec2 model for automatic speech recognition in Chinese (Mandarin), trained on Common Voice dataset.

Audio Model
OTHER

Quick Info

Released
3/2/2022
Framework
OTHER

Resources