AIbase
EN
Model Selection
Tags
Robust Speech Challenge

# Robust Speech Challenge

Wav2vec2 Xls R 300m Zh HK Lm V2
Apache-2.0
An automatic speech recognition model based on XLS-R architecture, optimized for Cantonese (zh-HK), fine-tuned on the Common Voice dataset and enhanced with a 5-gram language model.
Speech Recognition Transformers
W
w11wo
25
0
Wav2vec2 Xls R 300m Korean
Apache-2.0
Korean automatic speech recognition model based on XLS-R architecture, fine-tuned on the Zeroth Korean dataset
Speech Recognition Transformers Korean
W
w11wo
152
6
Wav2vec2 Xls R 300m Zh HK V2
Apache-2.0
Cantonese automatic speech recognition model based on XLS-R architecture, fine-tuned on Common Voice Cantonese dataset
Speech Recognition Transformers
W
w11wo
23
0
Wav2vec2 Xls R 300m Korean Lm
Apache-2.0
Korean automatic speech recognition model based on XLS-R architecture, fine-tuned on the Zeroth Korean dataset with an added 5-gram language model
Speech Recognition Transformers Korean
W
w11wo
23
1
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase