language, datasets, metrics, tags, license, model-index

language	datasets	metrics	tags	license	model-index
pt	CORAA common_voice mls cetuc voxforge	wer	audio speech wav2vec2 pt portuguese-speech-corpus automatic-speech-recognition speech PyTorch	apache-2.0	name results Alef Iury XLSR Wav2Vec2 Large 53 Portuguese task metrics name type Speech Recognition automatic-speech-recognition name type value Test CORAA WER wer 24.89%

Wav2vec 2.0 trained with CORAA Portuguese Dataset and Open Portuguese Datasets

This a the demonstration of a fine-tuned Wav2vec model for Portuguese using the following datasets:

• CORAA dataset
• CETUC.
• Multilingual Librispeech (MLS).
• VoxForge.
• Common Voice 6.1.

Repository

The repository that implements the model to be trained and tested is avaible here.