metadata

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