W

Wav2vec2 Large Xlsr Coraa Portuguese

Developed by Edresson
This is a Wav2vec 2.0 model fine-tuned on the CORAA Portuguese dataset for Portuguese speech recognition tasks.
Downloads 130
Release Time : 3/2/2022

Model Overview

This model is a Portuguese automatic speech recognition (ASR) model based on the XLSR Wav2Vec2 Large 53 architecture, fine-tuned on the CORAA and Common Voice 7 datasets.

Model Features

Portuguese speech recognition
Speech recognition model specifically optimized for Portuguese
Trained on CORAA dataset
Fine-tuned using the CORAA Portuguese speech corpus
XLSR Wav2Vec2 architecture
Utilizes the large-scale self-supervised pre-trained XLSR Wav2Vec2 architecture

Model Capabilities

Portuguese speech-to-text
Automatic speech recognition
Processing Portuguese speech input

Use Cases

Speech transcription
Portuguese speech transcription
Convert Portuguese speech content into text
Achieves a 25.26% word error rate on the CORAA test set
Voice assistants
Portuguese voice command recognition
Used for voice command recognition in Portuguese voice assistant systems
Achieves a 20.08% word error rate on the Common Voice 7 test set
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase