W

Wav2vec2 Xls R 1b Portuguese CORAA 3

Developed by lgris
Portuguese automatic speech recognition model fine-tuned on the CORAA dataset based on facebook/wav2vec2-xls-r-1b
Downloads 31
Release Time : 3/2/2022

Model Overview

This model is an optimized automatic speech recognition (ASR) model for Portuguese, fine-tuned on the CORAA dataset, capable of converting Portuguese speech into text.

Model Features

Large-scale pre-trained model fine-tuning
Fine-tuned on the 1-billion-parameter wav2vec2-xls-r-1b model, with powerful speech recognition capabilities
Portuguese optimization
Specifically optimized for Portuguese, achieving good performance on the CORAA dataset
Multi-dataset validation
Validated on multiple datasets including Common Voice and Robust Speech Events

Model Capabilities

Portuguese speech recognition
Speech-to-text
Automatic speech recognition

Use Cases

Speech transcription
Portuguese speech transcription
Convert Portuguese speech content into text
WER of 0.6020 on the CORAA evaluation set
Voice assistants
Portuguese voice command recognition
Used for command recognition in Portuguese voice assistant systems
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase