W

Wav2vec2 Large 100k Voxpopuli Pt

Developed by joaoalvarenga
This is an automatic speech recognition model for Portuguese, fine-tuned using the Common Voice dataset and based on the facebook/wav2vec2-large-100k-voxpopuli model.
Downloads 26
Release Time : 3/2/2022

Model Overview

This model is specifically designed for Portuguese automatic speech recognition tasks, achieving a high recognition accuracy with a word error rate (WER) of 19.74%.

Model Features

High Accuracy
Achieves a word error rate of 19.74% on the Common Voice Portuguese test set.
No Language Model Required
Can be used directly without additional language model support.
VoxPopuli Pre-trained
Fine-tuned from the facebook/wav2vec2-large-100k-voxpopuli model.

Model Capabilities

Portuguese speech recognition
Audio-to-text conversion
Speech transcription

Use Cases

Speech Transcription
Portuguese Speech-to-Text
Convert Portuguese speech content into text
Word error rate 19.74%
Voice Assistants
Portuguese Voice Assistant
For developing Portuguese voice assistants
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase