W

Wav2vec2 Large Xls R 300m Br D10

Developed by DrishtiSharma
This is a speech recognition model fine-tuned on Breton language dataset based on facebook/wav2vec2-xls-r-300m, achieving a 52.3% Word Error Rate (WER) on the Common Voice 8 test set.
Downloads 21
Release Time : 3/2/2022

Model Overview

This model is an automatic speech recognition (ASR) model optimized for Breton language, based on the wav2vec2 architecture, suitable for converting Breton speech audio to text.

Model Features

Breton language optimization
Specifically fine-tuned for Breton language, demonstrating good performance on speech recognition tasks for this language
Based on wav2vec2-xls-r architecture
Utilizes the powerful wav2vec2-xls-r-300m as the base model, featuring excellent speech feature extraction capabilities
Relatively lightweight
With 300 million parameters, it maintains good performance while being relatively lightweight

Model Capabilities

Breton speech recognition
Audio to text conversion
Speech transcription

Use Cases

Speech transcription
Breton speech transcription
Convert Breton speech content into text
Achieved 52.3% WER on Common Voice 8 test set
Voice assistants
Breton voice command recognition
Used to support Breton-language voice assistants and smart devices
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase