W

Wav2vec2 Xls R 300m Br Small

Developed by emre
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the Common Voice dataset, supporting Breton (br) speech recognition tasks.
Downloads 17
Release Time : 3/2/2022

Model Overview

This is a speech recognition model optimized for Breton, fine-tuned based on the wav2vec2-xls-r-300m architecture, suitable for Automatic Speech Recognition (ASR) tasks.

Model Features

Breton Optimization
Specifically fine-tuned for Breton, improving recognition accuracy for this language.
Based on XLS-R Architecture
Uses facebook's wav2vec2-xls-r-300m as the base model, featuring powerful speech feature extraction capabilities.
Trained on Common Voice Dataset
Fine-tuned on the Common Voice dataset, ensuring data diversity and quality.

Model Capabilities

Speech-to-text
Breton speech recognition
Automatic Speech Recognition

Use Cases

Speech Transcription
Breton Speech Transcription
Convert Breton speech content into text
Achieves a 66.75% Word Error Rate (WER) on the test set.
Voice Assistants
Breton Voice Assistant
Provide voice interaction functionality for Breton speakers
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase