XLS-R-300M-FR Open-Source Automatic Speech Recognition Model - Accurately Recognize French Speech Content

Xls R 300m Fr

Developed by AlexN

This is an automatic speech recognition (ASR) model fine-tuned on the Common Voice 8.0 French dataset based on facebook/wav2vec2-xls-r-300m

Downloads 21

Release Time : 3/2/2022

Model Overview

This model is specifically designed for French speech recognition tasks and performs excellently on the Common Voice 8.0 dataset

High-performance French Recognition

Achieves a WER of 21.58% on the Common Voice 8.0 French test set

Based on XLS-R Architecture

Uses facebook's wav2vec2-xls-r-300m pre-trained model as the base

Multi-scenario Adaptability

Also performs well on the Robust Speech Event dataset

French Speech Recognition

Speech-to-Text

Automatic Speech Transcription

Speech Transcription

French Speech-to-Text

Convert French speech content into text

WER of 21.58% on the standard test set

Voice Assistants

French Voice Command Recognition

Used for command recognition in French voice assistant systems

Property	Details
Model Name	xls - r - 300m - fr
Results	1. Task: Speech Recognition (automatic - speech - recognition) Dataset: Common Voice 8.0 fr (mozilla - foundation/common_voice_8_0, args: fr) Metrics: Test WER = 21.58 2. Task: Speech Recognition (automatic - speech - recognition) Dataset: Robust Speech Event - Dev Data (speech - recognition - community - v2/dev_data, args: fr) Metrics: Test WER = 36.03 3. Task: Automatic Speech Recognition (automatic - speech - recognition) Dataset: Robust Speech Event - Test Data (speech - recognition - community - v2/eval_data, args: fr) Metrics: Test WER = 38.86

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base