Xtreme_s_xlsr_minds14_fr Open-Source Automatic Speech Recognition Model - Achieve Accurate French Speech Recognition for Free

Xtreme S Xlsr Minds14 Fr

Developed by anton-l

An automatic speech recognition model fine-tuned on the GOOGLE/XTREME_S - MINDS14.FR-FR dataset based on facebook/wav2vec2-xls-r-300m

Speech Recognition

Transformers

Open Source License:Apache-2.0 #French speech recognition #High accuracy #Multi-GPU training

Downloads 41

Release Time : 3/8/2022

Model Overview

This is a model for French speech recognition, fine-tuned on the MINDS14.FR-FR dataset, with high recognition accuracy.

Model Features

High accuracy

Achieves 91.35% accuracy on the evaluation set

Multi-GPU training

Supports distributed multi-GPU training to improve training efficiency

Mixed precision training

Uses native AMP for mixed precision training to optimize training speed

Model Capabilities

French speech recognition

Speech-to-text

Use Cases

Speech transcription

French speech transcription

Convert French speech content into text

91.35% accuracy

Voice assistant

French voice command recognition

Recognize French voice commands

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.9751	10.0	50	2.0203	0.3462
0.4275	20.0	100	0.7434	0.7981
0.2484	30.0	150	0.7686	0.8462
0.0263	40.0	200	0.3922	0.9135
0.0118	50.0	250	0.4859	0.9038

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Xtreme S Xlsr Minds14 Fr

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 xtreme_s_xlsr_minds14_fr

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

🔧 Technical Details

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License