AIbase
EN
Home
Xlsr 300m CV 8.0 50 EP New Params Nl
X

Xlsr 300m CV 8.0 50 EP New Params Nl

Developed by Iskaj
This is an automatic speech recognition (ASR) model based on the XLS-R architecture with 300M parameters, specifically optimized for Dutch and trained on the Common Voice 8.0 dataset.
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Dutch speech recognition#Multi-scenario speech transcription#Low character error rate
Downloads 25
Release Time : 3/2/2022

Model Overview

This model is a deep learning model for Dutch speech recognition, based on Facebook's XLS-R architecture and fine-tuned on the Mozilla Common Voice 8.0 dataset.

Model Features

Dutch Optimization
Specifically optimized for Dutch speech recognition tasks
Large-scale Pretraining
Based on the 300M-parameter XLS-R architecture with powerful speech feature extraction capabilities
Multi-dataset Evaluation
Evaluated on multiple Dutch datasets including Common Voice and robust speech competitions

Model Capabilities

Dutch speech recognition
Conversational speech-to-text
Continuous speech recognition

Use Cases

Speech Transcription
Dutch Speech Transcription
Convert Dutch speech content into text
Achieved a WER of 35.44 on the Common Voice 8.0 test set
Voice Assistants
Dutch Voice Command Recognition
Used for Dutch voice assistants or smart home device voice command recognition
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase