W

Wav2vec2 Large Xlsr 53 Dutch

Developed by wietsedv
An automatic speech recognition model fine-tuned on the Dutch Common Voice dataset based on facebook/wav2vec2-large-xlsr-53, achieving a test WER of 17.09%.
Downloads 44
Release Time : 3/2/2022

Model Overview

This is a model for Dutch automatic speech recognition (ASR), fine-tuned on the XLSR-53 architecture, supporting voice input with a 16kHz sampling rate.

Model Features

Low Word Error Rate
Achieves 17.09% WER on the Common Voice Dutch test set.
No Language Model Required
Can be used directly without additional language model support.
16kHz Sampling Rate Support
Optimized specifically for processing voice input with a 16kHz sampling rate.

Model Capabilities

Dutch Speech Recognition
Audio to Text
Automatic Speech Recognition

Use Cases

Speech Transcription
Dutch Speech Transcription
Convert Dutch speech content into text
Word Error Rate 17.09%
Voice Assistants
Dutch Voice Command Recognition
Used for front-end speech recognition in Dutch voice assistants
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase