AIbase
EN
Home
Wav2vec2 Xls R 1b Npsc Bokmaal Low 27k
W

Wav2vec2 Xls R 1b Npsc Bokmaal Low 27k

Developed by NbAiLab
This is an automatic speech recognition model based on the wav2vec2 XLS-R architecture, specifically optimized for Norwegian Bokmål and trained on the NPSC dataset.
Speech Recognition
Transformers
Open Source License:Apache-2.0#Norwegian speech recognition#Low word error rate#Bokmål support
Downloads 22
Release Time : 3/2/2022

Model Overview

This model is primarily used for automatic speech recognition tasks in Norwegian Bokmål, with high recognition accuracy.

Model Features

High-precision Norwegian Bokmål recognition
Achieves a word error rate of 6.33% and a character error rate of 2.48% on the NPSC test set.
Based on large-scale pre-trained models
Uses the wav2vec2 XLS-R 1B parameter architecture as the foundation.
Optimized for low-resource scenarios
Specifically optimized for Norwegian Bokmål, suitable for speech recognition tasks in this language.

Model Capabilities

Norwegian Bokmål speech recognition
Audio-to-text conversion
Speech transcription

Use Cases

Speech transcription
Norwegian meeting minutes
Automatically transcribe Norwegian Bokmål meeting recordings into text
Accuracy exceeds 93%
Voice assistant
Used as the speech recognition module for Norwegian voice assistants
Education
Language learning assistance
Help learners check the accuracy of Norwegian pronunciation
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