X

Xls R 300m Npsc 4

Developed by Rolv-Arild
This model is an automatic speech recognition model fine-tuned on the Norwegian Parliamentary Speech Corpus (NPSC) based on facebook/wav2vec2-xls-r-300m, supporting Norwegian speech-to-text tasks.
Downloads 18
Release Time : 3/2/2022

Model Overview

This is an automatic speech recognition (ASR) model for Norwegian, fine-tuned on the 16K_MP3 dataset of the Norwegian Parliamentary Speech Corpus (NPSC), capable of converting Norwegian speech into text.

Model Features

High-accuracy Norwegian recognition
Achieved a word error rate (WER) of 16.97% on the NPSC evaluation set
Based on large-scale pre-trained model
Fine-tuned from facebook's wav2vec2-xls-r-300m model, with powerful speech feature extraction capabilities
Domain-specific optimization
Trained using Norwegian parliamentary speech data, suitable for formal Norwegian speech recognition

Model Capabilities

Norwegian speech recognition
16kHz audio processing
MP3 format support

Use Cases

Government & Parliament
Parliament meeting minutes
Automatically transcribe Norwegian parliamentary meeting content
Can replace manual transcription, improving efficiency
Education
Norwegian language learning aid
Help learners check Norwegian pronunciation accuracy
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase