AIbase
EN
Home
XLSR 300M Nynorsk
X

XLSR 300M Nynorsk

Developed by NbAiLab
A Nynorsk automatic speech recognition model based on the XLSR-300M architecture, trained on the NPSC dataset with low word error rate and character error rate.
Speech Recognition
Transformers
Open Source License:Apache-2.0#Nynorsk Speech Recognition#Low Character Error Rate#High Robustness
Downloads 22
Release Time : 3/2/2022

Model Overview

This model is an optimized automatic speech recognition (ASR) model for Nynorsk, based on Facebook's XLSR-300M architecture and trained on the Norwegian Parliamentary Speech Corpus (NPSC), suitable for speech-to-text tasks in Nynorsk (nn-NO).

Model Features

Low Error Rate
Achieves 12.1% word error rate (WER) and 4.2% character error rate (CER) on the Nynorsk test set
Professional Corpus Training
Trained using the Norwegian Parliamentary Speech Corpus (NPSC), suitable for formal and professional speech recognition scenarios
Robustness
The model exhibits good robustness to speech events and can handle varying quality of speech input

Model Capabilities

Nynorsk Speech Recognition
16kHz Audio Processing
MP3 Format Support

Use Cases

Government & Parliament
Parliamentary Record Transcription
Automatically transcribe speeches in Nynorsk used in the Norwegian Parliament
Highly accurate transcription of formal speech
Education
Language Learning Assistance
Help learners practice Nynorsk pronunciation and listening
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