W

Wav2vec2 Large Voxrex Npsc

Developed by NbAiLab
An automatic speech recognition model fine-tuned on the NBAILAB/NPSC - 16K_MP3 dataset based on KBLab/wav2vec2-large-voxrex
Downloads 37
Release Time : 3/2/2022

Model Overview

This model is an automatic speech recognition (ASR) model optimized for Norwegian speech recognition tasks, fine-tuned on the NPSC dataset, suitable for Norwegian speech-to-text tasks.

Model Features

Norwegian language optimization
Specially fine-tuned and optimized for Norwegian speech recognition tasks
Based on wav2vec2 architecture
Utilizes the powerful wav2vec2-large-voxrex base model
Robust speech processing
Capable of handling speech inputs under various speech qualities and environmental conditions

Model Capabilities

Norwegian speech recognition
Speech-to-text
16kHz audio processing

Use Cases

Speech transcription
Norwegian meeting minutes
Automatically transcribe Norwegian meeting recordings into text records
Achieves approximately 11% word error rate on the NPSC evaluation set
Voice assistant
Provide speech recognition capabilities for Norwegian voice assistants
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase