XLS-NPSC-OH Open-source Automatic Speech Recognition Model - Accurately Recognize Speech Content, Free to Use

Xls Npsc Oh

Developed by NbAiLab

This model is an automatic speech recognition model fine-tuned on the NBAILAB/NPSC - 48K_MP3 dataset based on KBLab/wav2vec2-large-voxrex

Downloads 30

Release Time : 3/2/2022

Model Overview

This is an automatic speech recognition model for Norwegian, fine-tuned on the NPSC dataset, capable of converting Norwegian speech to text

Norwegian speech recognition

Speech recognition capability specifically optimized for Norwegian

Based on wav2vec2 architecture

Fine-tuned using the advanced wav2vec2-large-voxrex architecture

High performance

Achieved a word error rate of 0.8586 on the evaluation set

Norwegian speech-to-text

High-precision speech recognition

Speech transcription

Norwegian meeting minutes

Automatically transcribe Norwegian meeting recordings into text records

Word error rate 0.8586

Voice assistant

Provide speech recognition capability for Norwegian voice assistants

Training Loss	Epoch	Step	Validation Loss	Wer
2.1093	2.61	1000	0.2572	0.9293

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base