W

Wav2vec2 Large Xlsr Swedish

Developed by marma
This is a Swedish automatic speech recognition model based on the XLSR-53 architecture, fine-tuned on the Common Voice dataset.
Downloads 24
Release Time : 3/2/2022

Model Overview

This model is used for Swedish automatic speech recognition tasks, fine-tuned based on Facebook's XLSR Wav2Vec2 architecture.

Model Features

XLSR Fine-tuning
Fine-tuned based on the XLSR-53 architecture, optimizing Swedish speech recognition performance
Multilingual Pre-training
Utilizes cross-lingual speech representation learning (XLSR) for pre-training

Model Capabilities

Swedish speech recognition
Audio to text conversion

Use Cases

Speech Transcription
Swedish Speech to Text
Convert Swedish speech content into text
Word error rate 23.33%
Voice Assistants
Swedish Voice Command Recognition
Used for command recognition in Swedish voice assistant systems
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase