Wav2vec2 Large Xlrs Korean V5
W
Wav2vec2 Large Xlrs Korean V5
Developed by student-47
This model is a Korean automatic speech recognition model fine-tuned on the zeroth_korean dataset based on facebook/wav2vec2-xls-r-300m, with a word error rate of 0.2433.
Downloads 285
Release Time : 5/25/2024
Model Overview
This is an automatic speech recognition model optimized for Korean, fine-tuned based on Facebook's wav2vec2-xls-r-300m architecture, suitable for Korean speech-to-text tasks.
Model Features
Korean optimization
Specially fine-tuned for Korean speech recognition tasks, performing well on the zeroth_korean dataset.
Based on wav2vec2-xls-r architecture
Utilizes Facebook's powerful wav2vec2-xls-r-300m base model, with excellent speech feature extraction capabilities.
Low word error rate
Achieved a word error rate of 0.2433 on the evaluation set, demonstrating excellent performance.
Model Capabilities
Korean speech recognition
Speech-to-text
Automatic speech transcription
Use Cases
Speech transcription
Korean meeting minutes
Automatically convert Korean meeting recordings into text transcripts
Accuracy approximately 75.67%
Korean customer service call transcription
Automatically convert customer service call recordings into text
Voice assistant
Korean voice command recognition
Used for voice command recognition systems in Korean smart devices
Featured Recommended AI Models
Š 2025AIbase