The open-source Korean speech recognition model wav2vec2-large-xlrs-korean-v5 offers precise recognition with a low error rate.

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.

Speech Recognition

Transformers

Open Source License:Apache-2.0 #Korean speech recognition #High-precision WER #wav2vec2 fine-tuning

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

Training Loss	Epoch	Step	Validation Loss	Wer
5.1453	1.4368	500	3.1530	1.0
2.4287	2.8736	1000	0.6084	0.8317
0.5556	4.3103	1500	0.3414	0.6165
0.3929	5.7471	2000	0.2729	0.5386
0.3211	7.1839	2500	0.2294	0.4794
0.281	8.6207	3000	0.2052	0.4298
0.2483	10.0575	3500	0.1911	0.4061
0.2243	11.4943	4000	0.1685	0.3873
0.2023	12.9310	4500	0.1627	0.3524
0.188	14.3678	5000	0.1572	0.3272
0.1784	15.8046	5500	0.1495	0.3131
0.1677	17.2414	6000	0.1424	0.2881
0.1533	18.6782	6500	0.1418	0.2709
0.1501	20.1149	7000	0.1387	0.2822
0.1402	21.5517	7500	0.1401	0.2697
0.1353	22.9885	8000	0.1367	0.2643
0.133	24.4253	8500	0.1337	0.2578
0.1254	25.8621	9000	0.1355	0.2560
0.1262	27.2989	9500	0.1339	0.2474
0.121	28.7356	10000	0.1300	0.2433

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Wav2vec2 Large Xlrs Korean V5

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 wav2vec2-large-xlrs-korean-v5

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

🔧 Technical Details

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License