dobby-seo/kosr
Korean speech recognition based on transformer (트랜스포머 기반 한국어 음성 인식)
This project helps developers build custom Korean speech recognition systems. It takes raw Korean speech audio data, like the KsponSpeech dataset, and processes it to train an end-to-end speech recognition model. The output is a trained model capable of transcribing spoken Korean into text, and it's intended for engineers or researchers working on Korean language processing applications.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher looking to develop or improve a Korean speech-to-text system using a transformer-based approach.
Not ideal if you need an out-of-the-box Korean speech recognition solution without custom model training or if your project doesn't involve deep learning development.
Stars
31
Forks
2
Language
Python
License
—
Category
Last pushed
Feb 19, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/dobby-seo/kosr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
srvk/eesen
The official repository of the Eesen project