sooftware/kospeech

Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.

51
/ 100
Established

This project helps researchers and developers working with Korean speech to convert spoken audio into written text. It provides tools and established methods for processing Korean speech data and building custom speech recognition models. It's designed for those who need to experiment with and benchmark different deep learning approaches for Korean Automatic Speech Recognition (ASR).

638 stars. No commits in the last 6 months.

Use this if you are a researcher or developer aiming to train your own Korean speech recognition models or explore various model architectures for ASR.

Not ideal if you simply want to use a pre-trained Korean speech recognition model immediately without building or customizing one.

Korean ASR research speech-to-text development natural language processing deep learning for audio speech technology
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

638

Forks

192

Language

Python

License

Apache-2.0

Last pushed

May 27, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/sooftware/kospeech"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.