scarletcho/KoLM
Korean text normalization and language preparation package for LM in Kaldi-based ASR system
This package helps prepare Korean text data for building speech recognition systems. It takes raw Korean text files, cleans them by normalizing, removing unwanted characters, and breaking them into sentences. The output is a refined text corpus and a pronunciation dictionary ready for use in Kaldi-based Automatic Speech Recognition (ASR) language model development. This tool is designed for speech scientists, linguists, or ASR engineers working with Korean language models.
No commits in the last 6 months. Available on PyPI.
Use this if you need to meticulously clean, normalize, and preprocess large Korean text corpora to create a robust language model and pronunciation dictionary for an ASR system.
Not ideal if your primary goal is general natural language processing tasks that do not require detailed grapheme-to-phone conversion or specific language model file formats for ASR.
Stars
63
Forks
21
Language
Python
License
GPL-3.0
Category
Last pushed
Apr 23, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/scarletcho/KoLM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
daanzu/kaldi-active-grammar
Python Kaldi speech recognition with grammars that can be set active/inactive dynamically at decode-time
gooofy/py-kaldi-asr
Some simple wrappers around kaldi-asr intended to make using kaldi's (online) decoders as...
nttcslab-sp/kaldiio
A pure python module for reading and writing kaldi ark files
pykaldi/pykaldi
A Python wrapper for Kaldi
kaldi-asr/kaldi
kaldi-asr/kaldi is the official location of the Kaldi project.