goodatlas/zeroth
Kaldi-based Korean ASR (한국어 음성인식) open-source project
ArchivedBuilt on Kaldi's latest recipes, the system employs TDNN, LSTM, and OPGRU acoustic models with chain architecture and reverberant speech augmentation. Language models and phonetic dictionaries are automatically derived from crowdsourced audio contributions via the MoreCoin app, with the corpus spanning 121M sentences and lexicon supporting 30M+ unique words. Integrated as an official Kaldi recipe, it provides a complete Korean ASR pipeline from acoustic modeling to inference.
358 stars. No commits in the last 6 months.
Stars
358
Forks
119
Language
Shell
License
Apache-2.0
Category
Last pushed
Aug 21, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/goodatlas/zeroth"
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
nttcslab-sp/kaldiio
A pure python module for reading and writing kaldi ark files
gooofy/py-kaldi-asr
Some simple wrappers around kaldi-asr intended to make using kaldi's (online) decoders as...
pykaldi/pykaldi
A Python wrapper for Kaldi
scarletcho/KoLM
Korean text normalization and language preparation package for LM in Kaldi-based ASR system