Text Normalization & Inverse Text Normalization

Implementation of MathReader, Text-to-Speech for Mathematical Documents

Automatic Korean word spacing with Python

The dataset of Korean conversational speech

End-to-End Speech Processing Toolkit

Awesome list of Korean Large Language Models.

Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.

A T5-based Text-to-Text model for Korean Numeral Normalization

Upload a local file and use AssemblyAI's Speaker Labels model to display turn-by-turn utterances for your file.

omo; the best agent harness - previously oh-my-opencode

Open-Source Frontier Voice AI

KSS: Korean String processing Suite

Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.

Pretrained Language Models for Korean

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

📖 Korean NLU Benchmark

Inverse Text Normalization by using bert2BERT.

A Korean postpositions processing package for *new-age*.

Korean text normalization and language preparation package for LM in Kaldi-based ASR system

The implementation for "Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions"

KenLM: Faster and Smaller Language Model Queries

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

A pytorch_lightning reimplementation of the Transducer module from ESPnet.