Transliteration models for 21 Indic languages

OpenCC made with Python

汉字转拼音(pypinyin)

Cantonese Linguistics and NLP

A copy of https://sourceforge.net/projects/pinyin4j, then deploy it to maven central repository.

A Python library for Korean romanization

Python library to use Google Transliterate API which powers the G Input Tools

A Node.js library to convert Korean Hangul to Japanese Kana that is pronunciation friendly like: 사랑해요! -> サランヘヨ!.

Convert Korean to Katakana

🏆 A ranked gallery of awesome streamlit apps built by the community

Official repository of the ACL 2024 paper "Guardians of the Machine Translation Meta-Evaluation: Sentinel Metrics Fall In!".

Multilingual text (NLP) processing toolkit

Convert subtitles from one format to another format. Supported formats: STL EBU, TTML SMI, VTT, SRT

Read, write, convert and segment WebVTT caption files in Python.

Online tool to check for plagiarism of inputted text.

↔️ T5 Machine Translation from English to Korean

This repo includes ChatGPT prompt curation to use ChatGPT better.

LLM(😽)

State-of-the-art LLM-based translation models.

The LLM Evaluation Framework

Java library and command-line tool to transliterate Japanese kanji to romaji (Latin alphabet)

Open-source tool to visualise your RAG 🔮

Japanese to romaji converter in Python

The high performance pinyin tool for java.(java 高性能中文转拼音工具。支持同音字。)

Subtitle conversion. Converts STL, SRT, TTML and SCC into TTML, WebVTT and SRT.

Interact with your documents using the power of GPT, 100% privately, no data leaks

Data augmentation for NLP

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

A practical and feature-rich paraphrasing framework to augment human intents in text form to build robust NLU models for conversational engines. Created by Prithiviraj Damodaran. Open to pull reque…