teny
MT booster
Tools and techniques for improving machine translation in resource-constrained environments.
Tools for low-resource machine translation
3 stars
2 watching
1 forks
Language: Python
last commit: about 13 years ago
Linked from 1 awesome list
richardlitt/low-resource-languagesRelated projects:
| Repository | Description | Stars |
|---|---|---|
 gentlegiantjgc/pymctranslate | Enables data translation between Minecraft versions and platforms via an intermediate format. | 27 |
 michael-wzhu/shennong-tcm-llm | Develops and deploys a large language model for Chinese traditional medicine applications | 316 |
 tencent/tencent-hunyuan-large | This project makes a large language model accessible for research and development | 1,245 |
 translate/pootle | An online platform to manage translations and localizations for projects | 1,487 |
 aaarghhh/atop_maltego | Tools and scripts to investigate TON assets using the ATOP Maltego transform | 24 |
 pythainlp/lexicon-thai | A Thai language corpus and lexicon repository for natural language processing | 142 |
 mozilla/pontoon | A web-based platform for managing translations and localizations in software applications. | 1,477 |
 kefirski/bytenet | A Pytorch implementation of a neural network model for machine translation | 47 |
 amakukha/stemmers_ukrainian | A novel stemmer for the Ukrainian language trained with AI | 28 |
 tchayintr/thbert | A pre-trained BERT model designed to facilitate NLP research and development with limited Thai language resources | 6 |
 tbsj/qarachay_malqar_translator | Developing a neural machine translation system for the Qarachay Malqar language | 1 |
 thudm/chinese-transformer-xl | A pre-trained Chinese language model based on the Transformer-XL architecture. | 218 |
 leviswind/pytorch-transformer | Implementation of a transformer-based translation model in PyTorch | 240 |
 mrkiven/pyzh | Gathers and translates Python articles from Readthedocs into Chinese | 1,421 |
 zhuiyitechnology/t5-pegasus | Pretrained Chinese text generation model trained on large-scale data | 558 |