├── .gitignore ├── 1m_split_sentences.sh ├── README.md ├── bad_translations_exps └── detect_bad_translations.py ├── criterion_sentences.sh ├── datasets ├── dl_and_preprop_mn_news.py ├── mn_en.txt └── utils.py ├── detect_bad_translations.py ├── generate_sentences.sh ├── install_translate.sh ├── lmstudio_exps ├── hello_lmstudio.py ├── prompt_translation_quality.ipynb ├── prompt_translation_quality.py ├── prompt_translation_quality_deepseek-r1-llama-70b.ipynb ├── prompt_translation_quality_deepseek8b.ipynb ├── prompt_translation_quality_llama3.3_70B_Groq.ipynb ├── prompt_translation_quallity_gemma3n.ipynb └── prompt_translation_quallity_gemma3n.py ├── prepare_translation.sh ├── requirements.txt ├── runtask.sh ├── sample_million_sentences.sh ├── sentences.py ├── split_sentences.sh └── translate_sentences.sh /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/.gitignore -------------------------------------------------------------------------------- /1m_split_sentences.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/1m_split_sentences.sh -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/README.md -------------------------------------------------------------------------------- /bad_translations_exps/detect_bad_translations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/bad_translations_exps/detect_bad_translations.py -------------------------------------------------------------------------------- /criterion_sentences.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/criterion_sentences.sh -------------------------------------------------------------------------------- /datasets/dl_and_preprop_mn_news.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/datasets/dl_and_preprop_mn_news.py -------------------------------------------------------------------------------- /datasets/mn_en.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/datasets/mn_en.txt -------------------------------------------------------------------------------- /datasets/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/datasets/utils.py -------------------------------------------------------------------------------- /detect_bad_translations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/detect_bad_translations.py -------------------------------------------------------------------------------- /generate_sentences.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/generate_sentences.sh -------------------------------------------------------------------------------- /install_translate.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/install_translate.sh -------------------------------------------------------------------------------- /lmstudio_exps/hello_lmstudio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/lmstudio_exps/hello_lmstudio.py -------------------------------------------------------------------------------- /lmstudio_exps/prompt_translation_quality.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/lmstudio_exps/prompt_translation_quality.ipynb -------------------------------------------------------------------------------- /lmstudio_exps/prompt_translation_quality.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/lmstudio_exps/prompt_translation_quality.py -------------------------------------------------------------------------------- /lmstudio_exps/prompt_translation_quality_deepseek-r1-llama-70b.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/lmstudio_exps/prompt_translation_quality_deepseek-r1-llama-70b.ipynb -------------------------------------------------------------------------------- /lmstudio_exps/prompt_translation_quality_deepseek8b.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/lmstudio_exps/prompt_translation_quality_deepseek8b.ipynb -------------------------------------------------------------------------------- /lmstudio_exps/prompt_translation_quality_llama3.3_70B_Groq.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/lmstudio_exps/prompt_translation_quality_llama3.3_70B_Groq.ipynb -------------------------------------------------------------------------------- /lmstudio_exps/prompt_translation_quallity_gemma3n.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/lmstudio_exps/prompt_translation_quallity_gemma3n.ipynb -------------------------------------------------------------------------------- /lmstudio_exps/prompt_translation_quallity_gemma3n.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/lmstudio_exps/prompt_translation_quallity_gemma3n.py -------------------------------------------------------------------------------- /prepare_translation.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/prepare_translation.sh -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/requirements.txt -------------------------------------------------------------------------------- /runtask.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/runtask.sh -------------------------------------------------------------------------------- /sample_million_sentences.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/sample_million_sentences.sh -------------------------------------------------------------------------------- /sentences.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/sentences.py -------------------------------------------------------------------------------- /split_sentences.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/split_sentences.sh -------------------------------------------------------------------------------- /translate_sentences.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation/HEAD/translate_sentences.sh --------------------------------------------------------------------------------