{"id":20526570,"url":"https://github.com/tugstugi/mongolian-nlp","last_synced_at":"2025-07-15T10:10:22.534Z","repository":{"id":33570631,"uuid":"159414507","full_name":"tugstugi/mongolian-nlp","owner":"tugstugi","description":"Useful resources for Mongolian NLP","archived":false,"fork":false,"pushed_at":"2024-12-14T16:17:44.000Z","size":93792,"stargazers_count":184,"open_issues_count":3,"forks_count":43,"subscribers_count":33,"default_branch":"master","last_synced_at":"2025-05-24T07:03:49.668Z","etag":null,"topics":["deep-learning","language-model","mongolian","natural-language-processing","nlp","pytorch","speech-recognition","text-to-speech"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tugstugi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-11-27T23:26:03.000Z","updated_at":"2025-05-19T03:12:11.000Z","dependencies_parsed_at":"2024-12-14T17:31:09.381Z","dependency_job_id":null,"html_url":"https://github.com/tugstugi/mongolian-nlp","commit_stats":{"total_commits":136,"total_committers":4,"mean_commits":34.0,"dds":"0.044117647058823484","last_synced_commit":"465a9a5f01a810b25c45ac175be776fffbf6cd66"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/tugstugi/mongolian-nlp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tugstugi%2Fmongolian-nlp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tugstugi%2Fmongolian-nlp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tugstugi%2Fmongolian-nlp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tugstugi%2Fmongolian-nlp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tugstugi","download_url":"https://codeload.github.com/tugstugi/mongolian-nlp/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tugstugi%2Fmongolian-nlp/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265427677,"owners_count":23763372,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","language-model","mongolian","natural-language-processing","nlp","pytorch","speech-recognition","text-to-speech"],"created_at":"2024-11-15T23:14:46.339Z","updated_at":"2025-07-15T10:10:22.509Z","avatar_url":"https://github.com/tugstugi.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"This repo will contain a list of useful resources for Mongolian NLP. Feel free to contribute.\n\n\n## Datasets\n* ****`DATASET`**** ~8 hours Mongolian TTS dataset:[MnTTS](datasets/MBSpeech-1.0-csv.zip) created from the Inner Mongolia University, China\n  * [Application Entry](http://mglip.com/corpus/corpus_detail.html?corpusid=20220819185345)\n  * [Source code of TTS model](https://github.com/walker-hyf/MnTTS)\n  * [Paper](https://arxiv.org/abs/2209.10848)\n* ****`DATASET`**** LJSpeech like male voice TTS [dataset](datasets/MBSpeech-1.0-csv.zip) created from the Mongolian Bible\n  * used in [tugstugi/pytorch-dc-tts](https://github.com/tugstugi/pytorch-dc-tts)\n  * use [dl_and_preprop_dataset.py](https://github.com/tugstugi/pytorch-dc-tts/blob/master/dl_and_preprop_dataset.py) to download the audio files\n* ****`DATASET`**** LJSpeech like Kalmyk (West Mongolian) female voice TTS [dataset](https://drive.google.com/uc?id=12JbPAwNeH-qRD1Lz1JfY6Rc2jetPddbG) created from the Kalmyk Bible (2 hours)\n* ****`DATASET`**** 300 hours [Kalmyk synthetic STT dataset](https://www.dropbox.com/s/thog6q63w53ub99/kalmyk_synthetic_stt_dataset_v2.tar.gz) created by a voice conversion model\n  * each WAV has a different text created from Kalmyk books\n  * source voice is the Kalmyk Bible female TTS\n  * target voices are from the VCTK dataset\n  * an example WAV: https://twitter.com/tugstugi/status/1409111296897912835\n* ****`DATASET`**** [Eduge news classification dataset](datasets/eduge.csv.gz) provided by [Bolorsoft LLC](https://bolorsoft.com/)\n  * used to train the [Eduge.mn](http://eduge.mn/) production news classifier\n  * 75K news with 9 categories: `урлаг соёл`, `эдийн засаг`, `эрүүл мэнд`, `хууль`, `улс төр`,\n`спорт`, `технологи`, `боловсрол` and `байгал орчин`\n* ****`DATASET`**** [11-11.mn government agency complaint dataset](https://www.kaggle.com/enqush/mongolian-government-agency-1111mn-dataset/home)\n  * 80K with 5 categories: `санал хүсэлт`, `гомдол`, `шүүмжлэл`, `талархал` and `өргөдөл`\n* ****`DATASET`**** [online news corpus](https://yadi.sk/d/z5e3MVnKvFvF6w?fbclid=IwAR2wRJ4fRRMSDI8rhbNLdU2n_RiK08hU2rKwXwI7rc6JN2YNTeTna8xOOlg)\n  * 700 million words\n* ****`DATASET`**** [Digital Archive of Mongolian Newspapers 1990-1995](https://eap.bl.uk/collection/EAP010-1?f%5B0%5D=ss_simplified_type%3AFile) of the British Library\n* [Common Crawl Mongolian dataset](http://data.statmt.org/cc-100/)\n* [opendata.burtgel.gov.mn](http://opendata.burtgel.gov.mn)\n  * ****`DATASET`**** [220K Mongolian personal names](datasets/mongolian_personal_names.csv.gz)\n  * ****`DATASET`**** [90K Mongolian clan/family names](datasets/mongolian_clan_names.csv.gz)\n  * ****`DATASET`**** [192K Mongolian company names](datasets/mongolian_company_names.csv.gz)\n* ****`DATASET`**** [Mongolian provinces (aimags and sums) names](datasets/districts.csv)\n* ****`DATASET`**** [195 country (with capital cities) names in Mongolian](datasets/countries.csv)\n* ****`DATASET`**** [250 Mongolian most frequent words](datasets/most_frequent_words.csv) from Mongolian news, books and Wikipedia articles. (total 670M words / 2M unique words).\n  * These words could be used also as the stop words.\n* ****`DATASET`**** [500 Mongolian abbreviations](datasets/mongolian_abbreviations.csv)\n* ****`DATASET`**** [Mongolian NER dataset](datasets/NER_v1.0.json.gz) created from Mongolian politics and sport news\n  * 10K sentences annotated by [tugstugi](https://github.com/tugstugi) and [enod](https://github.com/enod) using [doccano](https://github.com/chakki-works/doccano)\n  * 4 categories `LOCATION` (6453/1753), `PERSON` (2839/1698), `ORGANIZATION` (4453/1970) and `MISC` (3716/2617)\n* ****`DATASET`**** [Mongolian POS dataset](http://www.panl10n.net/center-for-research-on-language-processing-crlp-national-university-of-mongolia-mongolia/) of the National University of Mongolia\n  * 100k words\n  * used [POS tagsets](https://www.aclweb.org/anthology/W09-3415)\n* ****`DATASET`**** [Traditional Mongolian synthetic OCR dataset](https://drive.google.com/file/d/1s9t22tRI22uolUv1bv023xj-x68gu1dp) created from Mongolian song lyrics and dictionary\n  * 80K images\n  * without any data augmentation, for augmenting data use external libraries like [albumentations](https://github.com/albu/albumentations).\n* ****`DATASET`**** [Traditional Mongolian OCR dataset](https://www.kaggle.com/datasets/fandaoerji/molhw-ooo)\n  * 164631 sample, 200 people\n* ****`DATASET`**** [Handwritten Mongolian Cyrillic Characters Database](https://www.kaggle.com/vimpigro/handwritten-mongolian-cyrillic-characters-database/version/1) of the Mongolian University of Science and Technology\n  * 28x28 gray scale, 350k images\n  * [dataset description](https://www.studocu.com/en/document/mongolian-university-of-science-and-technology/information-technology/other/hmcc-with-erdenechimeg/5451932/view)\n* ****`DATASET`**** [Mongolian Wordnet](https://github.com/kbatsuren/monwn) of the National University of Mongolia\n  * 26875 words, 2979 glosses, 23665 synsets, 213 examples\n* ****`DATASET`**** [Mongolian Inflectional Morphology](https://github.com/unimorph/khk) from UniMorph 4.0\n  * 2085 lemmas and 14592 inflections (+ morpheme segmentations)\n* ****`DATASET`**** [Mongolian Derivational Morphology](https://github.com/kbatsuren/MorphyNet) from MorphyNet\n  * 1410 lemmas, 1629 derivations, and 229 derivational suffixes.\n* ****`DATASET`**** [Multilingual Spoken Words](https://mlcommons.org/en/multilingual-spoken-words/) multilingual keyword spotting dataset\n  * 2200 Mongolian keywords, 44000 audio files\n  * example keywords: `аав`, `байна`, `бэлдэж`, `дүрслэх`, `ламын`, `олов`, `сонирхож`, `түүний`, `хаанаас`, `хуулиар`, `чиглэсэн`\n* ****`DATASET`**** [Small Kalmyk text corpus](https://gitlab.com/Nomin-Ger.Ru/oyrad_corpus)\n  * newspaper, poetry etc.\n\n## Mongolian Text-to-Speech\n* ****`PYTORCH`**** [tugstugi/pytorch-dc-tts](https://github.com/tugstugi/pytorch-dc-tts)\n  * ****`DEMO`**** [Colab online demo](https://colab.research.google.com/github/tugstugi/pytorch-dc-tts/blob/master/notebooks/MongolianTTS.ipynb)\n  * ****`DATASET`**** LJSpeech like male voice [dataset](datasets/MBSpeech-1.0-csv.zip) created from the Mongolian Bible\n* ****`TF`**** [tugstugi/Tacotron-2](https://github.com/tugstugi/Tacotron-2) fork of [Rayhane-mamah/Tacotron-2](https://github.com/Rayhane-mamah/Tacotron-2) adapted for\nthe Mongolian Bible dataset\n  * ****`DEMO`**** [Colab online demo](https://colab.research.google.com/github/tugstugi/mongolian-nlp/blob/master/misc/Tacotron_MongolianTTS.ipynb)\n  * ****`DEMO`**** [speaker adaptation Colab online demo](https://colab.research.google.com/github/tugstugi/mongolian-nlp/blob/master/misc/Tacotron_MongolianTTS_Elbegdorj.ipynb) for the former Mongolian president Elbegdorj. The Tacotron model trained with the 5 hours Mongolian Bible dataset was fine tuned with a 10 minutes dataset created from a Elbegdorj's speech.\n* ****`PYTORCH`**** [Chimege TTS demo](https://reader.chimege.com/)\n  * 1x female\n  * [NVIDIA/tacotron2](https://github.com/NVIDIA/tacotron2/) + [NVIDIA/waveglow](https://github.com/NVIDIA/waveglow)\n* ****`DEMO`**** HMM [TTS online demo of the National University of Mongolia](http://172.104.34.197/nlp-web-demo/)\n  * 1x male and 2x female voices\n* ****`DEMO`**** ~~Yet another HMM? [TTS online demo](http://178.128.108.243/tts/) from “Мон Спийч Ай Ти” ХХК~~\n  * demo server is currently down\n  * 1x male and 1x female\n  * [female voice samples](http://nhrcm.gov.mn/%D0%BC%D1%8D%D0%B4%D1%8D%D1%8D/%D0%BD%D2%AF%D0%B1-%D1%8B%D0%BD-%D1%85%D2%AF%D0%BD%D0%B8%D0%B9-%D1%8D%D1%80%D1%85%D0%B8%D0%B9%D0%BD-%D0%BE%D0%BB%D0%BE%D0%BD-%D1%83%D0%BB%D1%81%D1%8B%D0%BD-%D1%81%D1%83%D1%83%D1%80%D1%8C-%D0%B3%D1%8D%D1%80%D1%8D%D1%8D/)\n* ****`SAMPLES`**** Tacotron2 [TTS demo samples](https://ikon.mn/n/1j9a) of Ikon.MN\n  * 1x female (35h)\n  * [NVIDIA/tacotron2](https://github.com/NVIDIA/tacotron2/) + [NVIDIA/waveglow](https://github.com/NVIDIA/waveglow)\n* ****`DEMO`**** [HMM based TTS online demo](http://mtts.mglip.com/) of the Inner Mongolian university\n  * 1x female\n* ****`DEMO`**** MTL-Tacotron [TTS demo samples](https://ttslr.github.io/SPL2020/) of the Inner Mongolian university \u0026 National University of Singapore\n  * 1x female\n* ****`TF`**** [ttslr/MonTTS](https://github.com/ttslr/MonTTS) Inner Mongolian TTS training code\n  * ****`SAMPLES`**** [Speech samples](https://github.com/ttslr/MonTTS/tree/main/prediction/mon_inference_fastspeech2)\n  * ****`DATASET SAMPLES`**** [MonSpeech](https://github.com/ttslr/MonTTS/tree/main/MonSpeech-samples) of the Inner Mongolia University\n  * dataset and pretrained models are not available\n* ****`TF`**** [walker-hyf/MnTTS](https://github.com/walker-hyf/MnTTS) Inner Mongolian TTS dataset and training code \n  * ****`SAMPLES`**** [Speech samples](https://github.com/walker-hyf/MnTTS/tree/main/prediction/MnTTS_inference)\n  * ****`DATASET`**** [MnTTS](http://mglip.com/corpus/corpus_detail.html?corpusid=20220819185345) of the Inner Mongolia University\n  * ****`Pretrained Model`**** [download link](https://drive.google.com/file/d/1eVtGQvRd7UKAEHOCricQ5RSAgminoCd_/view)\n  * dataset and pretrained models are available :)\n* ****`PRODUCT`**** [NVDA/HTS screen reader](https://www.idc-mn.info/english.php) developed by Innovation Development Center for the blind\n  * 1x female (National University of Mongolia voice)\n* ****`PYTORCH/DEMO`**** [Kalmyk TTS demo](https://colab.research.google.com/github/tugstugi/mongolian-nlp/blob/master/misc/Kalmyk_NVidia_Tacotron2_Waveglow.ipynb) Kalmyk is a Mongolic language spoken in Russia\n  * [dataset](https://drive.google.com/uc?id=12JbPAwNeH-qRD1Lz1JfY6Rc2jetPddbG) created from the Kalmyk Bible (2 hours)\n  * [NVIDIA/tacotron2](https://github.com/NVIDIA/tacotron2/) + [NVIDIA/waveglow](https://github.com/NVIDIA/waveglow)\n* ****`PYTORCH/DEMO`**** [Kalmyk TTS demo from Silero](https://colab.research.google.com/github/tugstugi/mongolian-nlp/blob/master/misc/SileroKalmykTTS.ipynb) Kalmyk is a Mongolic language spoken in Russia\n  * [snakers4/silero-models](https://github.com/snakers4/silero-models)\n\n## Mongolian Language Model\n* ***`MODEL`*** [5-gram binary LM](https://drive.google.com/open?id=1XsNNdLDpJ75GBpw1FAUqZXyqwsb4919x) generated by KenLM on a 670M word ***dirty*** corpus.\n  * it can be used either with [mozilla/DeepSpeech](https://github.com/mozilla/DeepSpeech): `./generate_trie alphabet.txt mn_5gram.binary trie`\n  * or in [tugstugi/mongolian-speech-recognition](https://github.com/tugstugi/mongolian-speech-recognition)\n* ***`TF`*** / ***`PYTORCH`*** [tugstugi/mongolian-bert](https://github.com/tugstugi/mongolian-bert) pretrained Mongolian [BERT](https://arxiv.org/abs/1810.04805) models\n  * trained by [tugstugi](https://github.com/tugstugi), [enod](https://github.com/enod) and [sharavsambuu](https://github.com/sharavsambuu)\n  * [nabar](https://github.com/nabar) sponsored 5x TPUs.\n* ***`PYTORCH`*** [bayartsogt-ya/albert-mongolian](https://github.com/bayartsogt-ya/albert-mongolian) pretrained Mongolian [ALBERT](https://arxiv.org/abs/1909.11942)\n* ***`PYTORCH`*** [robertritz/NLP](https://github.com/robertritz/NLP) ULMFiT experiments\n* ***`PYTORCH`*** [huggingface.co/bayartsogt/mongolian-gpt2](https://huggingface.co/bayartsogt/mongolian-gpt2) Mongolian GPT-2 model\n* ***`PYTORCH`*** [huggingface.co/bayartsogt/mongolian-roberta-base](https://huggingface.co/bayartsogt/mongolian-roberta-base) Mongolian Roberta base model\n\n## Mongolian Speech Recognition\n* ****`PYTORCH`**** [tugstugi/mongolian-speech-recognition](https://github.com/tugstugi/mongolian-speech-recognition)\n  * ****`DEMO`**** [Chimege Speech Recognition](https://writer.chimege.com/)\n  * a proprietary dataset is used\n* ****`PRODUCT`**** Chinese and [traditional Mongolian voice input](https://www.aicloud.com/home/product/subpage?key=znsr) from [aicloud.com](https://www.aicloud.com)\n  * direct [link](https://hci-app.oss-cn-beijing.aliyuncs.com/aicloud_input/HciCloudInputAndroid.apk) to the APK file\n  * seems to be working only for simple cases (or it works only for Southern Mongolian dialects...)\n  * same system but for [windows](http://index.mzywfy.org.cn:48080/fanyiju/download.jsp) (according to someone, you have to register with a Chinese identity card to use it)\n* ****`DEMO`**** ~~[Speech recognition](http://asr.mglip.com) of the Inner Mongolian university~~\n  * seems to be non functional\n* ****`PRODUCT`**** [Huawei cloud ASR](https://www.huaweicloud.com/en-us/product/rasr.html) supports minority languages such as Mongolian, Tibetan, and Uyghur.\n* ****`PRODUCT`**** [Google Cloud Speech-to-text](https://cloud.google.com/speech-to-text/docs/languages)\n  * 20% WER on a 3000 audio private test dataset\n* ****`PYTORCH`**** [Wav2Vec2 XLSR](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/) finetuned on Mongolian Common Voice\n  * ****`DEMO`**** [Colab online demo](https://colab.research.google.com/github/tugstugi/mongolian-nlp/blob/master/misc/Wav2Vec2_XLSR_Mongolian.ipynb)\n  * 50% WER\n* ****`PYTORCH`**** [Wav2Vec2 XLSR](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/) trained on Kalmyk dataset\n  * pretrained on 500 hours Kalmyk TV recordings and 1000 hours Mongolian speech recognition dataset\n  * finetuned on 300 hours synthetic Kalmyk STT dataset created by voice conversion\n  * 50% WER on a private test set created from Kalmyk TV recordnings, on clean voice recordings, it should have much lower WER\n  * ****`DEMO`**** [https://huggingface.co/tugstugi/wav2vec2-large-xlsr-53-kalmyk](https://huggingface.co/tugstugi/wav2vec2-large-xlsr-53-kalmyk)\n* ****`TF`**** [coqui.ai mongolian speech recognition](https://coqui.ai/mongolian/itml/v0.1.1) trained on Mongolian CommonVoice\n  * 90.08% WER\n\n## Mongolian Script\n* ****`DEMO`**** [Cyrillic to Mongolian script converter demo](http://trans.mglip.com/EnglishC2T.aspx) of the Inner Mongolian university\n* ****`DEMO`**** [Mongolian script OCR demo](http://ocr.mglip.com/OcrDemo) of the Inner Mongolian university\n* ****`PYTORCH`**** [tugstugi/bichig2cyrillic](bichig2cyrillic/) Mongolian script to (and back) cyrillic converter\n  * ****`DEMO`**** [Cyrillic to Mongolian Colab online demo](https://colab.research.google.com/github/tugstugi/mongolian-nlp/blob/master/bichig2cyrillic/notebooks/Cyrillic2Bichig.ipynb)\n* ****`PYTORCH`**** [tugstugi/image2bichig](image2bichig/) Traditional Mongolian OCR using CRNN\n  * ****`DEMO`**** [OCR Colab online demo](https://colab.research.google.com/github/tugstugi/mongolian-nlp/blob/master/misc/MongolianScriptOCR.ipynb)\n  * ****`DATASET`**** [Traditional Mongolian synthetic OCR dataset](https://drive.google.com/file/d/1s9t22tRI22uolUv1bv023xj-x68gu1dp)\n\n## Mongolian Text Classification\n* ****`TF2`**** [sharavsambuu/mongolian-text-classification](https://github.com/sharavsambuu/mongolian-text-classification)\n* ****`SKLEARN`**** / ****`DEMO`**** simple [SVM Colab notebook](https://colab.research.google.com/github/tugstugi/mongolian-nlp/blob/master/misc/Eduge_SVM.ipynb) classifying the Eduge dataset with around 91% accuracy.\n  * SentencePiece model from [tugstugi/mongolian-bert](https://github.com/tugstugi/mongolian-bert) is used as the text tokenizer.\n\n\n## Mongolian Named Entity Recognition\n* ****`DATASET`**** [Mongolian NER dataset](datasets/NER_v1.0.json.gz) created from Mongolian politics and sport news\n  * for more info see [datasets](https://github.com/tugstugi/mongolian-nlp#datasets)\n* ****`PYTORCH`**** [enod/mongolian-bert-ner](https://github.com/enod/mongolian-bert-ner) BERT based Mongolian NER\n  * uses [tugstugi/mongolian-bert](https://github.com/tugstugi/mongolian-bert) Mongolian pre-trained BERT models\n* ****`DEMO`**** [NER demo of the National University of Mongolia](http://172.104.34.197/nlp-web-demo/)\n\n## Misc\n* ****`PYTORCH`**** [tugstugi/forced_aligner](forced_aligner/) Mongolian forced alignment tool using [Rayhane-mamah/Tacotron-2](https://github.com/Rayhane-mamah/Tacotron-2)\nand [readbeyond/aeneas](https://github.com/readbeyond/aeneas)\n  * ****`DEMO`**** [Colab online demo](https://colab.research.google.com/github/tugstugi/mongolian-nlp/blob/master/forced_aligner/Forced_Aligner.ipynb)\n* ****`TF2`**** cyrillic transliteration Colab notebook [sharavsambuu/cyrillic-mongolian-transliteration](https://colab.research.google.com/drive/10Eq_VvR84oEOBUK5EflvAB35ZcrlQwGm)\n* ****`DATASET`**** 1M back-translated MN-\u003eEN sentence dataset [download link](https://drive.google.com/file/d/14AtTVgibirSdHYTBFM9G1XPS7DvM5SdE/view)\n  * [sharavsambuu/english-mongolian-nmt-dataset-augmentation](https://github.com/sharavsambuu/english-mongolian-nmt-dataset-augmentation)\n* ****`DICTIONARY`**** [Mongolian digitalized dictionaries](http://hkuri.cneas.tohoku.ac.jp/project1/ftsdata/list?groupId=14) from Center for Northeast Asian of the Tohoku University in Japan\n  * for usage see [Digitizing the Mongolian Language: An Introduction to the Polyglot “Online Dictionaries and Full-text Search of Mongolian Languages and Written Manchu”](https://digitalorientalist.com/2020/10/02/digitizing-the-mongolian-language-an-introduction-to-the-polyglot-online-dictionaries-and-full-text-search-of-mongolian-languages-and-written-manchu/)\n  * it includes also IPA pronuncations for Mongolian words\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftugstugi%2Fmongolian-nlp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftugstugi%2Fmongolian-nlp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftugstugi%2Fmongolian-nlp/lists"}