{ "test": { "name": "test", "latest_version": "0.1", "description": "It's a test file", "long_description": "A handy dummy corpus used for testing (like in unit testing) purpose", "url": "https://github.com/PyThaiNLP/pythainlp-corpus/", "project_urls": { "project_page": "https://www.thainlp.org/", "source": "https://github.com/PyThaiNLP/pythainlp-corpus/" }, "license": "CC0-1.0", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "versions": { "0.0.0": { "filename": "test.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/test-0.1/test.txt", "md5": "ff1f76282b7adcb310ffad3ecd867c3d", "pythainlp_version": "==1.0", "is_zip": "False", "is_tar_gz": "False" }, "0.0.1": { "filename": "test.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/test-0.1/test.txt", "md5": "ff1f76282b7adcb310ffad3ecd867c3d", "pythainlp_version": "<2.0", "is_zip": "False", "is_tar_gz": "False" }, "0.0.2": { "filename": "test.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/test-0.1/test.txt", "md5": "ff1f76282b7adcb310ffad3ecd867c3d", "pythainlp_version": "<=2.0", "is_zip": "False", "is_tar_gz": "False" }, "0.0.3": { "filename": "test.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/test-0.1/test.txt", "md5": "ff1f76282b7adcb310ffad3ecd867c3d", "pythainlp_version": ">=2.1<2.2", "is_zip": "False", "is_tar_gz": "False" }, "0.0.4": { "filename": "test.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/test-0.1/test.txt", "md5": "ff1f76282b7adcb310ffad3ecd867c3d", "pythainlp_version": "<2.0", "is_zip": "False", "is_tar_gz": "False" }, "0.0.5": { "filename": "test.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/test-0.1/test.txt", "md5": "ff1f76282b7adcb310ffad3ecd867c3d", "pythainlp_version": ">2.2<2.3", "is_zip": "False", "is_tar_gz": "False" }, "0.0.6": { "filename": "test.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/test-0.1/test.txt", "md5": "ff1f76282b7adcb310ffad3ecd867c3d", "pythainlp_version": ">=2.2<2.3", "is_zip": "False", "is_tar_gz": "False" }, "0.0.7": { "filename": "test.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/test-0.1/test.txt", "md5": "ff1f76282b7adcb310ffad3ecd867c3d", "pythainlp_version": ">2.2", "is_zip": "False", "is_tar_gz": "False" }, "0.0.8": { "filename": "test.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/test-0.1/test.txt", "md5": "ff1f76282b7adcb310ffad3ecd867c3d", "pythainlp_version": ">=2.2<=2.3", "is_zip": "False", "is_tar_gz": "False" }, "0.0.9": { "filename": "test.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/test-0.1/test.txt", "md5": "ff1f76282b7adcb310ffad3ecd867c3d", "pythainlp_version": ">=2.*", "is_zip": "False", "is_tar_gz": "False" }, "0.0.10": { "filename": "test.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/test-0.1/test.txt", "md5": "ff1f76282b7adcb310ffad3ecd867c3d", "pythainlp_version": ">=1.10", "is_zip": "False", "is_tar_gz": "False" }, "0.0.11": { "filename": "test.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/test-0.1/test.txt", "md5": "ff1f76282b7adcb310ffad3ecd867c36", "pythainlp_version": ">=1.10", "is_zip": "False", "is_tar_gz": "False" }, "0.1": { "filename": "test.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/test-0.1/test.txt", "md5": "ff1f76282b7adcb310ffad3ecd867c3d", "pythainlp_version": "*", "is_zip": "False", "is_tar_gz": "False" } } }, "g2p": { "name": "g2p", "latest_version": "0.1", "description": "Thai grapheme to phoneme", "long_description": "Data from Thai Wiktionary", "url": "https://github.com/PyThaiNLP/lexicon-thai/tree/master/G2P", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "license": "CC-BY-4.0", "versions": { "0.1": { "filename": "wiktionary-11-2-2020.tsv", "download_url": "https://raw.githubusercontent.com/PyThaiNLP/lexicon-thai/master/G2P/wiktionary-11-2-2020.tsv", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "thai-g2p": { "name": "thai-g2p", "latest_version": "0.1", "description": "Thai grapheme to phoneme (PyTorch)", "long_description": "Thai grapheme to phoneme in PyTorch", "url": "https://github.com/wannaphong/thai-g2p/", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "license": "CC-BY-4.0", "versions": { "0.1": { "filename": "thaig2p-0.1.tar", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/thaig2p-v0.1/thaig2p-0.1.tar", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "thai2fit_wv": { "name": "thai2fit_wv", "latest_version": "0.1", "description": "thai2vec word embeddings", "long_description": "-", "url": "https://github.com/cstorm125/thai2fit/", "authors": [ "Charin Polpanumas" ], "author_email": "", "license": "CC-BY-4.0", "versions": { "0.1": { "filename": "thai2vec.bin", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/thai2fit_wv-v0.1/thai2vec.bin", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "thai2rom-dataset": { "name": "thai2rom-dataset", "latest_version": "0.1", "description": "Thai romanization model", "long_description": "-", "url": "https://github.com/wannaphong/thai-romanization/", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "license": "CC0-1.0", "versions": { "0.1": { "filename": "thai2rom.csv", "download_url": "https://raw.githubusercontent.com/wannaphong/thai-romanization/master/dataset/data.csv", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "thai2rom-pytorch": { "name": "thai2rom-pytorch", "latest_version": "0.1", "description": "Thai romanization model (LSTM)", "long_description": "Thai romanization using LSTM encoder-decoder model", "url": "https://github.com/c4n/thai-romanization/", "authors": [ "Can Udomcharoenchaikit" ], "author_email": "", "license": "Apache-2.0", "versions": { "0.1": { "filename": "thai2rom-pytorch.tar", "download_url": "https://raw.githubusercontent.com/c4n/thai-romanization/master/notebook/thai2rom-pytorch.tar", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "thai2rom-pytorch-attn": { "name": "thai2rom-pytorch-attn", "latest_version": "0.1", "description": "Thai romanization model (LSTM-Attention)", "long_description": "Thai romanization using LSTM encoder-decoder model with attention mechanism", "url": "https://github.com/artificiala/thai-romanization/", "authors": [ "Chakri Lowphansirikul" ], "author_email": "", "license": "Apache-2.0", "versions": { "0.1": { "filename": "thai2rom-pytorch-attn-v0.1.tar", "download_url": "https://raw.githubusercontent.com/lalital/thai-romanization/master/notebook/thai2rom-pytorch-attn-v0.1.tar", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "thainer": { "name": "thainer", "latest_version": "1.5", "description": "Thai Named Entity Recognition", "long_description": "Thai Named Entity Recognition", "url": "https://github.com/wannaphong/thai-ner/", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "license": "CC-BY-4.0", "versions": { "1.3": { "filename": "thai-ner-1-3.crfsuite", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/thainer-1.3/data.model", "md5": "-", "pythainlp_version": "<=2.2", "is_zip": "False", "is_tar_gz": "False" }, "1.4": { "filename": "thai-ner-1-4.crfsuite", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/thainer-1.4/thai-ner-1-4.crfsuite", "md5": "-", "pythainlp_version": ">=2.2<=2.2.6", "is_zip": "False", "is_tar_gz": "False" }, "1.5": { "filename": "thai-ner-1-5.crfsuite", "download_url": "https://github.com/wannaphong/thai-ner/releases/download/1.5/thai-ner-1-5-newmm-lst20.crfsuite", "md5": "-", "pythainlp_version": ">=2.2.7", "is_zip": "False", "is_tar_gz": "False" } } }, "thainer-1.4": { "name": "thainer-1.4", "latest_version": "1.4", "description": "Thai Named Entity Recognition 1.4 for PyThaiNLP 2.3", "long_description": "Thai Named Entity Recognition", "url": "https://github.com/wannaphong/thai-ner/", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "license": "CC-BY-4.0", "versions": { "1.4": { "filename": "thai-ner-1-4.crfsuite", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/thainer-1.4/thai-ner-1-4.crfsuite", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "wiki_itos_lstm": { "name": "wiki_itos_lstm", "latest_version": "0.32", "description": "ULMFit index to text for LSTM", "long_description": "ULMFit index to text for LSTM", "url": "https://github.com/cstorm125/thai2fit/", "authors": [ "Charin Polpanumas" ], "author_email": "", "license": "CC-BY-4.0", "versions": { "0.32": { "filename": "itos_lstm.pkl", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/wiki_itos_lstm-v0.32/thwiki_itos.pkl", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "wiki_itos_lstm_json": { "name": "wiki_itos_lstm_json", "latest_version": "0.32", "description": "ULMFit index to text for LSTM", "long_description": "ULMFit index to text for LSTM", "url": "https://github.com/cstorm125/thai2fit/", "authors": [ "Charin Polpanumas" ], "author_email": "", "license": "CC-BY-4.0", "versions": { "0.32": { "filename": "itos_lstm.json", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/wiki_itos_lstm-v0.32/thwiki_itos.json", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "wiki_lm_lstm": { "name": "wiki_lm_lstm", "latest_version": "0.32", "description": "Wikipedia-pretrained ULMFit language model for LSTM", "long_description": "Wikipedia-pretrained ULMFit language model for LSTM", "url": "https://github.com/cstorm125/thai2fit/", "authors": [ "Charin Polpanumas" ], "author_email": "", "license": "CC-BY-4.0", "versions": { "0.32": { "filename": "thwiki_model_lstm.pth", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/wiki_lm_lstm-v0.32/thwiki_model_lstm.pth", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "scb_1m_th-en_newmm": { "name": "scb_1m_th-en_newmm", "latest_version": "1.0", "description": "SCB_1M+TBASE_th-en_newmm-moses", "long_description": "-", "url": "https://airesearch.in.th/releases/machine-translation-models/", "project_urls": { "project_page": "https://airesearch.in.th/", "source": "https://github.com/vistec-AI/model-releases/releases/tag/SCB_1M%2BTBASE_v1.0" }, "license": "NOASSERTION", "authors": [ "VISTEC-depa Thailand Artificial Intelligence Research Institute" ], "author_email": "-", "versions": { "1.0": { "filename": "SCB_1M-MT_OPUS+TBASE_th-en_newmm-moses_130000-130000_v1.0.tar.gz", "download_url": "https://github.com/vistec-AI/model-releases/releases/download/SCB_1M%2BTBASE_v1.0/SCB_1M-MT_OPUS+TBASE_th-en_newmm-moses_130000-130000_v1.0.tar.gz", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "True" } } }, "scb_1m_th-en_spm": { "name": "scb_1m_th-en_spm", "latest_version": "1.0", "description": "SCB_1M+TBASE_th-en_spm-spm", "long_description": "-", "url": "https://airesearch.in.th/releases/machine-translation-models/", "project_urls": { "project_page": "https://airesearch.in.th/", "source": "https://github.com/vistec-AI/model-releases/releases/tag/SCB_1M%2BTBASE_v1.0" }, "license": "NOASSERTION", "authors": [ "VISTEC-depa Thailand Artificial Intelligence Research Institute" ], "author_email": "-", "versions": { "1.0": { "filename": "SCB_1M-MT_OPUS+TBASE_th-en_spm-spm_32000-joined_v1.0.tar.gz", "download_url": "https://github.com/vistec-AI/model-releases/releases/download/SCB_1M%2BTBASE_v1.0/SCB_1M-MT_OPUS+TBASE_th-en_spm-spm_32000-joined_v1.0.tar.gz", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "True" } } }, "scb_1m_en-th_moses": { "name": "scb_1m_en-th_moses", "latest_version": "1.0", "description": "SCB_1M+TBASE_en-th_moses-spm", "long_description": "-", "url": "https://airesearch.in.th/releases/machine-translation-models/", "project_urls": { "project_page": "https://airesearch.in.th/", "source": "https://github.com/vistec-AI/model-releases/releases/tag/SCB_1M%2BTBASE_v1.0" }, "license": "NOASSERTION", "authors": [ "VISTEC-depa Thailand Artificial Intelligence Research Institute" ], "author_email": "-", "versions": { "1.0": { "filename": "SCB_1M-MT_OPUS+TBASE_en-th_moses-spm_130000-16000_v1.0.tar.gz", "download_url": "https://github.com/vistec-AI/model-releases/releases/download/SCB_1M%2BTBASE_v1.0/SCB_1M-MT_OPUS+TBASE_en-th_moses-spm_130000-16000_v1.0.tar.gz", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "True" } } }, "scb_1m_en-th_spm": { "name": "scb_1m_en-th_spm", "latest_version": "1.0", "description": "scb_1m_en-th_spm", "long_description": "-", "url": "https://airesearch.in.th/releases/machine-translation-models/", "project_urls": { "project_page": "https://airesearch.in.th/", "source": "https://github.com/vistec-AI/model-releases/releases/tag/SCB_1M%2BTBASE_v1.0" }, "license": "NOASSERTION", "authors": [ "VISTEC-depa Thailand Artificial Intelligence Research Institute" ], "author_email": "-", "versions": { "1.0": { "filename": "SCB_1M-MT_OPUS+TBASE_en-th_spm-spm_32000-joined_v1.0.tar.gz", "download_url": "https://github.com/vistec-AI/model-releases/releases/download/SCB_1M%2BTBASE_v1.0/SCB_1M-MT_OPUS+TBASE_en-th_spm-spm_32000-joined_v1.0.tar.gz", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "True" } } }, "scb_en_th": { "name": "scb_en_th", "latest_version": "1.0", "description": "scb_en-th", "long_description": "-", "url": "https://airesearch.in.th/releases/machine-translation-models/", "project_urls": { "project_page": "https://airesearch.in.th/", "source": "https://github.com/vistec-AI/model-releases/releases/tag/SCB_1M%2BTBASE_v1.0" }, "license": "NOASSERTION", "authors": [ "VISTEC-depa Thailand Artificial Intelligence Research Institute" ], "author_email": "-", "versions": { "1.0": { "filename": "SCB_1M-MT_OPUS+TBASE_en-th_moses-newmm_space_130000-130000_v1.0.tar.gz", "download_url": "https://github.com/vistec-AI/model-releases/releases/download/SCB_1M%2BTBASE_v1.0/SCB_1M-MT_OPUS+TBASE_en-th_moses-newmm_space_130000-130000_v1.0.tar.gz", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "True" } } }, "scb_th_en": { "name": "scb_th_en", "latest_version": "1.0", "description": "scb_1m_th-en_spm", "long_description": "-", "url": "https://airesearch.in.th/releases/machine-translation-models/", "project_urls": { "project_page": "https://airesearch.in.th/", "source": "https://github.com/vistec-AI/model-releases/releases/tag/SCB_1M%2BTBASE_v1.0" }, "license": "NOASSERTION", "authors": [ "VISTEC-depa Thailand Artificial Intelligence Research Institute" ], "author_email": "-", "versions": { "1.0": { "filename": "SCB_1M-MT_OPUS+TBASE_th-en_spm-moses_16000-130000_v1.0.tar.gz", "download_url": "https://github.com/vistec-AI/model-releases/releases/download/SCB_1M%2BTBASE_v1.0/SCB_1M-MT_OPUS+TBASE_th-en_spm-moses_16000-130000_v1.0.tar.gz", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "True" } } }, "pos_lst20_perceptron": { "name": "pos_lst20_perceptron", "latest_version": "0.2.3", "description": "Perceptron POS tagger (LST20)", "long_description": "Perceptron part-of-speech tagger from LST20 dataset. LST20 corpus are free for research and open source only. If you want to use in Commercial use, please contract NECTEC.", "url": "https://github.com/PyThaiNLP/", "project_urls": { "project_page": "https://github.com/PyThaiNLP/", "source": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/tag/lst20-v0.2.2" }, "license": "CC0-1.0", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "versions": { "0.2.2": { "filename": "pos_lst20_perceptron.pkl", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/lst20-v0.2.2/pos_lst20_perceptron-v0.2.2.pkl", "md5": "-", "pythainlp_version": ">=2.2<2.2.6", "is_zip": "False", "is_tar_gz": "False" }, "0.2.3": { "filename": "pos_lst20_perceptron.pkl", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/lst20-v0.2.3/pos_lst20_perceptron-v0.2.3.pkl", "md5": "-", "pythainlp_version": ">=2.2.6", "is_zip": "False", "is_tar_gz": "False" }, "0.2.4": { "filename": "pos_lst20_perceptron-v0.2.4.json", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/pos_lst20-v0.2.4/pos_lst20_perceptron-v0.2.4.json", "md5": "-", "pythainlp_version": ">3.0.9", "is_zip": "False", "is_tar_gz": "False" } } }, "pos_lst20_unigram": { "name": "pos_lst20_unigram", "latest_version": "0.2.3", "description": "Unigram POS tagger (LST20)", "long_description": "Unigram part-of-speech tagger from LST20 dataset. LST20 corpus are free for research and open source only. If you want to use in Commercial use, please contract NECTEC.", "url": "https://github.com/PyThaiNLP/", "project_urls": { "project_page": "https://github.com/PyThaiNLP/", "source": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/tag/lst20-v0.2.2" }, "license": "CC0-1.0", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "versions": { "0.2.2": { "filename": "pos_lst20_unigram.json", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/lst20-v0.2.2/pos_lst20_unigram-v0.2.2.json", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" }, "0.2.3": { "filename": "pos_lst20_unigram.json", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/lst20-v0.2.3/pos_lst20_unigram-v0.2.3.json", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "lst20-cls": { "name": "lst20-cls", "latest_version": "0.2", "description": "lst20-cls (LST20)", "long_description": "CLS from LST20 dataset. LST20 corpus are free for research and open source only. If you want to use in Commercial use, please contract NECTEC.", "url": "https://github.com/PyThaiNLP/", "project_urls": { "project_page": "https://github.com/PyThaiNLP/", "source": "https://github.com/PyThaiNLP/pythainlp-corpus/tree/lst20-cls-v0.1" }, "license": "CC0-1.0", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "versions": { "0.1": { "filename": "cls.crfsuite", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/lst20-cls-v0.1/cls.crfsuite", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" }, "0.2": { "filename": "cls-v0.2.crfsuite", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/lst20-cls-v0.2/cls-v0.2.crfsuite", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "thai_w2p": { "name": "thai_w2p", "latest_version": "0.2", "description": "Thai Word-to-Phoneme (W2P) converter", "long_description": "Thai Word-to-Phoneme (W2P) converter", "url": "https://github.com/wannaphong/Thai_W2P", "project_urls": { "project_page": "https://github.com/wannaphong/Thai_W2P", "source": "https://github.com/wannaphong/Thai_W2P" }, "license": "CC0-1.0", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "versions": { "0.1": { "filename": "w2p_0.1.npy", "download_url": "https://github.com/wannaphong/Thai_W2P/releases/download/v0.1/w2p_0.1.npy", "md5": "-", "pythainlp_version": ">=2.2.6", "is_zip": "False", "is_tar_gz": "False" }, "0.2": { "filename": "thai_w2p_v0.2.npy", "download_url": "https://github.com/wannaphong/Thai_W2P/releases/download/v0.2/thai_w2p_v0.2.npy", "md5": "-", "pythainlp_version": ">=3.0.6", "is_zip": "False", "is_tar_gz": "False" } } }, "thai_w2p_npz": { "name": "thai_w2p_npz", "latest_version": "0.2", "description": "Thai Word-to-Phoneme (W2P) converter", "long_description": "Thai Word-to-Phoneme (W2P) converter", "url": "https://github.com/wannaphong/Thai_W2P", "project_urls": { "project_page": "https://github.com/wannaphong/Thai_W2P", "source": "https://github.com/wannaphong/Thai_W2P" }, "license": "CC0-1.0", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "versions": { "0.2": { "filename": "thai_w2p_v0.2.npz", "download_url": "https://github.com/wannaphong/Thai_W2P/releases/download/v0.2/thai_w2p_v0.2.npz", "md5": "-", "pythainlp_version": ">=5.3.0", "is_zip": "False", "is_tar_gz": "False" } } }, "tnc_bigram_word_freqs": { "name": "tnc_bigram_word_freqs", "latest_version": "2017", "description": "Bigram word frequency from Thai National Corpus (TNC)", "long_description": "Bigram word frequency from Thai National Corpus (TNC)", "url": "http://www.arts.chula.ac.th/ling", "project_urls": { "project_page": "http://www.arts.chula.ac.th/ling", "source": "http://www.arts.chula.ac.th/ling" }, "license": "CC0-1.0", "authors": [ "chula" ], "author_email": "?", "versions": { "2017": { "filename": "201705_2gram.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/tnc-v2017/201705_2gram.txt", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "tnc_trigram_word_freqs": { "name": "tnc_trigram_word_freqs", "latest_version": "2017", "description": "Trigram word frequency from Thai National Corpus (TNC)", "long_description": "Trigram word frequency from Thai National Corpus (TNC)", "url": "http://www.arts.chula.ac.th/ling", "project_urls": { "project_page": "http://www.arts.chula.ac.th/ling", "source": "http://www.arts.chula.ac.th/ling" }, "license": "CC0-1.0", "authors": [ "chula" ], "author_email": "?", "versions": { "2017": { "filename": "201705_3gram.txt", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/tnc-v2017/201705_3gram.txt", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "oscar_icu": { "name": "oscar_icu", "latest_version": "1.0", "description": "Thai unigram word frequency from OSCAR Corpus (icu word tokenize)", "long_description": "Thai unigram word frequency from OSCAR Corpus (icu word tokenize)", "url": "https://web.facebook.com/groups/colab.thailand/permalink/1524070061101680/?_rdc=1&_rdr", "project_urls": { "project_page": "https://web.facebook.com/groups/colab.thailand/permalink/1524070061101680/?_rdc=1&_rdr", "source": "https://colab.research.google.com/github/vistec-AI/colab/blob/master/OSCAR.ipynb" }, "license": "CC0-1.0", "authors": [ "Korakot Chaovavanich" ], "author_email": "?", "versions": { "1.0": { "filename": "oscar_word_freq.csv", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/oscar_icu-v1.0/oscar_word_freq.csv", "md5": "-", "pythainlp_version": ">=2.2", "is_zip": "False", "is_tar_gz": "False" } } }, "ltw2v": { "name": "ltw2v", "latest_version": "0.1", "description": "LTW2V: The Large Thai Word2Vec", "long_description": "LTW2V is The large Thai Word2Vec. It built with oxidized-thainlp from OSCAR Corpus (Open Super-large Crawled Aggregated coRpus).", "url": "https://github.com/PyThaiNLP/large-thaiword2vec", "project_urls": { "project_page": "https://github.com/PyThaiNLP/large-thaiword2vec", "source": "https://github.com/PyThaiNLP/large-thaiword2vec" }, "license": "Apache-2.0", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "versions": { "0.1": { "filename": "LTW2V_v0.1.bin", "download_url": "https://github.com/PyThaiNLP/large-thaiword2vec/releases/download/v0.1/LTW2V_v0.1.bin", "md5": "-", "pythainlp_version": ">=2.3", "is_zip": "False", "is_tar_gz": "False" } } }, "ltw2v_v1.0_5_window": { "name": "ltw2v_v1.0_5_window", "latest_version": "1.0", "description": "LTW2V: The Large Thai Word2Vec v1.0 (5 window)", "long_description": "LTW2V is The large Thai Word2Vec. It trained OSCAR Corpus (Open Super-large Crawled Aggregated coRpus).", "url": "https://github.com/PyThaiNLP/large-thaiword2vec", "project_urls": { "project_page": "https://github.com/PyThaiNLP/large-thaiword2vec", "source": "https://github.com/PyThaiNLP/large-thaiword2vec" }, "license": "Apache-2.0", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "versions": { "1.0": { "filename": "LTW2V_v1.0-window5.bin", "download_url": "https://zenodo.org/record/7280277/files/LTW2V_v1.0-window5.bin", "md5": "-", "pythainlp_version": ">=3.0", "is_zip": "False", "is_tar_gz": "False" } } }, "ltw2v_v1.0_15_window": { "name": "ltw2v_v1.0_15_window", "latest_version": "1.0", "description": "LTW2V: The Large Thai Word2Vec v1.0 (15 window)", "long_description": "LTW2V is The large Thai Word2Vec. It trained OSCAR Corpus (Open Super-large Crawled Aggregated coRpus).", "url": "https://github.com/PyThaiNLP/large-thaiword2vec", "project_urls": { "project_page": "https://github.com/PyThaiNLP/large-thaiword2vec", "source": "https://github.com/PyThaiNLP/large-thaiword2vec" }, "license": "Apache-2.0", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "versions": { "1.0": { "filename": "LTW2V_v1.0-window5.bin", "download_url": "https://zenodo.org/record/7280277/files/LTW2V_v1.0-window15.bin", "md5": "-", "pythainlp_version": ">=3.0", "is_zip": "False", "is_tar_gz": "False" } } }, "test_zip": { "name": "test_zip", "latest_version": "0.1", "description": "It's a test file", "long_description": "A handy dummy corpus used for testing (like in unit testing) purpose", "url": "https://github.com/PyThaiNLP/pythainlp-corpus/", "project_urls": { "project_page": "https://www.thainlp.org/", "source": "https://github.com/PyThaiNLP/pythainlp-corpus/" }, "license": "CC0-1.0", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "wannaphong@yahoo.com", "versions": { "0.1": { "filename": "test.zip", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/test_zip-v0.1/test.zip", "md5": "-", "pythainlp_version": ">=3.0", "is_zip": "True", "is_tar_gz": "False" } } }, "onnx_lst20ner": { "name": "onnx_lst20ner", "latest_version": "1.0", "description": "LST20 NER model", "long_description": "This is LST20 NER model from WangchanBERTa. It is ONNX model.", "url": "https://huggingface.co/airesearch/wangchanberta-base-att-spm-uncased", "project_urls": { "project_page": "https://huggingface.co/airesearch/wangchanberta-base-att-spm-uncased", "source": "https://github.com/vistec-AI/thai2transformers" }, "license": "Apache-2.0", "authors": [ "airesearch" ], "author_email": "", "versions": { "1.0": { "filename": "lst20ner-onnx-v1.0.zip", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/onnx_lst20ner-v1.0/lst20ner-onnx-v1.0.zip", "md5": "-", "pythainlp_version": ">=3.0", "is_zip": "True", "is_tar_gz": "False" } } }, "thai_nner": { "name": "thai_nner", "latest_version": "1.0", "description": "Thai Nested Named Entity Recognition", "long_description": "Thai Nested Named Entity Recognition", "url": "https://github.com/vistec-AI/Thai-NNER", "project_urls": { "project_page": "https://github.com/vistec-AI/Thai-NNER", "source": "https://github.com/vistec-AI/Thai-NNER" }, "license": "CC-BY-SA-3.0", "authors": [ "Weerayut Buaphet" ], "author_email": "-", "versions": { "1.0": { "filename": "thai_nner_model.pth", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/thai_nner_v1.0/model.pth", "md5": "-", "pythainlp_version": "*", "is_zip": "False", "is_tar_gz": "False" } } }, "blackboard_unigram_tagger": { "name": "blackboard_unigram_tagger", "latest_version": "1.0", "description": "Part-of-speech tagging (unigram) from Blackboard treebank", "long_description": "Part-of-speech tagging (unigram) from Blackboard treebank", "url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/tag/blackboard_unigram_tagger-v1.0", "project_urls": { "project_page": "https://github.com/PyThaiNLP/pythainlp-corpus/", "source": "https://github.com/PyThaiNLP/pythainlp-corpus/" }, "license": "CC0-1.0", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "-", "versions": { "1.0": { "filename": "blackboard_unigram_tagger-v1.0.json", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/blackboard_unigram_tagger-v1.0/blackboard_unigram_tagger-v1.0.json", "md5": "-", "pythainlp_version": "*", "is_zip": "False", "is_tar_gz": "False" } } }, "blackboard_pt_tagger": { "name": "blackboard_pt_tagger", "latest_version": "1.0", "description": "Part-of-speech tagging (perceptron) from Blackboard treebank", "long_description": "Part-of-speech tagging (perceptron) from Blackboard treebank", "url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/tag/blackboard_pt_tagger-v1.0", "project_urls": { "project_page": "https://github.com/PyThaiNLP/pythainlp-corpus/", "source": "https://github.com/PyThaiNLP/pythainlp-corpus/" }, "license": "CC0-1.0", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "-", "versions": { "1.0": { "filename": "blackboard_pt_tagger-v1.0_pythainlp.json", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/blackboard_pt_tagger-v1.0/blackboard_pt_tagger-v1.0_pythainlp.json", "md5": "-", "pythainlp_version": "*", "is_zip": "False", "is_tar_gz": "False" } } }, "thai_dict": { "name": "thai_dict", "latest_version": "1.0", "description": "Thai dictionary from Thai wiktionary", "long_description": "Thai dictionary from Thai wiktionary", "url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/tag/thai_dict-v1.0", "project_urls": { "project_page": "https://github.com/PyThaiNLP/pythainlp-corpus/", "source": "https://github.com/PyThaiNLP/pythainlp-corpus/" }, "license": "CC-BY-SA-4.0", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "-", "versions": { "1.0": { "filename": "thai_dictionary_v1.0.csv", "download_url": "https://github.com/PyThaiNLP/pythainlp-corpus/releases/download/thai_dict-v1.0/thai_dictionary.csv", "md5": "-", "pythainlp_version": "*", "is_zip": "False", "is_tar_gz": "False" } } }, "thai_synonym": { "name": "thai_synonym", "latest_version": "1.0", "description": "The synonym for Thai (open source & open data)", "long_description": "The synonym for Thai (open source & open data)", "url": "https://github.com/PyThaiNLP/thai-synonym", "project_urls": { "project_page": "https://github.com/PyThaiNLP/thai-synonym", "source": "https://github.com/PyThaiNLP/thai-synonym" }, "license": "CC0-1.0", "authors": [ "Wannaphong Phatthiyaphaibun" ], "author_email": "-", "versions": { "1.0": { "filename": "thai_synonym_v1.0.csv", "download_url": "https://github.com/PyThaiNLP/thai-synonym/raw/master/data.csv", "md5": "-", "pythainlp_version": "*", "is_zip": "False", "is_tar_gz": "False" } } } }