Spaces:
Sleeping
Sleeping
| { | |
| "af_afribooms": { | |
| "id": "af_afribooms", | |
| "name": "Afrikaans AfriBooms", | |
| "display_name": "Afrikaans — AfriBooms", | |
| "language": "Afrikaans", | |
| "language_code": "af", | |
| "treebank": "AfriBooms", | |
| "ud_short_id": "af_afribooms", | |
| "ud_version": "2.12", | |
| "folder": "afrikaans_afribooms_af", | |
| "model_file": "afrikaans_afribooms_af_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 93 | |
| }, | |
| "grc_perseus": { | |
| "id": "grc_perseus", | |
| "name": "Ancient Greek Perseus", | |
| "display_name": "Ancient Greek — Perseus", | |
| "language": "Ancient Greek", | |
| "language_code": "grc", | |
| "treebank": "Perseus", | |
| "ud_short_id": "grc_perseus", | |
| "ud_version": "2.12", | |
| "folder": "ancient_greek_perseus_grc", | |
| "model_file": "ancient_greek_perseus_grc_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 208 | |
| }, | |
| "grc_proiel": { | |
| "id": "grc_proiel", | |
| "name": "Ancient Greek PROIEL", | |
| "display_name": "Ancient Greek — PROIEL", | |
| "language": "Ancient Greek", | |
| "language_code": "grc", | |
| "treebank": "PROIEL", | |
| "ud_short_id": "grc_proiel", | |
| "ud_version": "2.12", | |
| "folder": "ancient_greek_proiel_grc", | |
| "model_file": "ancient_greek_proiel_grc_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 189 | |
| }, | |
| "hbo_ptnk": { | |
| "id": "hbo_ptnk", | |
| "name": "Ancient Hebrew PTNK", | |
| "display_name": "Ancient Hebrew — PTNK", | |
| "language": "Ancient Hebrew", | |
| "language_code": "hbo", | |
| "treebank": "PTNK", | |
| "ud_short_id": "hbo_ptnk", | |
| "ud_version": "2.12", | |
| "folder": "ancient_hebrew_ptnk_hbo", | |
| "model_file": "ancient_hebrew_ptnk_hbo_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 72 | |
| }, | |
| "ar_padt": { | |
| "id": "ar_padt", | |
| "name": "Arabic PADT", | |
| "display_name": "Arabic — PADT", | |
| "language": "Arabic", | |
| "language_code": "ar", | |
| "treebank": "PADT", | |
| "ud_short_id": "ar_padt", | |
| "ud_version": "2.12", | |
| "folder": "arabic_padt_ar", | |
| "model_file": "arabic_padt_ar_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 111 | |
| }, | |
| "hy_armtdp": { | |
| "id": "hy_armtdp", | |
| "name": "Armenian ArmTDP", | |
| "display_name": "Armenian — ArmTDP", | |
| "language": "Armenian", | |
| "language_code": "hy", | |
| "treebank": "ArmTDP", | |
| "ud_short_id": "hy_armtdp", | |
| "ud_version": "2.12", | |
| "folder": "armenian_armtdp_hy", | |
| "model_file": "armenian_armtdp_hy_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 172 | |
| }, | |
| "hy_bsut": { | |
| "id": "hy_bsut", | |
| "name": "Armenian BSUT", | |
| "display_name": "Armenian — BSUT", | |
| "language": "Armenian", | |
| "language_code": "hy", | |
| "treebank": "BSUT", | |
| "ud_short_id": "hy_bsut", | |
| "ud_version": "2.12", | |
| "folder": "armenian_bsut_hy", | |
| "model_file": "armenian_bsut_hy_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 165 | |
| }, | |
| "eu_bdt": { | |
| "id": "eu_bdt", | |
| "name": "Basque BDT", | |
| "display_name": "Basque — BDT", | |
| "language": "Basque", | |
| "language_code": "eu", | |
| "treebank": "BDT", | |
| "ud_short_id": "eu_bdt", | |
| "ud_version": "2.12", | |
| "folder": "basque_bdt_eu", | |
| "model_file": "basque_bdt_eu_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 96 | |
| }, | |
| "be_hse": { | |
| "id": "be_hse", | |
| "name": "Belarusian HSE", | |
| "display_name": "Belarusian — HSE", | |
| "language": "Belarusian", | |
| "language_code": "be", | |
| "treebank": "HSE", | |
| "ud_short_id": "be_hse", | |
| "ud_version": "2.12", | |
| "folder": "belarusian_hse_be", | |
| "model_file": "belarusian_hse_be_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 598 | |
| }, | |
| "bg_btb": { | |
| "id": "bg_btb", | |
| "name": "Bulgarian BTB", | |
| "display_name": "Bulgarian — BTB", | |
| "language": "Bulgarian", | |
| "language_code": "bg", | |
| "treebank": "BTB", | |
| "ud_short_id": "bg_btb", | |
| "ud_version": "2.12", | |
| "folder": "bulgarian_btb_bg", | |
| "model_file": "bulgarian_btb_bg_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 139 | |
| }, | |
| "ca_ancora": { | |
| "id": "ca_ancora", | |
| "name": "Catalan AnCora", | |
| "display_name": "Catalan — AnCora", | |
| "language": "Catalan", | |
| "language_code": "ca", | |
| "treebank": "AnCora", | |
| "ud_short_id": "ca_ancora", | |
| "ud_version": "2.12", | |
| "folder": "catalan_ancora_ca", | |
| "model_file": "catalan_ancora_ca_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 118 | |
| }, | |
| "zh_gsd": { | |
| "id": "zh_gsd", | |
| "name": "Chinese GSD", | |
| "display_name": "Chinese — GSD", | |
| "language": "Chinese", | |
| "language_code": "zh", | |
| "treebank": "GSD", | |
| "ud_short_id": "zh_gsd", | |
| "ud_version": "2.12", | |
| "folder": "chinese_traditional_gsd_zh", | |
| "model_file": "chinese_traditional_gsd_zh_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 3582 | |
| }, | |
| "zh_gsdsimp": { | |
| "id": "zh_gsdsimp", | |
| "name": "Chinese GSDSimp", | |
| "display_name": "Chinese — GSDSimp", | |
| "language": "Chinese", | |
| "language_code": "zh", | |
| "treebank": "GSDSimp", | |
| "ud_short_id": "zh_gsdsimp", | |
| "ud_version": "2.12", | |
| "folder": "chinese_simplified_gsdsimp_zh", | |
| "model_file": "chinese_simplified_gsdsimp_zh_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 3456 | |
| }, | |
| "lzh_kyoto": { | |
| "id": "lzh_kyoto", | |
| "name": "Classical Chinese Kyoto", | |
| "display_name": "Classical Chinese — Kyoto", | |
| "language": "Classical Chinese", | |
| "language_code": "lzh", | |
| "treebank": "Kyoto", | |
| "ud_short_id": "lzh_kyoto", | |
| "ud_version": "2.12", | |
| "folder": "classical_chinese_kyoto_lzh", | |
| "model_file": "classical_chinese_kyoto_lzh_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 5711 | |
| }, | |
| "cop_scriptorium": { | |
| "id": "cop_scriptorium", | |
| "name": "Coptic Scriptorium", | |
| "display_name": "Coptic — Scriptorium", | |
| "language": "Coptic", | |
| "language_code": "cop", | |
| "treebank": "Scriptorium", | |
| "ud_short_id": "cop_scriptorium", | |
| "ud_version": "2.12", | |
| "folder": "coptic_scriptorium_cop", | |
| "model_file": "coptic_scriptorium_cop_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 58 | |
| }, | |
| "hr_set": { | |
| "id": "hr_set", | |
| "name": "Croatian SET", | |
| "display_name": "Croatian — SET", | |
| "language": "Croatian", | |
| "language_code": "hr", | |
| "treebank": "SET", | |
| "ud_short_id": "hr_set", | |
| "ud_version": "2.12", | |
| "folder": "croatian_set_hr", | |
| "model_file": "croatian_set_hr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 115 | |
| }, | |
| "cs_cac": { | |
| "id": "cs_cac", | |
| "name": "Czech CAC", | |
| "display_name": "Czech — CAC", | |
| "language": "Czech", | |
| "language_code": "cs", | |
| "treebank": "CAC", | |
| "ud_short_id": "cs_cac", | |
| "ud_version": "2.12", | |
| "folder": "czech_cac_cs", | |
| "model_file": "czech_cac_cs_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 103 | |
| }, | |
| "cs_cltt": { | |
| "id": "cs_cltt", | |
| "name": "Czech CLTT", | |
| "display_name": "Czech — CLTT", | |
| "language": "Czech", | |
| "language_code": "cs", | |
| "treebank": "CLTT", | |
| "ud_short_id": "cs_cltt", | |
| "ud_version": "2.12", | |
| "folder": "czech_cltt_cs", | |
| "model_file": "czech_cltt_cs_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 110 | |
| }, | |
| "cs_fictree": { | |
| "id": "cs_fictree", | |
| "name": "Czech FicTree", | |
| "display_name": "Czech — FicTree", | |
| "language": "Czech", | |
| "language_code": "cs", | |
| "treebank": "FicTree", | |
| "ud_short_id": "cs_fictree", | |
| "ud_version": "2.12", | |
| "folder": "czech_fictree_cs", | |
| "model_file": "czech_fictree_cs_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 109 | |
| }, | |
| "cs_pdt": { | |
| "id": "cs_pdt", | |
| "name": "Czech PDT", | |
| "display_name": "Czech — PDT", | |
| "language": "Czech", | |
| "language_code": "cs", | |
| "treebank": "PDT", | |
| "ud_short_id": "cs_pdt", | |
| "ud_version": "2.12", | |
| "folder": "czech_pdt_cs", | |
| "model_file": "czech_pdt_cs_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 146 | |
| }, | |
| "da_ddt": { | |
| "id": "da_ddt", | |
| "name": "Danish DDT", | |
| "display_name": "Danish — DDT", | |
| "language": "Danish", | |
| "language_code": "da", | |
| "treebank": "DDT", | |
| "ud_short_id": "da_ddt", | |
| "ud_version": "2.12", | |
| "folder": "danish_ddt_da", | |
| "model_file": "danish_ddt_da_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 104 | |
| }, | |
| "nl_alpino": { | |
| "id": "nl_alpino", | |
| "name": "Dutch Alpino", | |
| "display_name": "Dutch — Alpino", | |
| "language": "Dutch", | |
| "language_code": "nl", | |
| "treebank": "Alpino", | |
| "ud_short_id": "nl_alpino", | |
| "ud_version": "2.12", | |
| "folder": "dutch_alpino_nl", | |
| "model_file": "dutch_alpino_nl_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 104 | |
| }, | |
| "nl_lassysmall": { | |
| "id": "nl_lassysmall", | |
| "name": "Dutch LassySmall", | |
| "display_name": "Dutch — LassySmall", | |
| "language": "Dutch", | |
| "language_code": "nl", | |
| "treebank": "LassySmall", | |
| "ud_short_id": "nl_lassysmall", | |
| "ud_version": "2.12", | |
| "folder": "dutch_lassysmall_nl", | |
| "model_file": "dutch_lassysmall_nl_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 114 | |
| }, | |
| "en_atis": { | |
| "id": "en_atis", | |
| "name": "English Atis", | |
| "display_name": "English — Atis", | |
| "language": "English", | |
| "language_code": "en", | |
| "treebank": "Atis", | |
| "ud_short_id": "en_atis", | |
| "ud_version": "2.12", | |
| "folder": "english_atis_en", | |
| "model_file": "english_atis_en_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 70 | |
| }, | |
| "en_ewt": { | |
| "id": "en_ewt", | |
| "name": "English EWT", | |
| "display_name": "English — EWT", | |
| "language": "English", | |
| "language_code": "en", | |
| "treebank": "EWT", | |
| "ud_short_id": "en_ewt", | |
| "ud_version": "2.12", | |
| "folder": "english_ewt_en", | |
| "model_file": "english_ewt_en_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 114 | |
| }, | |
| "en_gum": { | |
| "id": "en_gum", | |
| "name": "English GUM", | |
| "display_name": "English — GUM", | |
| "language": "English", | |
| "language_code": "en", | |
| "treebank": "GUM", | |
| "ud_short_id": "en_gum", | |
| "ud_version": "2.12", | |
| "folder": "english_gum_en", | |
| "model_file": "english_gum_en_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 205 | |
| }, | |
| "en_lines": { | |
| "id": "en_lines", | |
| "name": "English LinES", | |
| "display_name": "English — LinES", | |
| "language": "English", | |
| "language_code": "en", | |
| "treebank": "LinES", | |
| "ud_short_id": "en_lines", | |
| "ud_version": "2.12", | |
| "folder": "english_lines_en", | |
| "model_file": "english_lines_en_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 89 | |
| }, | |
| "en_partut": { | |
| "id": "en_partut", | |
| "name": "English ParTUT", | |
| "display_name": "English — ParTUT", | |
| "language": "English", | |
| "language_code": "en", | |
| "treebank": "ParTUT", | |
| "ud_short_id": "en_partut", | |
| "ud_version": "2.12", | |
| "folder": "english_partut_en", | |
| "model_file": "english_partut_en_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 106 | |
| }, | |
| "et_edt": { | |
| "id": "et_edt", | |
| "name": "Estonian EDT", | |
| "display_name": "Estonian — EDT", | |
| "language": "Estonian", | |
| "language_code": "et", | |
| "treebank": "EDT", | |
| "ud_short_id": "et_edt", | |
| "ud_version": "2.12", | |
| "folder": "estonian_edt_et", | |
| "model_file": "estonian_edt_et_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 132 | |
| }, | |
| "et_ewt": { | |
| "id": "et_ewt", | |
| "name": "Estonian EWT", | |
| "display_name": "Estonian — EWT", | |
| "language": "Estonian", | |
| "language_code": "et", | |
| "treebank": "EWT", | |
| "ud_short_id": "et_ewt", | |
| "ud_version": "2.12", | |
| "folder": "estonian_ewt_et", | |
| "model_file": "estonian_ewt_et_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 134 | |
| }, | |
| "fi_ftb": { | |
| "id": "fi_ftb", | |
| "name": "Finnish FTB", | |
| "display_name": "Finnish — FTB", | |
| "language": "Finnish", | |
| "language_code": "fi", | |
| "treebank": "FTB", | |
| "ud_short_id": "fi_ftb", | |
| "ud_version": "2.12", | |
| "folder": "finnish_ftb_fi", | |
| "model_file": "finnish_ftb_fi_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 101 | |
| }, | |
| "fi_tdt": { | |
| "id": "fi_tdt", | |
| "name": "Finnish TDT", | |
| "display_name": "Finnish — TDT", | |
| "language": "Finnish", | |
| "language_code": "fi", | |
| "treebank": "TDT", | |
| "ud_short_id": "fi_tdt", | |
| "ud_version": "2.12", | |
| "folder": "finnish_tdt_fi", | |
| "model_file": "finnish_tdt_fi_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 249 | |
| }, | |
| "fr_gsd": { | |
| "id": "fr_gsd", | |
| "name": "French GSD", | |
| "display_name": "French — GSD", | |
| "language": "French", | |
| "language_code": "fr", | |
| "treebank": "GSD", | |
| "ud_short_id": "fr_gsd", | |
| "ud_version": "2.12", | |
| "folder": "french_gsd_fr", | |
| "model_file": "french_gsd_fr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 314 | |
| }, | |
| "fr_parisstories": { | |
| "id": "fr_parisstories", | |
| "name": "French ParisStories", | |
| "display_name": "French — ParisStories", | |
| "language": "French", | |
| "language_code": "fr", | |
| "treebank": "ParisStories", | |
| "ud_short_id": "fr_parisstories", | |
| "ud_version": "2.12", | |
| "folder": "french_parisstories_fr", | |
| "model_file": "french_parisstories_fr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 85 | |
| }, | |
| "fr_partut": { | |
| "id": "fr_partut", | |
| "name": "French ParTUT", | |
| "display_name": "French — ParTUT", | |
| "language": "French", | |
| "language_code": "fr", | |
| "treebank": "ParTUT", | |
| "ud_short_id": "fr_partut", | |
| "ud_version": "2.12", | |
| "folder": "french_partut_fr", | |
| "model_file": "french_partut_fr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 101 | |
| }, | |
| "fr_rhapsodie": { | |
| "id": "fr_rhapsodie", | |
| "name": "French Rhapsodie", | |
| "display_name": "French — Rhapsodie", | |
| "language": "French", | |
| "language_code": "fr", | |
| "treebank": "Rhapsodie", | |
| "ud_short_id": "fr_rhapsodie", | |
| "ud_version": "2.12", | |
| "folder": "french_rhapsodie_fr", | |
| "model_file": "french_rhapsodie_fr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 84 | |
| }, | |
| "fr_sequoia": { | |
| "id": "fr_sequoia", | |
| "name": "French Sequoia", | |
| "display_name": "French — Sequoia", | |
| "language": "French", | |
| "language_code": "fr", | |
| "treebank": "Sequoia", | |
| "ud_short_id": "fr_sequoia", | |
| "ud_version": "2.12", | |
| "folder": "french_sequoia_fr", | |
| "model_file": "french_sequoia_fr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 114 | |
| }, | |
| "gl_ctg": { | |
| "id": "gl_ctg", | |
| "name": "Galician CTG", | |
| "display_name": "Galician — CTG", | |
| "language": "Galician", | |
| "language_code": "gl", | |
| "treebank": "CTG", | |
| "ud_short_id": "gl_ctg", | |
| "ud_version": "2.12", | |
| "folder": "galician_ctg_gl", | |
| "model_file": "galician_ctg_gl_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 117 | |
| }, | |
| "de_gsd": { | |
| "id": "de_gsd", | |
| "name": "German GSD", | |
| "display_name": "German — GSD", | |
| "language": "German", | |
| "language_code": "de", | |
| "treebank": "GSD", | |
| "ud_short_id": "de_gsd", | |
| "ud_version": "2.12", | |
| "folder": "german_gsd_de", | |
| "model_file": "german_gsd_de_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 253 | |
| }, | |
| "de_hdt": { | |
| "id": "de_hdt", | |
| "name": "German HDT", | |
| "display_name": "German — HDT", | |
| "language": "German", | |
| "language_code": "de", | |
| "treebank": "HDT", | |
| "ud_short_id": "de_hdt", | |
| "ud_version": "2.12", | |
| "folder": "german_hdt_de", | |
| "model_file": "german_hdt_de_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 128 | |
| }, | |
| "got_proiel": { | |
| "id": "got_proiel", | |
| "name": "Gothic PROIEL", | |
| "display_name": "Gothic — PROIEL", | |
| "language": "Gothic", | |
| "language_code": "got", | |
| "treebank": "PROIEL", | |
| "ud_short_id": "got_proiel", | |
| "ud_version": "2.12", | |
| "folder": "gothic_proiel_got", | |
| "model_file": "gothic_proiel_got_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 70 | |
| }, | |
| "el_gdt": { | |
| "id": "el_gdt", | |
| "name": "Greek GDT", | |
| "display_name": "Greek — GDT", | |
| "language": "Greek", | |
| "language_code": "el", | |
| "treebank": "GDT", | |
| "ud_short_id": "el_gdt", | |
| "ud_version": "2.12", | |
| "folder": "greek_gdt_el", | |
| "model_file": "greek_gdt_el_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 151 | |
| }, | |
| "he_htb": { | |
| "id": "he_htb", | |
| "name": "Hebrew HTB", | |
| "display_name": "Hebrew — HTB", | |
| "language": "Hebrew", | |
| "language_code": "he", | |
| "treebank": "HTB", | |
| "ud_short_id": "he_htb", | |
| "ud_version": "2.12", | |
| "folder": "hebrew_htb_he", | |
| "model_file": "hebrew_htb_he_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 58 | |
| }, | |
| "he_iahltwiki": { | |
| "id": "he_iahltwiki", | |
| "name": "Hebrew IAHLTwiki", | |
| "display_name": "Hebrew — IAHLTwiki", | |
| "language": "Hebrew", | |
| "language_code": "he", | |
| "treebank": "IAHLTwiki", | |
| "ud_short_id": "he_iahltwiki", | |
| "ud_version": "2.12", | |
| "folder": "hebrew_iahltwiki_he", | |
| "model_file": "hebrew_iahltwiki_he_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 160 | |
| }, | |
| "hi_hdtb": { | |
| "id": "hi_hdtb", | |
| "name": "Hindi HDTB", | |
| "display_name": "Hindi — HDTB", | |
| "language": "Hindi", | |
| "language_code": "hi", | |
| "treebank": "HDTB", | |
| "ud_short_id": "hi_hdtb", | |
| "ud_version": "2.12", | |
| "folder": "hindi_hdtb_hi", | |
| "model_file": "hindi_hdtb_hi_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 105 | |
| }, | |
| "hu_szeged": { | |
| "id": "hu_szeged", | |
| "name": "Hungarian Szeged", | |
| "display_name": "Hungarian — Szeged", | |
| "language": "Hungarian", | |
| "language_code": "hu", | |
| "treebank": "Szeged", | |
| "ud_short_id": "hu_szeged", | |
| "ud_version": "2.12", | |
| "folder": "hungarian_szeged_hu", | |
| "model_file": "hungarian_szeged_hu_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 97 | |
| }, | |
| "is_gc": { | |
| "id": "is_gc", | |
| "name": "Icelandic GC", | |
| "display_name": "Icelandic — GC", | |
| "language": "Icelandic", | |
| "language_code": "is", | |
| "treebank": "GC", | |
| "ud_short_id": "is_gc", | |
| "ud_version": "2.12", | |
| "folder": "icelandic_gc_is", | |
| "model_file": "icelandic_gc_is_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 127 | |
| }, | |
| "is_icepahc": { | |
| "id": "is_icepahc", | |
| "name": "Icelandic IcePaHC", | |
| "display_name": "Icelandic — IcePaHC", | |
| "language": "Icelandic", | |
| "language_code": "is", | |
| "treebank": "IcePaHC", | |
| "ud_short_id": "is_icepahc", | |
| "ud_version": "2.12", | |
| "folder": "icelandic_icepahc_is", | |
| "model_file": "icelandic_icepahc_is_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 106 | |
| }, | |
| "is_modern": { | |
| "id": "is_modern", | |
| "name": "Icelandic Modern", | |
| "display_name": "Icelandic — Modern", | |
| "language": "Icelandic", | |
| "language_code": "is", | |
| "treebank": "Modern", | |
| "ud_short_id": "is_modern", | |
| "ud_version": "2.12", | |
| "folder": "icelandic_modern_is", | |
| "model_file": "icelandic_modern_is_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 104 | |
| }, | |
| "id_gsd": { | |
| "id": "id_gsd", | |
| "name": "Indonesian GSD", | |
| "display_name": "Indonesian — GSD", | |
| "language": "Indonesian", | |
| "language_code": "id", | |
| "treebank": "GSD", | |
| "ud_short_id": "id_gsd", | |
| "ud_version": "2.12", | |
| "folder": "indonesian_gsd_id", | |
| "model_file": "indonesian_gsd_id_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 290 | |
| }, | |
| "ga_idt": { | |
| "id": "ga_idt", | |
| "name": "Irish IDT", | |
| "display_name": "Irish — IDT", | |
| "language": "Irish", | |
| "language_code": "ga", | |
| "treebank": "IDT", | |
| "ud_short_id": "ga_idt", | |
| "ud_version": "2.12", | |
| "folder": "irish_idt_ga", | |
| "model_file": "irish_idt_ga_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 106 | |
| }, | |
| "ga_twittirish": { | |
| "id": "ga_twittirish", | |
| "name": "Irish TwittIrish", | |
| "display_name": "Irish — TwittIrish", | |
| "language": "Irish", | |
| "language_code": "ga", | |
| "treebank": "TwittIrish", | |
| "ud_short_id": "ga_twittirish", | |
| "ud_version": "2.12", | |
| "folder": "irish_twittirish_ga", | |
| "model_file": "irish_twittirish_ga_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 168 | |
| }, | |
| "it_isdt": { | |
| "id": "it_isdt", | |
| "name": "Italian ISDT", | |
| "display_name": "Italian — ISDT", | |
| "language": "Italian", | |
| "language_code": "it", | |
| "treebank": "ISDT", | |
| "ud_short_id": "it_isdt", | |
| "ud_version": "2.12", | |
| "folder": "italian_isdt_it", | |
| "model_file": "italian_isdt_it_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 132 | |
| }, | |
| "it_markit": { | |
| "id": "it_markit", | |
| "name": "Italian MarkIT", | |
| "display_name": "Italian — MarkIT", | |
| "language": "Italian", | |
| "language_code": "it", | |
| "treebank": "MarkIT", | |
| "ud_short_id": "it_markit", | |
| "ud_version": "2.12", | |
| "folder": "italian_markit_it", | |
| "model_file": "italian_markit_it_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 95 | |
| }, | |
| "it_partut": { | |
| "id": "it_partut", | |
| "name": "Italian ParTUT", | |
| "display_name": "Italian — ParTUT", | |
| "language": "Italian", | |
| "language_code": "it", | |
| "treebank": "ParTUT", | |
| "ud_short_id": "it_partut", | |
| "ud_version": "2.12", | |
| "folder": "italian_partut_it", | |
| "model_file": "italian_partut_it_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 103 | |
| }, | |
| "it_postwita": { | |
| "id": "it_postwita", | |
| "name": "Italian PoSTWITA", | |
| "display_name": "Italian — PoSTWITA", | |
| "language": "Italian", | |
| "language_code": "it", | |
| "treebank": "PoSTWITA", | |
| "ud_short_id": "it_postwita", | |
| "ud_version": "2.12", | |
| "folder": "italian_postwita_it", | |
| "model_file": "italian_postwita_it_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 195 | |
| }, | |
| "it_twittiro": { | |
| "id": "it_twittiro", | |
| "name": "Italian TWITTIRO", | |
| "display_name": "Italian — TWITTIRO", | |
| "language": "Italian", | |
| "language_code": "it", | |
| "treebank": "TWITTIRO", | |
| "ud_short_id": "it_twittiro", | |
| "ud_version": "2.12", | |
| "folder": "italian_twittiro_it", | |
| "model_file": "italian_twittiro_it_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 117 | |
| }, | |
| "it_vit": { | |
| "id": "it_vit", | |
| "name": "Italian VIT", | |
| "display_name": "Italian — VIT", | |
| "language": "Italian", | |
| "language_code": "it", | |
| "treebank": "VIT", | |
| "ud_short_id": "it_vit", | |
| "ud_version": "2.12", | |
| "folder": "italian_vit_it", | |
| "model_file": "italian_vit_it_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 97 | |
| }, | |
| "ja_gsd": { | |
| "id": "ja_gsd", | |
| "name": "Japanese GSD", | |
| "display_name": "Japanese — GSD", | |
| "language": "Japanese", | |
| "language_code": "ja", | |
| "treebank": "GSD", | |
| "ud_short_id": "ja_gsd", | |
| "ud_version": "2.12", | |
| "folder": "japanese_gsd_ja", | |
| "model_file": "japanese_gsd_ja_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 3016 | |
| }, | |
| "ja_gsdluw": { | |
| "id": "ja_gsdluw", | |
| "name": "Japanese GSDLUW", | |
| "display_name": "Japanese — GSDLUW", | |
| "language": "Japanese", | |
| "language_code": "ja", | |
| "treebank": "GSDLUW", | |
| "ud_short_id": "ja_gsdluw", | |
| "ud_version": "2.12", | |
| "folder": "japanese_gsdluw_ja", | |
| "model_file": "japanese_gsdluw_ja_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 3028 | |
| }, | |
| "ko_gsd": { | |
| "id": "ko_gsd", | |
| "name": "Korean GSD", | |
| "display_name": "Korean — GSD", | |
| "language": "Korean", | |
| "language_code": "ko", | |
| "treebank": "GSD", | |
| "ud_short_id": "ko_gsd", | |
| "ud_version": "2.12", | |
| "folder": "korean_gsd_ko", | |
| "model_file": "korean_gsd_ko_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 1747 | |
| }, | |
| "ko_kaist": { | |
| "id": "ko_kaist", | |
| "name": "Korean Kaist", | |
| "display_name": "Korean — Kaist", | |
| "language": "Korean", | |
| "language_code": "ko", | |
| "treebank": "Kaist", | |
| "ud_short_id": "ko_kaist", | |
| "ud_version": "2.12", | |
| "folder": "korean_kaist_ko", | |
| "model_file": "korean_kaist_ko_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 2332 | |
| }, | |
| "la_ittb": { | |
| "id": "la_ittb", | |
| "name": "Latin ITTB", | |
| "display_name": "Latin — ITTB", | |
| "language": "Latin", | |
| "language_code": "la", | |
| "treebank": "ITTB", | |
| "ud_short_id": "la_ittb", | |
| "ud_version": "2.12", | |
| "folder": "latin_ittb_la", | |
| "model_file": "latin_ittb_la_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 49 | |
| }, | |
| "la_llct": { | |
| "id": "la_llct", | |
| "name": "Latin LLCT", | |
| "display_name": "Latin — LLCT", | |
| "language": "Latin", | |
| "language_code": "la", | |
| "treebank": "LLCT", | |
| "ud_short_id": "la_llct", | |
| "ud_version": "2.12", | |
| "folder": "latin_llct_la", | |
| "model_file": "latin_llct_la_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 66 | |
| }, | |
| "la_proiel": { | |
| "id": "la_proiel", | |
| "name": "Latin PROIEL", | |
| "display_name": "Latin — PROIEL", | |
| "language": "Latin", | |
| "language_code": "la", | |
| "treebank": "PROIEL", | |
| "ud_short_id": "la_proiel", | |
| "ud_version": "2.12", | |
| "folder": "latin_proiel_la", | |
| "model_file": "latin_proiel_la_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 165 | |
| }, | |
| "la_udante": { | |
| "id": "la_udante", | |
| "name": "Latin UDante", | |
| "display_name": "Latin — UDante", | |
| "language": "Latin", | |
| "language_code": "la", | |
| "treebank": "UDante", | |
| "ud_short_id": "la_udante", | |
| "ud_version": "2.12", | |
| "folder": "latin_udante_la", | |
| "model_file": "latin_udante_la_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 69 | |
| }, | |
| "lv_lvtb": { | |
| "id": "lv_lvtb", | |
| "name": "Latvian LVTB", | |
| "display_name": "Latvian — LVTB", | |
| "language": "Latvian", | |
| "language_code": "lv", | |
| "treebank": "LVTB", | |
| "ud_short_id": "lv_lvtb", | |
| "ud_version": "2.12", | |
| "folder": "latvian_lvtb_lv", | |
| "model_file": "latvian_lvtb_lv_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 132 | |
| }, | |
| "lt_alksnis": { | |
| "id": "lt_alksnis", | |
| "name": "Lithuanian ALKSNIS", | |
| "display_name": "Lithuanian — ALKSNIS", | |
| "language": "Lithuanian", | |
| "language_code": "lt", | |
| "treebank": "ALKSNIS", | |
| "ud_short_id": "lt_alksnis", | |
| "ud_version": "2.12", | |
| "folder": "lithuanian_alksnis_lt", | |
| "model_file": "lithuanian_alksnis_lt_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 113 | |
| }, | |
| "qaf_arabizi": { | |
| "id": "qaf_arabizi", | |
| "name": "Maghrebi Arabic French Arabizi", | |
| "display_name": "Maghrebi Arabic French — Arabizi", | |
| "language": "Maghrebi Arabic French", | |
| "language_code": "qaf", | |
| "treebank": "Arabizi", | |
| "ud_short_id": "qaf_arabizi", | |
| "ud_version": "2.12", | |
| "folder": "maghrebi_arabic_arabizi_qaf", | |
| "model_file": "maghrebi_arabic_arabizi_qaf_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 124 | |
| }, | |
| "mr_ufal": { | |
| "id": "mr_ufal", | |
| "name": "Marathi UFAL", | |
| "display_name": "Marathi — UFAL", | |
| "language": "Marathi", | |
| "language_code": "mr", | |
| "treebank": "UFAL", | |
| "ud_short_id": "mr_ufal", | |
| "ud_version": "2.12", | |
| "folder": "marathi_ufal_mr", | |
| "model_file": "marathi_ufal_mr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 71 | |
| }, | |
| "pcm_nsc": { | |
| "id": "pcm_nsc", | |
| "name": "Naija NSC", | |
| "display_name": "Naija — NSC", | |
| "language": "Naija", | |
| "language_code": "pcm", | |
| "treebank": "NSC", | |
| "ud_short_id": "pcm_nsc", | |
| "ud_version": "2.12", | |
| "folder": "naija_nsc_pcm", | |
| "model_file": "naija_nsc_pcm_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 82 | |
| }, | |
| "no_bokmaal": { | |
| "id": "no_bokmaal", | |
| "name": "Norwegian Bokmaal", | |
| "display_name": "Norwegian — Bokmaal", | |
| "language": "Norwegian", | |
| "language_code": "no", | |
| "treebank": "Bokmaal", | |
| "ud_short_id": "no_bokmaal", | |
| "ud_version": "2.12", | |
| "folder": "norwegian_bokmaal_no", | |
| "model_file": "norwegian_bokmaal_no_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 120 | |
| }, | |
| "no_nynorsk": { | |
| "id": "no_nynorsk", | |
| "name": "Norwegian Nynorsk", | |
| "display_name": "Norwegian — Nynorsk", | |
| "language": "Norwegian", | |
| "language_code": "no", | |
| "treebank": "Nynorsk", | |
| "ud_short_id": "no_nynorsk", | |
| "ud_version": "2.12", | |
| "folder": "norwegian_nynorsk_no", | |
| "model_file": "norwegian_nynorsk_no_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 116 | |
| }, | |
| "cu_proiel": { | |
| "id": "cu_proiel", | |
| "name": "Old Church Slavonic PROIEL", | |
| "display_name": "Old Church Slavonic — PROIEL", | |
| "language": "Old Church Slavonic", | |
| "language_code": "cu", | |
| "treebank": "PROIEL", | |
| "ud_short_id": "cu_proiel", | |
| "ud_version": "2.12", | |
| "folder": "old_church_slavonic_proiel_cu", | |
| "model_file": "old_church_slavonic_proiel_cu_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 178 | |
| }, | |
| "orv_birchbark": { | |
| "id": "orv_birchbark", | |
| "name": "Old East Slavic Birchbark", | |
| "display_name": "Old East Slavic — Birchbark", | |
| "language": "Old East Slavic", | |
| "language_code": "orv", | |
| "treebank": "Birchbark", | |
| "ud_short_id": "orv_birchbark", | |
| "ud_version": "2.12", | |
| "folder": "old_east_slavic_birchbark_orv", | |
| "model_file": "old_east_slavic_birchbark_orv_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 122 | |
| }, | |
| "orv_rnc": { | |
| "id": "orv_rnc", | |
| "name": "Old East Slavic RNC", | |
| "display_name": "Old East Slavic — RNC", | |
| "language": "Old East Slavic", | |
| "language_code": "orv", | |
| "treebank": "RNC", | |
| "ud_short_id": "orv_rnc", | |
| "ud_version": "2.12", | |
| "folder": "old_east_slavic_rnc_orv", | |
| "model_file": "old_east_slavic_rnc_orv_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 150 | |
| }, | |
| "orv_torot": { | |
| "id": "orv_torot", | |
| "name": "Old East Slavic TOROT", | |
| "display_name": "Old East Slavic — TOROT", | |
| "language": "Old East Slavic", | |
| "language_code": "orv", | |
| "treebank": "TOROT", | |
| "ud_short_id": "orv_torot", | |
| "ud_version": "2.12", | |
| "folder": "old_east_slavic_torot_orv", | |
| "model_file": "old_east_slavic_torot_orv_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 142 | |
| }, | |
| "fa_perdt": { | |
| "id": "fa_perdt", | |
| "name": "Persian PerDT", | |
| "display_name": "Persian — PerDT", | |
| "language": "Persian", | |
| "language_code": "fa", | |
| "treebank": "PerDT", | |
| "ud_short_id": "fa_perdt", | |
| "ud_version": "2.12", | |
| "folder": "persian_perdt_fa", | |
| "model_file": "persian_perdt_fa_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 141 | |
| }, | |
| "fa_seraji": { | |
| "id": "fa_seraji", | |
| "name": "Persian Seraji", | |
| "display_name": "Persian — Seraji", | |
| "language": "Persian", | |
| "language_code": "fa", | |
| "treebank": "Seraji", | |
| "ud_short_id": "fa_seraji", | |
| "ud_version": "2.12", | |
| "folder": "persian_seraji_fa", | |
| "model_file": "persian_seraji_fa_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 104 | |
| }, | |
| "pl_lfg": { | |
| "id": "pl_lfg", | |
| "name": "Polish LFG", | |
| "display_name": "Polish — LFG", | |
| "language": "Polish", | |
| "language_code": "pl", | |
| "treebank": "LFG", | |
| "ud_short_id": "pl_lfg", | |
| "ud_version": "2.12", | |
| "folder": "polish_lfg_pl", | |
| "model_file": "polish_lfg_pl_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 112 | |
| }, | |
| "pl_pdb": { | |
| "id": "pl_pdb", | |
| "name": "Polish PDB", | |
| "display_name": "Polish — PDB", | |
| "language": "Polish", | |
| "language_code": "pl", | |
| "treebank": "PDB", | |
| "ud_short_id": "pl_pdb", | |
| "ud_version": "2.12", | |
| "folder": "polish_pdb_pl", | |
| "model_file": "polish_pdb_pl_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 139 | |
| }, | |
| "qpm_philotis": { | |
| "id": "qpm_philotis", | |
| "name": "Pomak Philotis", | |
| "display_name": "Pomak — Philotis", | |
| "language": "Pomak", | |
| "language_code": "qpm", | |
| "treebank": "Philotis", | |
| "ud_short_id": "qpm_philotis", | |
| "ud_version": "2.12", | |
| "folder": "pomak_philotis_qpm", | |
| "model_file": "pomak_philotis_qpm_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 125 | |
| }, | |
| "pt_bosque": { | |
| "id": "pt_bosque", | |
| "name": "Portuguese Bosque", | |
| "display_name": "Portuguese — Bosque", | |
| "language": "Portuguese", | |
| "language_code": "pt", | |
| "treebank": "Bosque", | |
| "ud_short_id": "pt_bosque", | |
| "ud_version": "2.12", | |
| "folder": "portuguese_bosque_pt", | |
| "model_file": "portuguese_bosque_pt_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 120 | |
| }, | |
| "pt_cintil": { | |
| "id": "pt_cintil", | |
| "name": "Portuguese CINTIL", | |
| "display_name": "Portuguese — CINTIL", | |
| "language": "Portuguese", | |
| "language_code": "pt", | |
| "treebank": "CINTIL", | |
| "ud_short_id": "pt_cintil", | |
| "ud_version": "2.12", | |
| "folder": "portuguese_cintil_pt", | |
| "model_file": "portuguese_cintil_pt_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 120 | |
| }, | |
| "pt_petrogold": { | |
| "id": "pt_petrogold", | |
| "name": "Portuguese PetroGold", | |
| "display_name": "Portuguese — PetroGold", | |
| "language": "Portuguese", | |
| "language_code": "pt", | |
| "treebank": "PetroGold", | |
| "ud_short_id": "pt_petrogold", | |
| "ud_version": "2.12", | |
| "folder": "portuguese_petrogold_pt", | |
| "model_file": "portuguese_petrogold_pt_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 166 | |
| }, | |
| "ro_nonstandard": { | |
| "id": "ro_nonstandard", | |
| "name": "Romanian Nonstandard", | |
| "display_name": "Romanian — Nonstandard", | |
| "language": "Romanian", | |
| "language_code": "ro", | |
| "treebank": "Nonstandard", | |
| "ud_short_id": "ro_nonstandard", | |
| "ud_version": "2.12", | |
| "folder": "romanian_nonstandard_ro", | |
| "model_file": "romanian_nonstandard_ro_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 109 | |
| }, | |
| "ro_rrt": { | |
| "id": "ro_rrt", | |
| "name": "Romanian RRT", | |
| "display_name": "Romanian — RRT", | |
| "language": "Romanian", | |
| "language_code": "ro", | |
| "treebank": "RRT", | |
| "ud_short_id": "ro_rrt", | |
| "ud_version": "2.12", | |
| "folder": "romanian_rrt_ro", | |
| "model_file": "romanian_rrt_ro_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 153 | |
| }, | |
| "ro_simonero": { | |
| "id": "ro_simonero", | |
| "name": "Romanian SiMoNERo", | |
| "display_name": "Romanian — SiMoNERo", | |
| "language": "Romanian", | |
| "language_code": "ro", | |
| "treebank": "SiMoNERo", | |
| "ud_short_id": "ro_simonero", | |
| "ud_version": "2.12", | |
| "folder": "romanian_simonero_ro", | |
| "model_file": "romanian_simonero_ro_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 123 | |
| }, | |
| "ru_gsd": { | |
| "id": "ru_gsd", | |
| "name": "Russian GSD", | |
| "display_name": "Russian — GSD", | |
| "language": "Russian", | |
| "language_code": "ru", | |
| "treebank": "GSD", | |
| "ud_short_id": "ru_gsd", | |
| "ud_version": "2.12", | |
| "folder": "russian_gsd_ru", | |
| "model_file": "russian_gsd_ru_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 199 | |
| }, | |
| "ru_syntagrus": { | |
| "id": "ru_syntagrus", | |
| "name": "Russian SynTagRus", | |
| "display_name": "Russian — SynTagRus", | |
| "language": "Russian", | |
| "language_code": "ru", | |
| "treebank": "SynTagRus", | |
| "ud_short_id": "ru_syntagrus", | |
| "ud_version": "2.12", | |
| "folder": "russian_syntagrus_ru", | |
| "model_file": "russian_syntagrus_ru_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 171 | |
| }, | |
| "ru_taiga": { | |
| "id": "ru_taiga", | |
| "name": "Russian Taiga", | |
| "display_name": "Russian — Taiga", | |
| "language": "Russian", | |
| "language_code": "ru", | |
| "treebank": "Taiga", | |
| "ud_short_id": "ru_taiga", | |
| "ud_version": "2.12", | |
| "folder": "russian_taiga_ru", | |
| "model_file": "russian_taiga_ru_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 267 | |
| }, | |
| "gd_arcosg": { | |
| "id": "gd_arcosg", | |
| "name": "Scottish Gaelic ARCOSG", | |
| "display_name": "Scottish Gaelic — ARCOSG", | |
| "language": "Scottish Gaelic", | |
| "language_code": "gd", | |
| "treebank": "ARCOSG", | |
| "ud_short_id": "gd_arcosg", | |
| "ud_version": "2.12", | |
| "folder": "scottish_gaelic_arcosg_gd", | |
| "model_file": "scottish_gaelic_arcosg_gd_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 107 | |
| }, | |
| "sr_set": { | |
| "id": "sr_set", | |
| "name": "Serbian SET", | |
| "display_name": "Serbian — SET", | |
| "language": "Serbian", | |
| "language_code": "sr", | |
| "treebank": "SET", | |
| "ud_short_id": "sr_set", | |
| "ud_version": "2.12", | |
| "folder": "serbian_set_sr", | |
| "model_file": "serbian_set_sr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 99 | |
| }, | |
| "sk_snk": { | |
| "id": "sk_snk", | |
| "name": "Slovak SNK", | |
| "display_name": "Slovak — SNK", | |
| "language": "Slovak", | |
| "language_code": "sk", | |
| "treebank": "SNK", | |
| "ud_short_id": "sk_snk", | |
| "ud_version": "2.12", | |
| "folder": "slovak_snk_sk", | |
| "model_file": "slovak_snk_sk_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 129 | |
| }, | |
| "sl_ssj": { | |
| "id": "sl_ssj", | |
| "name": "Slovenian SSJ", | |
| "display_name": "Slovenian — SSJ", | |
| "language": "Slovenian", | |
| "language_code": "sl", | |
| "treebank": "SSJ", | |
| "ud_short_id": "sl_ssj", | |
| "ud_version": "2.12", | |
| "folder": "slovenian_ssj_sl", | |
| "model_file": "slovenian_ssj_sl_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 141 | |
| }, | |
| "es_ancora": { | |
| "id": "es_ancora", | |
| "name": "Spanish AnCora", | |
| "display_name": "Spanish — AnCora", | |
| "language": "Spanish", | |
| "language_code": "es", | |
| "treebank": "AnCora", | |
| "ud_short_id": "es_ancora", | |
| "ud_version": "2.12", | |
| "folder": "spanish_ancora_es", | |
| "model_file": "spanish_ancora_es_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 118 | |
| }, | |
| "es_gsd": { | |
| "id": "es_gsd", | |
| "name": "Spanish GSD", | |
| "display_name": "Spanish — GSD", | |
| "language": "Spanish", | |
| "language_code": "es", | |
| "treebank": "GSD", | |
| "ud_short_id": "es_gsd", | |
| "ud_version": "2.12", | |
| "folder": "spanish_gsd_es", | |
| "model_file": "spanish_gsd_es_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 316 | |
| }, | |
| "sv_lines": { | |
| "id": "sv_lines", | |
| "name": "Swedish LinES", | |
| "display_name": "Swedish — LinES", | |
| "language": "Swedish", | |
| "language_code": "sv", | |
| "treebank": "LinES", | |
| "ud_short_id": "sv_lines", | |
| "ud_version": "2.12", | |
| "folder": "swedish_lines_sv", | |
| "model_file": "swedish_lines_sv_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 94 | |
| }, | |
| "sv_talbanken": { | |
| "id": "sv_talbanken", | |
| "name": "Swedish Talbanken", | |
| "display_name": "Swedish — Talbanken", | |
| "language": "Swedish", | |
| "language_code": "sv", | |
| "treebank": "Talbanken", | |
| "ud_short_id": "sv_talbanken", | |
| "ud_version": "2.12", | |
| "folder": "swedish_talbanken_sv", | |
| "model_file": "swedish_talbanken_sv_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 92 | |
| }, | |
| "ta_ttb": { | |
| "id": "ta_ttb", | |
| "name": "Tamil TTB", | |
| "display_name": "Tamil — TTB", | |
| "language": "Tamil", | |
| "language_code": "ta", | |
| "treebank": "TTB", | |
| "ud_short_id": "ta_ttb", | |
| "ud_version": "2.12", | |
| "folder": "tamil_ttb_ta", | |
| "model_file": "tamil_ttb_ta_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 75 | |
| }, | |
| "tr_atis": { | |
| "id": "tr_atis", | |
| "name": "Turkish Atis", | |
| "display_name": "Turkish — Atis", | |
| "language": "Turkish", | |
| "language_code": "tr", | |
| "treebank": "Atis", | |
| "ud_short_id": "tr_atis", | |
| "ud_version": "2.12", | |
| "folder": "turkish_atis_tr", | |
| "model_file": "turkish_atis_tr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 84 | |
| }, | |
| "tr_boun": { | |
| "id": "tr_boun", | |
| "name": "Turkish BOUN", | |
| "display_name": "Turkish — BOUN", | |
| "language": "Turkish", | |
| "language_code": "tr", | |
| "treebank": "BOUN", | |
| "ud_short_id": "tr_boun", | |
| "ud_version": "2.12", | |
| "folder": "turkish_boun_tr", | |
| "model_file": "turkish_boun_tr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 110 | |
| }, | |
| "tr_framenet": { | |
| "id": "tr_framenet", | |
| "name": "Turkish FrameNet", | |
| "display_name": "Turkish — FrameNet", | |
| "language": "Turkish", | |
| "language_code": "tr", | |
| "treebank": "FrameNet", | |
| "ud_short_id": "tr_framenet", | |
| "ud_version": "2.12", | |
| "folder": "turkish_framenet_tr", | |
| "model_file": "turkish_framenet_tr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 82 | |
| }, | |
| "tr_imst": { | |
| "id": "tr_imst", | |
| "name": "Turkish IMST", | |
| "display_name": "Turkish — IMST", | |
| "language": "Turkish", | |
| "language_code": "tr", | |
| "treebank": "IMST", | |
| "ud_short_id": "tr_imst", | |
| "ud_version": "2.12", | |
| "folder": "turkish_imst_tr", | |
| "model_file": "turkish_imst_tr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 93 | |
| }, | |
| "tr_kenet": { | |
| "id": "tr_kenet", | |
| "name": "Turkish Kenet", | |
| "display_name": "Turkish — Kenet", | |
| "language": "Turkish", | |
| "language_code": "tr", | |
| "treebank": "Kenet", | |
| "ud_short_id": "tr_kenet", | |
| "ud_version": "2.12", | |
| "folder": "turkish_kenet_tr", | |
| "model_file": "turkish_kenet_tr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 97 | |
| }, | |
| "tr_penn": { | |
| "id": "tr_penn", | |
| "name": "Turkish Penn", | |
| "display_name": "Turkish — Penn", | |
| "language": "Turkish", | |
| "language_code": "tr", | |
| "treebank": "Penn", | |
| "ud_short_id": "tr_penn", | |
| "ud_version": "2.12", | |
| "folder": "turkish_penn_tr", | |
| "model_file": "turkish_penn_tr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 110 | |
| }, | |
| "tr_tourism": { | |
| "id": "tr_tourism", | |
| "name": "Turkish Tourism", | |
| "display_name": "Turkish — Tourism", | |
| "language": "Turkish", | |
| "language_code": "tr", | |
| "treebank": "Tourism", | |
| "ud_short_id": "tr_tourism", | |
| "ud_version": "2.12", | |
| "folder": "turkish_tourism_tr", | |
| "model_file": "turkish_tourism_tr_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 82 | |
| }, | |
| "qtd_sagt": { | |
| "id": "qtd_sagt", | |
| "name": "Turkish German SAGT", | |
| "display_name": "Turkish German — SAGT", | |
| "language": "Turkish German", | |
| "language_code": "qtd", | |
| "treebank": "SAGT", | |
| "ud_short_id": "qtd_sagt", | |
| "ud_version": "2.12", | |
| "folder": "turkish_german_sagt_qtd", | |
| "model_file": "turkish_german_sagt_qtd_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 87 | |
| }, | |
| "uk_iu": { | |
| "id": "uk_iu", | |
| "name": "Ukrainian IU", | |
| "display_name": "Ukrainian — IU", | |
| "language": "Ukrainian", | |
| "language_code": "uk", | |
| "treebank": "IU", | |
| "ud_short_id": "uk_iu", | |
| "ud_version": "2.12", | |
| "folder": "ukrainian_iu_uk", | |
| "model_file": "ukrainian_iu_uk_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 194 | |
| }, | |
| "ur_udtb": { | |
| "id": "ur_udtb", | |
| "name": "Urdu UDTB", | |
| "display_name": "Urdu — UDTB", | |
| "language": "Urdu", | |
| "language_code": "ur", | |
| "treebank": "UDTB", | |
| "ud_short_id": "ur_udtb", | |
| "ud_version": "2.12", | |
| "folder": "urdu_udtb_ur", | |
| "model_file": "urdu_udtb_ur_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 132 | |
| }, | |
| "ug_udt": { | |
| "id": "ug_udt", | |
| "name": "Uyghur UDT", | |
| "display_name": "Uyghur — UDT", | |
| "language": "Uyghur", | |
| "language_code": "ug", | |
| "treebank": "UDT", | |
| "ud_short_id": "ug_udt", | |
| "ud_version": "2.12", | |
| "folder": "uyghur_udt_ug", | |
| "model_file": "uyghur_udt_ug_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 73 | |
| }, | |
| "vi_vtb": { | |
| "id": "vi_vtb", | |
| "name": "Vietnamese VTB", | |
| "display_name": "Vietnamese — VTB", | |
| "language": "Vietnamese", | |
| "language_code": "vi", | |
| "treebank": "VTB", | |
| "ud_short_id": "vi_vtb", | |
| "ud_version": "2.12", | |
| "folder": "vietnamese_vtb_vi", | |
| "model_file": "vietnamese_vtb_vi_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 160 | |
| }, | |
| "cy_ccg": { | |
| "id": "cy_ccg", | |
| "name": "Welsh CCG", | |
| "display_name": "Welsh — CCG", | |
| "language": "Welsh", | |
| "language_code": "cy", | |
| "treebank": "CCG", | |
| "ud_short_id": "cy_ccg", | |
| "ud_version": "2.12", | |
| "folder": "welsh_ccg_cy", | |
| "model_file": "welsh_ccg_cy_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 96 | |
| }, | |
| "hyw_armtdp": { | |
| "id": "hyw_armtdp", | |
| "name": "Western Armenian ArmTDP", | |
| "display_name": "Western Armenian — ArmTDP", | |
| "language": "Western Armenian", | |
| "language_code": "hyw", | |
| "treebank": "ArmTDP", | |
| "ud_short_id": "hyw_armtdp", | |
| "ud_version": "2.12", | |
| "folder": "western_armenian_armtdp_hyw", | |
| "model_file": "western_armenian_armtdp_hyw_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 183 | |
| }, | |
| "wo_wtb": { | |
| "id": "wo_wtb", | |
| "name": "Wolof WTB", | |
| "display_name": "Wolof — WTB", | |
| "language": "Wolof", | |
| "language_code": "wo", | |
| "treebank": "WTB", | |
| "ud_short_id": "wo_wtb", | |
| "ud_version": "2.12", | |
| "folder": "wolof_wtb_wo", | |
| "model_file": "wolof_wtb_wo_model.pt", | |
| "vocab_file": "vocab.json", | |
| "config_file": "config.json", | |
| "model_type": "char_lstm_attention_lemmatizer", | |
| "vocab_size": 103 | |
| } | |
| } |