docuracy/symphonym-v7
057
1{2 "total_toponyms": 66924548,3 "in_training_namespaces": 57593810,4 "with_ipa": 31113585,5 "with_panphon_embedding": 31113585,6 "panphon_coverage_pct": 54.02244616218305,7 "from_db_cache": 31113562,8 "from_precomputed": 2,9 "from_epitran": 21,10 "by_script": {11 "CYRILLIC": 3614762,12 "LATIN": 55617677,13 "CJK": 2973525,14 "ARABIC": 2098089,15 "HEBREW": 151960,16 "KATAKANA": 340555,17 "MALAYALAM": 68176,18 "HIRAGANA": 151980,19 "OTHER": 342642,20 "GEORGIAN": 105902,21 "GREEK": 217997,22 "DEVANAGARI": 166957,23 "ARMENIAN": 153467,24 "THAI": 251458,25 "KANNADA": 43155,26 "HANGUL": 393996,27 "GUJARATI": 21428,28 "BENGALI": 106896,29 "TAMIL": 52486,30 "TELUGU": 5144031 },32 "by_script_lang_ipa": {33 "LATIN:en": 8039689,34 "LATIN:fr": 2311837,35 "LATIN:nl": 2292068,36 "LATIN:de": 2063027,37 "LATIN:sv": 1715947,38 "LATIN:es": 1518527,39 "CJK:zh": 1306961,40 "LATIN:id": 931192,41 "LATIN:tr": 843744,42 "LATIN:it": 815130,43 "CYRILLIC:ru": 803734,44 "LATIN:pt": 711346,45 "LATIN:pl": 655880,46 "LATIN:cs": 593385,47 "ARABIC:fa": 576743,48 "LATIN:fi": 532010,49 "CYRILLIC:uk": 435644,50 "LATIN:no": 428240,51 "ARABIC:ar": 412306,52 "LATIN:ro": 375292,53 "KATAKANA:ja": 310410,54 "LATIN:da": 297142,55 "LATIN:ms": 285578,56 "LATIN:vi": 267432,57 "LATIN:hu": 247134,58 "CYRILLIC:bg": 235749,59 "CYRILLIC:sr": 235582,60 "HANGUL:ko": 228523,61 "THAI:th": 210310,62 "GREEK:el": 168827,63 "ARMENIAN:hy": 143819,64 "HEBREW:he": 127337,65 "LATIN:sw": 113131,66 "ARABIC:ur": 109688,67 "GEORGIAN:ka": 86021,68 "BENGALI:bn": 77935,69 "LATIN:la": 77703,70 "CYRILLIC:mk": 61607,71 "DEVANAGARI:hi": 60800,72 "MALAYALAM:ml": 53546,73 "CJK:wuu": 48883,74 "TAMIL:ta": 47700,75 "TELUGU:te": 47617,76 "HIRAGANA:ja": 47533,77 "CJK:gan": 37097,78 "CJK:yue": 31345,79 "DEVANAGARI:mr": 24452,80 "KANNADA:kn": 20962,81 "GUJARATI:gu": 20329,82 "LATIN:yue": 13719,83 "DEVANAGARI:ne": 10249,84 "CJK:ko": 2060,85 "LATIN:wuu": 254,86 "KATAKANA:zh": 69,87 "LATIN:gan": 60,88 "CYRILLIC:zh": 53,89 "OTHER:zh": 51,90 "OTHER:ko": 21,91 "HIRAGANA:yue": 15,92 "ARABIC:yue": 14,93 "HANGUL:zh": 14,94 "HIRAGANA:zh": 14,95 "ARABIC:zh": 13,96 "OTHER:he": 10,97 "GREEK:zh": 9,98 "THAI:yue": 7,99 "THAI:zh": 7,100 "CYRILLIC:yue": 7,101 "OTHER:yue": 5,102 "KATAKANA:ko": 4,103 "HEBREW:yue": 4,104 "THAI:wuu": 3,105 "CYRILLIC:ko": 3,106 "BENGALI:yue": 3,107 "DEVANAGARI:zh": 3,108 "KATAKANA:yue": 3,109 "TAMIL:yue": 2,110 "ARMENIAN:yue": 2,111 "TELUGU:zh": 2,112 "HANGUL:yue": 2,113 "CYRILLIC:wuu": 2,114 "GREEK:ko": 1,115 "OTHER:wuu": 1,116 "ARABIC:ko": 1,117 "GEORGIAN:yue": 1,118 "HEBREW:zh": 1,119 "OTHER:gan": 1,120 "TAMIL:zh": 1121 },122 "training_namespaces": [123 "gn",124 "wd",125 "tgn"126 ],127 "num_workers": 62,128 "db_engine": "DuckDB",129 "ipa_backends": [130 "epitran",131 "phonikud",132 "charsiu_g2p"133 ]134}