upload training datasets

Author: lpcoladangelo

training-data/20251126-languages-training-data.csv

@@ -0,0 +1,342 @@
+language_as_recorded,language_code,authorized_label,structured_value,ds_qid
+Text in Sinhala,,,,
+Text in Latin,,,,
+Text in Latin and German,,,,
+Text in Greek and Latin,,,,
+Text in Ancient Greek,,,,
+In Spanish,,,,
+Text in Italian,,,,
+arm,,,,
+sin,,,,
+Text in Greek,,,,
+ger,,,,
+lat,,,,
+Modern Javanese,,,,
+Text in Spanish,,,,
+Text in Armenian,,,,
+Text in Dutch,,,,
+In Latin,,,,
+In Pali,,,,
+Text in English and Latin,,,,
+In Geez,,,,
+"In Batak (Poda, Toba script). The script uses the southern ta. Two variants of the letter na occur; next to the standard form the ancient na (as Voorhoeve called it) is also occasionally used. The ancient na is typically found in Mandailing manuscripts, but this manuscript is clearly not Mandailing, but was probably written in the Toba district",,,,
+In Ge'ez,,,,
+Text in Church Slavic,,,,
+"In Batak (Poda, Toba script)",,,,
+Text in Ge'ez,,,,
+In French,,,,
+Text written in Sanskrit,,,,
+eng,,,,
+In Latin and French,,,,
+Text written in Tibetan,,,,
+Text in Latin and Spanish,,,,
+In Latin and Spanish,,,,
+syr,,,,
+In Chinese and Japanese,,,,
+jpn,,,,
+In Arabic with rubrics and marginal text in Persian,,,,
+Text in Arabic,,,,
+Text in Pali and Sinhala,,,,
+Text in Latin and Italian,,,,
+Text in German,,,,
+In Batak (Poda),,,,
+Text in Latin and English,,,,
+Text in French,,,,
+In Italian,,,,
+Low-German dialect,,,,
+fre,,,,
+"In Dutch, three documents in French",,,,
+Text in English,,,,
+ita,,,,
+Hebrew,,,,
+Text in Syriac,,,,
+In Middle French,,,,
+"In Latin, with some Italian in epistolary formulas",,,,
+In Japanese,,,,
+san,,,,
+Written in Pali,,,,
+"In Persian, Tajik script",,,,
+Text in Pali,,,,
+Latin words,,,,
+Text in French and Latin,,,,
+Text in Italian and Latin,,,,
+Text in Latin with notes in Italian in the margins,,,,
+In Persian,,,,
+tib,,,,
+In Greek,,,,
+"In Kanbun, without typical Japanese reading marks",,,,
+In Syriac,,,,
+Italian,,,,
+Text in Latin; translated from Italian,,,,
+Text in Greek and Church Slavonic,,,,
+Text in Latin and French,,,,
+per,,,,
+In German and Latin,,,,
+Latin,,,,
+In Hebrew,,,,
+Text in Greek and Arabic,,,,
+In Spanish and Latin,,,,
+Text written in Tamil,,,,
+gre,,,,
+In Latin; fol. 68v in English,,,,
+"Text in English, translated from French",,,,
+Text in Bengali and Sanskrit,,,,
+Greek,,,,
+Text in Latin and with marginalia in Latin and Greek,,,,
+"Text chiefly in Latin, with prayer to the Holy Trinity (fol. 92) in French",,,,
+heb,,,,
+und,,,,
+In German,,,,
+Text in multiple languages,,,,
+Text written in Sinhalese script,,,,
+"Text in Latin, French, Anglo-Norman French, and English",,,,
+Text in German and some Latin,,,,
+Texts in Latin,,,,
+In English,,,,
+Latin and German,,,,
+Arabic,,,,
+Chiefly in Latin with some Italian,,,,
+"Middle High German, Rhenish (Middle Franconian) dialect",,,,
+"Latin, with a few documents in Italian",,,,
+In Italian and Latin,,,,
+Latin and Italian,,,,
+"Latin, with one leaf in Italian (f. 2r)",,,,
+German,,,,
+Italian and Latin,,,,
+Latin and Low German,,,,
+Hebrew (vocalized),,,,
+"Latin, with some words in German (f. 54r, 55r, 89r)",,,,
+In Dutch,,,,
+"In Latin, with a few words in Italian",,,,
+German; liturgical text on covers in Latin,,,,
+"Latin, with short passages in German",,,,
+"In Latin, with later summaries in French (verso)",,,,
+Middle French,,,,
+In Latin and Italian,,,,
+"Italian, in Tuscan dialect",,,,
+"In Coptic, with a few marginal notations of later date in Arabic and German",,,,
+"Some items in Latin, some in Italian",,,,
+"In Latin, with German words (f. 2r-51r)",,,,
+"Italian, probably Tuscan, with some prayers in Latin",,,,
+Spanish,,,,
+"Latin, with a few headings in French",,,,
+"Latin, with some French translations in the first conjugation table (f. 8r-9r)",,,,
+"Latin, with a few notes in Italian",,,,
+Latin and French,,,,
+"German, with some French on two leaves (f. 153-154)",,,,
+"Latin, with one section (f. 267r-272r) and some recipes, notes, and names in Italian",,,,
+Persian,,,,
+"Latin, with calendar and accessory texts in French",,,,
+"In Italian, with a few words in Latin",,,,
+"In Italian, with notarial signatures in Latin",,,,
+Written in Latin with a small amount of Italian (f. 91r-94v),,,,
+"Latin, with occasional paragraphs in Italian",,,,
+"Middle High German, with some Latin",,,,
+"Italian, in the Venetian dialect",,,,
+"Latin, with calendar in French (f. 1r-12v)",,,,
+Provençal,,,,
+"Italian, with a short work in Latin (f. 26r-30v)",,,,
+"In Latin, with some documents in Italian",,,,
+Old French,,,,
+Italian; possibly in the Florentine vernacular,,,,
+"Latin, with some rubrics and directions in French",,,,
+"Catalan, with prologue in Latin",,,,
+French,,,,
+Persian and Arabic,,,,
+"Latin, with occasional words in Greek",,,,
+Hebrew; introduction in Italian,,,,
+"German, with Latin phrases",,,,
+"Italian, with Greek on flyleaves",,,,
+Italian with a short section in Latin (f. 49r-49v),,,,
+"In German, with Latin phrase",,,,
+"Latin, with a poem in Middle English",,,,
+"In Italian, with first paragraph and notarial signature in Latin",,,,
+"Latin, with some passages in German (f. 10v, 20v-21r, 40v-43v, 83v-84v, 91r-93v) and Czech (f. 11v, 26v-28v)",,,,
+"Latin, with one inscription in Hebrew (f. 20r)",,,,
+Added notes in Italian (Volume 1),,,,
+"Latin, with annotations in Latin and Greek",,,,
+"Latin, with some Italian (f. 5r-7v, 13r-15v, 46r-51v) and Spanish (f. 9r-11v)",,,,
+Italian and Spanish,,,,
+"Hebrew, with occasional notes in Italian (f. 22r, 24v, 26v, 27v, 82v, 83v)",,,,
+"Latin, with some Italian",,,,
+"Latin with occasional words in Greek (f. 21r, 134v)",,,,
+"Middle French, with verses in Old French",,,,
+Ancient Greek,,,,
+"Italian, with some Latin, most frequently for the openings and closings of documents",,,,
+Low German,,,,
+"Latin, with a few words in Middle English",,,,
+"Italian, with a few headings, etc. in Latin",,,,
+"Latin, with two recipes in Italian",,,,
+"French, with citations and margin notes in Latin",,,,
+"Latin, with words transcribed from Arabic",,,,
+"Middle English, with some Latin notations",,,,
+Ottoman Turkish with some Arabic,,,,
+"Italian (Venetian dialect), with three recipes in Latin (f. 17r)",,,,
+"Italian, with a preface in Latin",,,,
+"In Italian, with some letters to Donato Acciaiuoli in Latin",,,,
+"Middle French, with some sections in Latin (f. 77r-81v, 85v-87r, 93r-98r, 137v, 141r)",,,,
+"In Italian, Latin, and Spanish",,,,
+"Latin, with occasional Greek terms. Blank spaces left for other Greek terms",,,,
+Hebrew and Latin,,,,
+Aramaic,,,,
+"Latin, with a few words in Spanish (f. 7r)",,,,
+"Italian, with a few items in Latin",,,,
+"Latin, with one work in German (f. 167r-167v)",,,,
+"Latin, with Middle French notations in margins",,,,
+"Italian, in the Venetian dialect; list of indulgences in Latin (f. 56r-61v)",,,,
+"Italian, with colophon in Latin",,,,
+"Latin, with Low German prayers and interlinear translations interspersed throughout",,,,
+"English, with some notes in Latin and occasional words in Greek",,,,
+"Italian, with first item and some titles in Latin",,,,
+Dutch,,,,
+"Latin, with some Greek",,,,
+"Italian, with some Latin",,,,
+"Latin, with weekday devotions in Italian (f. 129-133)",,,,
+German with Latin calendar and colophon,,,,
+"Latin, with a few words in Greek in notes and passages in Greek in printed text",,,,
+Middle French and Latin,,,,
+"Mostly in German, with significant sections of the text in Latin. Some notations on the front and back end-leaves (dating from later than the text itself) are in Latin",,,,
+"Spanish, with some Latin",,,,
+Latin and Spanish,,,,
+"In Italian, with a few lines in Latin",,,,
+"In Latin, with a few words in Middle English",,,,
+Middle English and Latin,,,,
+"Latin (f. 1r-56v), with some Spanish (f. 78r-169v) and sections of German",,,,
+"Italian, with one note in Latin and Italian",,,,
+"Italian, Latin, and Spanish",,,,
+Latin with Spanish notes at the end,,,,
+"Arabic, with some Persian",,,,
+"Italian, with headings and occasional marginal notes in Latin",,,,
+"Latin and Italian, with a few words in Greek",,,,
+"Latin, except for one document in Italian",,,,
+Ethiopic,,,,
+"Latin, with a few notes in German",,,,
+"Latin, with words and names in Ancient Greek and Hebrew",,,,
+"Italian, in the Northeastern (Venetian?) vernacular",,,,
+"Latin, with first item in Italian (f. 2r-68r)",,,,
+"Latin, with the final poem in Italian (f. 16v)",,,,
+"Latin, with title and final words in Greek and notes inside the covers in Greek and Italian",,,,
+"German, with chapter and closing rubrics in Latin",,,,
+Latin with rubrics in German and later additions in Latin and German,,,,
+"Judeo-Arabic, with a brief work in Hebrew (f. 25r-39v); notes in Samaritan (f. 1v-7v, 21r-22v, 3 bifolia laid in after f. 22v, marginal notes as on f. 281v), Arabic (f. 1r, marginal notes on Samaritan bifolia), and Latin letters (f. 20v, 25v, 238r, 239v)",,,,
+"Italian, with a few copies in Latin and Spanish",,,,
+In Latin with extensive rubrics in German,,,,
+Middle English,,,,
+"Latin, with quotations in Greek",,,,
+gmh,,,,
+"Latin, with a few sentences in Italian",,,,
+"Latin, with a Hebrew alphabet and a few Hebrew words (f. 95v)",,,,
+"Latin, with calendar (f. 1r-12v), the Fifteen joys (f. 72v-75r), and a suffrage of Saint Bernard (f. 106r-106v) in Middle French",,,,
+"Latin, with later additions in German",,,,
+"In Latin, with some Hungarian and Turkish",,,,
+"Latin, with table of contents and later additions in Italian",,,,
+"Middle English, passages in Latin",,,,
+cze,,,,
+"English, with many works translated from Latin and retaining Latin titles",,,,
+French and German,,,,
+"Provençal, Occitan (modern Provençal), and one document in Latin",,,,
+"Latin, with French translation",,,,
+"English, with a few words in Latin",,,,
+"Middle High German, with one prayer in Latin (f. 8r)",,,,
+"Greek, with Greek and Latin annotations",,,,
+"Latin, with a few lines in German",,,,
+"In Latin, with the words of the bride and groom and the note of the bride's brother in Middle English",,,,
+Armenian,,,,
+"Latin, with some lines of Greek",,,,
+"Latin, with many 16th- and 17th-century entries and marginalia in Italian",,,,
+"Latin, with some Italian passages",,,,
+"Italian, with short introduction in Latin",,,,
+"Hebrew, with one interlinear glossed word in Latin (f. 54r)",,,,
+"Italian, with one prayer in Latin",,,,
+Italian; mottoes or epitaphs in Latin,,,,
+"Italian, with occasional phrases in Latin",,,,
+"Latin, with a few poems in Italian (f. 106r-108v)",,,,
+"In Latin, with brief endorsements in Middle English",,,,
+"Latin, with 23 letters from Gregory XI in French",,,,
+Ladino,,,,
+Middle High German,,,,
+"Latin, with Greek word ""telos"" (f. 24v)",,,,
+"Italian, last item in Latin",,,,
+"Mostly German, with benedictions in Latin (f. 22v-23r)",,,,
+"Italian, with a few words in Greek",,,,
+"Latin, with several items in Italian",,,,
+"In Italian, with some Latin",,,,
+"Arabic, with commentary in Ottoman Turkish",,,,
+"Italian, with short ""Missa"" text at end in Latin",,,,
+"Latin, with chart of Greek letters and diphthongs (f. 11r)",,,,
+"Latin, with a few marginal notes in French",,,,
+In Latin and Middle French,,,,
+"Latin, with passages in Spanish, Italian, Sicilian dialect, and Catalan",,,,
+In Spanish with two quotations in Latin (f. 3v),,,,
+"Spanish, with heading in Latin",,,,
+enm,,,,
+"In English, with endorsement in Latin",,,,
+"In Latin, with some Italian (f. 1r)",,,,
+"Middle High German, with some headings and sections in Latin",,,,
+"In Latin, with some documents in Italian and Spanish",,,,
+Latin with some rubrics in Middle English,,,,
+"German, with some letters in Latin",,,,
+"In Latin, with a few words in Greek",,,,
+"Plant names in Latin, with a few words in Italian (f. 2r-53v); texts about Morocco in English, Spanish, and Latin (54r-97v); glossary of words in Arabic, Spanish, and Latin (f. 98r-101r)",,,,
+"Predominant work in Hebrew (p. 19-234), with shorter works in Judeo-Arabic",,,,
+"Italian, in the Tuscan dialect",,,,
+"Provençal (f. 1-13, 25-26) and Old French (f. 14-23)",,,,
+"Latin, Middle French, and some words in Middle English (f. 214v)",,,,
+"Latin, with frequent Greek words",,,,
+"Italian, with a few words in Friulian (northeastern Italian) dialect",,,,
+Latin with German interlinear glosses and translations,,,,
+In Old French,,,,
+Middle English; some works in Latin,,,,
+"German, with Latin and Hebrew",,,,
+Latin (f. 1r-5r) and Italian with rubrics in Latin (f. 5v-20r),,,,
+Latin and Middle High German,,,,
+Latin and German (lower Alemannic with middle German idioms),,,,
+"Latin, with one later page in Italian (pasted-in note following f. 66)",,,,
+In Catalan,,,,
+"In Italian, with two leaves in Latin",,,,
+"In Italian, with 1 document each in Latin and Spanish",,,,
+"Italian, some of the letters are in Spanish",,,,
+In Middle English,,,,
+"English, with a fragment from a document in Latin (f. 76-78)",,,,
+"Latin, with articles and prayers in Polish",,,,
+"Latin, with one document in French",,,,
+"Italian, with a few words in Latin",,,,
+"Latin, with notes on original cover in Italian",,,,
+"Latin, with a few leaves in German",,,,
+"Old French, last section has some Latin",,,,
+"Latin, with marginal notes and accounts in French",,,,
+"Latin, with a few short sections in Italian (p. 169-174)",,,,
+In Valencian Catalan,,,,
+"Italian and Latin, with two documents in French",,,,
+"Italian, with three documents in Latin (f.7-8 and f.37)",,,,
+"Latin (f. 1r-77r, and table of contents, f. 88v) and French (f. 77v-88v)",,,,
+Latin and Old French,,,,
+"Italian, with one letter in Spanish",,,,
+"Condition in Middle English, obligation in Latin, and later summary in English",,,,
+Ge'ez,,,,
+Amharic,,,,
+English?,,,,
+Arabic or Persian,,,,
+English,,,,
+ara,,,,
+"Ottoman Turkish, Persian and Arabic",,,,
+"In Arabic, with one page in Persian",,,,
+Arabic and Persian,,,,
+In Arabic and Ottoman Turkish,,,,
+In Arabic,,,,
+Ottoman Turkish and Arabic,,,,
+"Arabic, Persian, and Ottoman Turkish",,,,
+ota,,,,
+"In Arabic, Ottoman Turkish and Persian",,,,
+Arabic and Urdu,,,,
+Pushto,,,,
+Arabic and Ottoman Turkish,,,,
+Urdu,,,,
+"Arabic, Persian and Ottoman Turkish",,,,
+Turkmen in Arabic script,,,,
+urd,,,,
+Chagatai,,,,
+In Chagatai,,,,
+"Arabic, Ottoman Turkish and Persian",,,,
+spa,,,,
+dut,,,,