More test sentences

etc/test_sentences/fi.txt

@@ -0,0 +1,7 @@
+Sateenkaari on spektrin väreissä esiintyvä ilmakehän optinen ilmiö.
+Se syntyy, kun valo taittuu pisaran etupinnasta, heijastuu pisaran takapinnasta ja taittuu jälleen pisaran etupinnasta.
+Koska vesipisara on dispersiivinen, valkoinen valo hajoaa väreiksi muodostaen sateenkaaren.
+Prisman tuottama spektri on valon eri aallonpituuksien tasainen jatkumo ilman kaistoja.
+Ihmissilmä kykenee erottamaan spektristä erikseen joitain satoja eri värejä.
+Tämän mukaisesti Munsellin värisysteemi erottaa 100 eri värisävyä.
+Päävärien näennäinen erillisyys on ihmisen näköjärjestelmän ominaisuus ja päävärien tarkka lukumäärä on jossain määrin vapaavalintainen.

etc/test_sentences/ne.txt

@@ -0,0 +1,4 @@
+इन्द्रेणी वा इन्द्रधनुष प्रकाश र रंगबाट उत्पन्न भएको यस्तो घटना हो जसमा रंगीन प्रकाशको एउटा अर्धवृत आकाशमा देखिन्छ। जब सूर्यको प्रकाश पृथ्वीको वायुमण्डलमा भएको पानीको थोपा माथि पर्छ, पानीको थोपाले प्रकाशलाई परावर्तन, आवर्तन र डिस्पर्सन गर्दछ। फलस्वरुप आकाशमा एउटा सप्तरङ्गी अर्धवृताकार प्रकाशीय आकृति उत्पन्न हुन्छ। यो आकृतिलाई नै इन्द्रेणी भनिन्छ। इन्द्रेणी देखिनुको कारण वायुमण्डलमा पानीका कणहरु हुनु नै हो। वर्षा, झरनाबाट उछिट्टिएको पानी, शीत, कुहिरो आदिको इन्द्रेणी देखिने प्रक्रियामा महत्त्वपूर्ण भूमिका हुन्छ। इन्द्रेणीमा सात रंगहरु रातो, सुन्तला, पहेंलो, हरियो, आकाशे निलो, गाढा निलो र बैजनी रंग क्रमैसँग देखिन्छ। यसमा सबैभन्दा माथिल्लो छेउमा रातो रंग र अर्को छेउमा बैजनी रंग देखिन्छ। इन्द्रेणी पूर्ण वृत्ताकार समेत हुन सक्ने भए पनि साधरण अवलोकनकर्ताले जमिन माथि बनेको आधा भाग मात्र देख्न सकिन्छ ।
+इन्द्रेणी देखिनुको कारण वायुमण्डलमा पानीका कणहरु हुनु नै हो। वर्षा, झरनाबाट उछिट्टिएको पानी, शीत, कुहिरो आदिको इन्द्रेणी देखिने प्रक्रियामा महत्त्वपूर्ण भूमिका हुन्छ।
+इन्द्रेणीमा सात रंगहरु रातो, सुन्तला, पहेंलो, हरियो, आकाशे निलो, गाढा निलो र बैजनी रंग क्रमैसँग देखिन्छ। यसमा सबैभन्दा माथिल्लो छेउमा रातो रंग र अर्को छेउमा बैजनी रंग देखिन्छ।
+इन्द्रेणी पूर्ण वृत्ताकार समेत हुन सक्ने भए पनि साधरण अवलोकनकर्ताले जमिन माथि बनेको आधा भाग मात्र देख्न सकिन्छ ।

etc/test_sentences/test_fi.jsonl

@@ -0,0 +1,7 @@
+{"phoneme_ids":[1,0,31,0,120,0,14,0,32,0,18,0,122,0,44,0,23,0,121,0,14,0,122,0,30,0,74,0,3,0,27,0,26,0,3,0,31,0,28,0,120,0,18,0,23,0,32,0,30,0,74,0,26,0,3,0,34,0,120,0,39,0,30,0,18,0,21,0,31,0,31,0,39,0,3,0,120,0,18,0,31,0,74,0,122,0,26,0,32,0,121,0,37,0,34,0,39,0,3,0,120,0,21,0,24,0,25,0,14,0,23,0,18,0,20,0,39,0,26,0,3,0,120,0,27,0,28,0,32,0,74,0,26,0,18,0,26,0,3,0,120,0,21,0,24,0,25,0,74,0,42,0,10,0,2],"phonemes":["s","ˈ","a","t","e","ː","ŋ","k","ˌ","a","ː","r","ɪ"," ","o","n"," ","s","p","ˈ","e","k","t","r","ɪ","n"," ","v","ˈ","æ","r","e","i","s","s","æ"," ","ˈ","e","s","ɪ","ː","n","t","ˌ","y","v","æ"," ","ˈ","i","l","m","a","k","e","h","æ","n"," ","ˈ","o","p","t","ɪ","n","e","n"," ","ˈ","i","l","m","ɪ","ø","."],"processed_text":"Sateenkaari on spektrin väreissä esiintyvä ilmakehän optinen ilmiö.","text":"Sateenkaari on spektrin väreissä esiintyvä ilmakehän optinen ilmiö."}
+{"phoneme_ids":[1,0,31,0,18,0,3,0,31,0,120,0,37,0,26,0,32,0,37,0,122,0,8,0,23,0,120,0,33,0,26,0,3,0,34,0,120,0,14,0,24,0,27,0,3,0,32,0,120,0,14,0,21,0,32,0,122,0,33,0,122,0,3,0,28,0,120,0,21,0,31,0,14,0,30,0,14,0,26,0,3,0,120,0,18,0,32,0,33,0,28,0,121,0,21,0,26,0,26,0,14,0,31,0,32,0,14,0,8,0,20,0,120,0,18,0,21,0,22,0,14,0,31,0,32,0,33,0,122,0,3,0,28,0,120,0,21,0,31,0,14,0,30,0,14,0,26,0,3,0,32,0,120,0,14,0,23,0,14,0,28,0,121,0,21,0,26,0,26,0,14,0,31,0,32,0,14,0,3,0,22,0,14,0,3,0,32,0,120,0,14,0,21,0,32,0,122,0,33,0,122,0,3,0,22,0,120,0,39,0,24,0,24,0,18,0,122,0,25,0,3,0,28,0,120,0,21,0,31,0,14,0,30,0,14,0,26,0,3,0,120,0,18,0,32,0,33,0,28,0,121,0,21,0,26,0,26,0,14,0,31,0,32,0,14,0,10,0,2],"phonemes":["s","e"," ","s","ˈ","y","n","t","y","ː",",","k","ˈ","u","n"," ","v","ˈ","a","l","o"," ","t","ˈ","a","i","t","ː","u","ː"," ","p","ˈ","i","s","a","r","a","n"," ","ˈ","e","t","u","p","ˌ","i","n","n","a","s","t","a",",","h","ˈ","e","i","j","a","s","t","u","ː"," ","p","ˈ","i","s","a","r","a","n"," ","t","ˈ","a","k","a","p","ˌ","i","n","n","a","s","t","a"," ","j","a"," ","t","ˈ","a","i","t","ː","u","ː"," ","j","ˈ","æ","l","l","e","ː","m"," ","p","ˈ","i","s","a","r","a","n"," ","ˈ","e","t","u","p","ˌ","i","n","n","a","s","t","a","."],"processed_text":"Se syntyy, kun valo taittuu pisaran etupinnasta, heijastuu pisaran takapinnasta ja taittuu jälleen pisaran etupinnasta.","text":"Se syntyy, kun valo taittuu pisaran etupinnasta, heijastuu pisaran takapinnasta ja taittuu jälleen pisaran etupinnasta."}
+{"phoneme_ids":[1,0,23,0,120,0,27,0,31,0,23,0,14,0,3,0,34,0,120,0,18,0,31,0,74,0,28,0,121,0,21,0,31,0,14,0,30,0,14,0,3,0,27,0,26,0,3,0,17,0,120,0,21,0,31,0,28,0,18,0,30,0,31,0,121,0,21,0,122,0,34,0,74,0,26,0,18,0,26,0,8,0,34,0,120,0,14,0,24,0,23,0,27,0,21,0,26,0,18,0,26,0,3,0,34,0,120,0,14,0,24,0,27,0,3,0,20,0,120,0,14,0,22,0,27,0,14,0,122,0,3,0,34,0,120,0,39,0,30,0,18,0,21,0,23,0,31,0,74,0,3,0,25,0,120,0,33,0,27,0,17,0,27,0,31,0,32,0,14,0,18,0,26,0,3,0,31,0,120,0,14,0,32,0,18,0,122,0,44,0,23,0,121,0,14,0,122,0,30,0,18,0,26,0,10,0,2],"phonemes":["k","ˈ","o","s","k","a"," ","v","ˈ","e","s","ɪ","p","ˌ","i","s","a","r","a"," ","o","n"," ","d","ˈ","i","s","p","e","r","s","ˌ","i","ː","v","ɪ","n","e","n",",","v","ˈ","a","l","k","o","i","n","e","n"," ","v","ˈ","a","l","o"," ","h","ˈ","a","j","o","a","ː"," ","v","ˈ","æ","r","e","i","k","s","ɪ"," ","m","ˈ","u","o","d","o","s","t","a","e","n"," ","s","ˈ","a","t","e","ː","ŋ","k","ˌ","a","ː","r","e","n","."],"processed_text":"Koska vesipisara on dispersiivinen, valkoinen valo hajoaa väreiksi muodostaen sateenkaaren.","text":"Koska vesipisara on dispersiivinen, valkoinen valo hajoaa väreiksi muodostaen sateenkaaren."}
+{"phoneme_ids":[1,0,28,0,30,0,120,0,21,0,31,0,25,0,14,0,26,0,3,0,32,0,120,0,33,0,27,0,32,0,122,0,14,0,25,0,14,0,3,0,31,0,28,0,120,0,18,0,23,0,32,0,30,0,74,0,3,0,27,0,26,0,3,0,34,0,120,0,14,0,24,0,27,0,26,0,3,0,120,0,18,0,30,0,74,0,3,0,120,0,14,0,122,0,24,0,24,0,27,0,25,0,28,0,74,0,32,0,121,0,33,0,122,0,23,0,31,0,21,0,18,0,26,0,3,0,32,0,120,0,14,0,31,0,14,0,21,0,26,0,18,0,26,0,3,0,22,0,120,0,14,0,32,0,23,0,33,0,25,0,27,0,3,0,120,0,21,0,24,0,25,0,14,0,44,0,3,0,23,0,120,0,14,0,21,0,31,0,32,0,27,0,22,0,14,0,10,0,2],"phonemes":["p","r","ˈ","i","s","m","a","n"," ","t","ˈ","u","o","t","ː","a","m","a"," ","s","p","ˈ","e","k","t","r","ɪ"," ","o","n"," ","v","ˈ","a","l","o","n"," ","ˈ","e","r","ɪ"," ","ˈ","a","ː","l","l","o","m","p","ɪ","t","ˌ","u","ː","k","s","i","e","n"," ","t","ˈ","a","s","a","i","n","e","n"," ","j","ˈ","a","t","k","u","m","o"," ","ˈ","i","l","m","a","ŋ"," ","k","ˈ","a","i","s","t","o","j","a","."],"processed_text":"Prisman tuottama spektri on valon eri aallonpituuksien tasainen jatkumo ilman kaistoja.","text":"Prisman tuottama spektri on valon eri aallonpituuksien tasainen jatkumo ilman kaistoja."}
+{"phoneme_ids":[1,0,120,0,21,0,20,0,25,0,74,0,31,0,31,0,121,0,21,0,24,0,25,0,39,0,3,0,23,0,120,0,37,0,23,0,18,0,26,0,18,0,122,0,3,0,120,0,18,0,30,0,27,0,32,0,122,0,14,0,25,0,14,0,122,0,26,0,3,0,31,0,28,0,120,0,18,0,23,0,32,0,30,0,74,0,31,0,32,0,39,0,3,0,120,0,18,0,30,0,74,0,23,0,31,0,18,0,122,0,26,0,3,0,22,0,120,0,27,0,21,0,32,0,14,0,21,0,26,0,3,0,31,0,120,0,14,0,32,0,27,0,22,0,14,0,3,0,120,0,18,0,30,0,74,0,3,0,34,0,120,0,39,0,30,0,18,0,22,0,39,0,10,0,2],"phonemes":["ˈ","i","h","m","ɪ","s","s","ˌ","i","l","m","æ"," ","k","ˈ","y","k","e","n","e","ː"," ","ˈ","e","r","o","t","ː","a","m","a","ː","n"," ","s","p","ˈ","e","k","t","r","ɪ","s","t","æ"," ","ˈ","e","r","ɪ","k","s","e","ː","n"," ","j","ˈ","o","i","t","a","i","n"," ","s","ˈ","a","t","o","j","a"," ","ˈ","e","r","ɪ"," ","v","ˈ","æ","r","e","j","æ","."],"processed_text":"Ihmissilmä kykenee erottamaan spektristä erikseen joitain satoja eri värejä.","text":"Ihmissilmä kykenee erottamaan spektristä erikseen joitain satoja eri värejä."}
+{"phoneme_ids":[1,0,32,0,121,0,39,0,25,0,39,0,26,0,3,0,25,0,120,0,33,0,23,0,14,0,21,0,31,0,121,0,18,0,31,0,32,0,74,0,25,0,3,0,25,0,120,0,33,0,26,0,31,0,18,0,24,0,24,0,74,0,26,0,3,0,34,0,120,0,39,0,30,0,74,0,31,0,121,0,37,0,31,0,32,0,18,0,122,0,25,0,74,0,3,0,120,0,18,0,30,0,27,0,32,0,122,0,14,0,122,0,3,0,31,0,120,0,14,0,32,0,14,0,3,0,120,0,18,0,30,0,74,0,3,0,34,0,120,0,39,0,30,0,74,0,31,0,121,0,39,0,34,0,37,0,39,0,10,0,2],"phonemes":["t","ˌ","æ","m","æ","n"," ","m","ˈ","u","k","a","i","s","ˌ","e","s","t","ɪ","m"," ","m","ˈ","u","n","s","e","l","l","ɪ","n"," ","v","ˈ","æ","r","ɪ","s","ˌ","y","s","t","e","ː","m","ɪ"," ","ˈ","e","r","o","t","ː","a","ː"," ","s","ˈ","a","t","a"," ","ˈ","e","r","ɪ"," ","v","ˈ","æ","r","ɪ","s","ˌ","æ","v","y","æ","."],"processed_text":"Tämän mukaisesti Munsellin värisysteemi erottaa 100 eri värisävyä.","text":"Tämän mukaisesti Munsellin värisysteemi erottaa 100 eri värisävyä."}
+{"phoneme_ids":[1,0,28,0,120,0,39,0,122,0,34,0,39,0,30,0,21,0,18,0,26,0,3,0,26,0,120,0,39,0,18,0,26,0,26,0,121,0,39,0,21,0,26,0,18,0,26,0,3,0,120,0,18,0,30,0,74,0,24,0,24,0,74,0,31,0,37,0,122,0,31,0,3,0,27,0,26,0,3,0,120,0,21,0,20,0,25,0,74,0,31,0,18,0,26,0,3,0,26,0,120,0,39,0,23,0,42,0,22,0,121,0,39,0,30,0,22,0,18,0,31,0,32,0,121,0,18,0,24,0,25,0,39,0,26,0,3,0,120,0,27,0,25,0,74,0,26,0,121,0,14,0,21,0,31,0,33,0,122,0,31,0,3,0,22,0,14,0,3,0,28,0,120,0,39,0,122,0,34,0,39,0,30,0,21,0,18,0,26,0,3,0,32,0,120,0,14,0,30,0,23,0,122,0,14,0,3,0,24,0,120,0,33,0,23,0,33,0,25,0,121,0,39,0,122,0,30,0,39,0,3,0,27,0,26,0,3,0,22,0,120,0,27,0,31,0,31,0,14,0,21,0,26,0,3,0,25,0,120,0,39,0,122,0,30,0,74,0,26,0,3,0,34,0,120,0,14,0,28,0,14,0,122,0,34,0,14,0,24,0,121,0,21,0,26,0,32,0,14,0,21,0,26,0,18,0,26,0,10,0,2],"phonemes":["p","ˈ","æ","ː","v","æ","r","i","e","n"," ","n","ˈ","æ","e","n","n","ˌ","æ","i","n","e","n"," ","ˈ","e","r","ɪ","l","l","ɪ","s","y","ː","s"," ","o","n"," ","ˈ","i","h","m","ɪ","s","e","n"," ","n","ˈ","æ","k","ø","j","ˌ","æ","r","j","e","s","t","ˌ","e","l","m","æ","n"," ","ˈ","o","m","ɪ","n","ˌ","a","i","s","u","ː","s"," ","j","a"," ","p","ˈ","æ","ː","v","æ","r","i","e","n"," ","t","ˈ","a","r","k","ː","a"," ","l","ˈ","u","k","u","m","ˌ","æ","ː","r","æ"," ","o","n"," ","j","ˈ","o","s","s","a","i","n"," ","m","ˈ","æ","ː","r","ɪ","n"," ","v","ˈ","a","p","a","ː","v","a","l","ˌ","i","n","t","a","i","n","e","n","."],"processed_text":"Päävärien näennäinen erillisyys on ihmisen näköjärjestelmän ominaisuus ja päävärien tarkka lukumäärä on jossain määrin vapaavalintainen.","text":"Päävärien näennäinen erillisyys on ihmisen näköjärjestelmän ominaisuus ja päävärien tarkka lukumäärä on jossain määrin vapaavalintainen."}