diff --git a/.gitignore b/.gitignore index 8594f9f..d50d151 100644 --- a/.gitignore +++ b/.gitignore @@ -13,6 +13,8 @@ htmlcov /build/ /local/ /dist/ +/lib/ +/install/ *.so .venv/ diff --git a/etc/test_sentences/ar.txt b/etc/test_sentences/ar.txt new file mode 100644 index 0000000..bdb214a --- /dev/null +++ b/etc/test_sentences/ar.txt @@ -0,0 +1,8 @@ +أَوَّلُ مَنْ عَمَّرَ مَمْلَكَةَ آرْثِنْ. قَتَل أَباهُ لِيَحْكُمَ مَمْلَكَتَهْ. خَانَ مَمْلَكَةً كانَتْ أَكْثَرَ الْحُلَفَاءِ إِخْلَاصًا فِي عَهْدِ أَبِيهْ. حَوَّلَ نَفْسَهُ إِلَى تِنِّينٍ وَتَخَلى عَنْ عَالَمِهِ لِيُعْلِنَ الْحَرْبَ عَلَى سُكّانِ الْعَالَمِ الَّذِي لَجَأَ إِلَيْهْ. لَمْ يَتْرُكْ مَكَانًا إِلَّا وَأَخَذَهُ بِالْقُوَّةِ أَو دَمّرهُ عَنْ بَكْرَةِ أَبِيهْ. إِنَّهُ الْمَلك الْمَشْؤُومْ, الْخَائِنُ الْمَحْرُومْ, حَدِيزُسْ بْيُوكُورْنُو فْرِزِلْيُوسْ اِبْنُ أَسْبُثْيُسْ السَّابِعْ, وَالْمُسَمَّى حَدِيزْ. +قَوْسُ قُزح يسمى كذلك قوس المطر أو قوس الألوان وهو ظاهرة طبيعية فيزيائية ناتجة عن انكسار وتحلل ضوء +الشمس خلال قطرة ماء المطر، يظهر قوس المطر بعد سقوط المطر أو خلال سقوط المطر والشمس مشرقة، تكون +الألوان في القوس اللون الأحمر من الخارج ويتدرج إلى البرتقالي فالأصفر فالأخضر فالأزرق فأزرق غامق (نيلي) +فبنفسجي من الداخل، ضوء الشمس يحتوي على العديد من الألوان الطيفية وهي عبارة عن أشعة ذات أطوال موجية +مختلفة، يظهر قوس القزح عادة بشكل نصف دائري وفي حالات نادرة يكون قمرياً حيث يكون انكسار ضوء القمر +المسبب لهُ عبر قطرة الماء ملائماً مع مكان وجود القمر في تلك اللحظات. ويظهر للمشاهد نتيجة لضوئهِ الخافت أبيض +لأن العين البشرية لا تستطيع أن ترى الألوان في الليل. diff --git a/etc/test_sentences/test_ar.jsonl b/etc/test_sentences/test_ar.jsonl new file mode 100644 index 0000000..dbe8ea8 --- /dev/null +++ b/etc/test_sentences/test_ar.jsonl @@ -0,0 +1,8 @@ +{"phoneme_ids":[1,0,109,0,120,0,14,0,33,0,122,0,24,0,121,0,33,0,3,0,25,0,120,0,21,0,26,0,3,0,110,0,120,0,33,0,25,0,14,0,30,0,121,0,14,0,3,0,25,0,120,0,33,0,25,0,24,0,24,0,23,0,14,0,32,0,121,0,21,0,26,0,3,0,109,0,14,0,122,0,30,0,120,0,14,0,126,0,14,0,26,0,121,0,14,0,10,0,2,1,0,29,0,120,0,14,0,32,0,21,0,24,0,121,0,14,0,3,0,109,0,120,0,14,0,15,0,14,0,122,0,20,0,121,0,33,0,3,0,24,0,21,0,122,0,121,0,14,0,43,0,23,0,33,0,25,0,121,0,14,0,3,0,25,0,121,0,33,0,25,0,24,0,14,0,23,0,120,0,14,0,32,0,14,0,20,0,121,0,33,0,10,0,2,1,0,127,0,120,0,14,0,122,0,26,0,3,0,25,0,33,0,25,0,24,0,120,0,21,0,23,0,14,0,32,0,121,0,14,0,26,0,3,0,23,0,14,0,122,0,26,0,121,0,14,0,32,0,3,0,109,0,120,0,14,0,23,0,126,0,14,0,30,0,121,0,33,0,3,0,14,0,24,0,43,0,33,0,24,0,120,0,14,0,19,0,14,0,122,0,109,0,121,0,21,0,3,0,109,0,127,0,24,0,120,0,14,0,122,0,31,0,142,0,14,0,26,0,3,0,19,0,21,0,122,0,3,0,110,0,120,0,14,0,20,0,17,0,21,0,3,0,109,0,120,0,14,0,15,0,21,0,122,0,20,0,121,0,21,0,10,0,2,1,0,43,0,120,0,14,0,33,0,24,0,121,0,14,0,3,0,26,0,120,0,14,0,19,0,31,0,21,0,20,0,121,0,21,0,3,0,109,0,24,0,120,0,14,0,122,0,3,0,32,0,120,0,14,0,26,0,21,0,122,0,26,0,121,0,21,0,26,0,3,0,35,0,14,0,32,0,120,0,33,0,127,0,14,0,24,0,24,0,121,0,14,0,3,0,110,0,120,0,14,0,26,0,3,0,110,0,14,0,122,0,24,0,120,0,21,0,25,0,21,0,20,0,121,0,21,0,3,0,24,0,14,0,121,0,21,0,33,0,110,0,121,0,14,0,24,0,14,0,26,0,121,0,14,0,3,0,14,0,24,0,43,0,120,0,14,0,30,0,15,0,14,0,3,0,110,0,120,0,14,0,24,0,14,0,122,0,3,0,31,0,33,0,23,0,122,0,121,0,14,0,122,0,26,0,21,0,3,0,14,0,24,0,110,0,120,0,14,0,122,0,24,0,21,0,25,0,121,0,21,0,3,0,14,0,24,0,24,0,41,0,120,0,21,0,122,0,3,0,24,0,14,0,17,0,108,0,121,0,14,0,109,0,14,0,3,0,109,0,24,0,120,0,14,0,21,0,20,0,121,0,21,0,10,0,2,1,0,24,0,14,0,25,0,3,0,22,0,120,0,14,0,32,0,30,0,33,0,23,0,3,0,25,0,120,0,14,0,23,0,14,0,122,0,26,0,121,0,14,0,26,0,3,0,109,0,24,0,24,0,120,0,14,0,122,0,3,0,35,0,121,0,14,0,109,0,14,0,127,0,120,0,14,0,41,0,14,0,20,0,121,0,33,0,3,0,15,0,21,0,121,0,14,0,122,0,24,0,29,0,33,0,122,0,32,0,121,0,21,0,3,0,109,0,120,0,14,0,33,0,3,0,17,0,14,0,25,0,120,0,14,0,30,0,21,0,20,0,121,0,21,0,3,0,110,0,120,0,14,0,26,0,3,0,15,0,14,0,23,0,30,0,121,0,14,0,32,0,21,0,3,0,109,0,120,0,14,0,15,0,21,0,122,0,20,0,121,0,21,0,10,0,2,1,0,109,0,26,0,26,0,20,0,120,0,33,0,3,0,14,0,24,0,25,0,120,0,21,0,24,0,23,0,33,0,3,0,14,0,24,0,25,0,120,0,14,0,96,0,109,0,33,0,122,0,25,0,121,0,33,0,8,0,3,0,14,0,24,0,127,0,120,0,14,0,122,0,109,0,21,0,26,0,121,0,33,0,3,0,14,0,24,0,25,0,120,0,14,0,43,0,30,0,33,0,122,0,25,0,121,0,14,0,8,0,3,0,43,0,14,0,17,0,120,0,21,0,122,0,38,0,14,0,31,0,121,0,33,0,26,0,3,0,15,0,21,0,122,0,121,0,33,0,122,0,23,0,33,0,122,0,30,0,121,0,14,0,26,0,33,0,122,0,3,0,19,0,14,0,30,0,121,0,14,0,38,0,14,0,24,0,121,0,21,0,122,0,33,0,122,0,31,0,121,0,33,0,3,0,120,0,14,0,15,0,26,0,21,0,3,0,109,0,14,0,31,0,15,0,120,0,14,0,126,0,21,0,122,0,31,0,121,0,21,0,26,0,3,0,109,0,14,0,31,0,31,0,31,0,120,0,14,0,122,0,15,0,21,0,110,0,121,0,21,0,8,0,3,0,35,0,14,0,24,0,25,0,120,0,33,0,31,0,14,0,25,0,25,0,121,0,14,0,3,0,43,0,120,0,14,0,17,0,21,0,122,0,38,0,121,0,14,0,10,0,2],"phonemes":["ʔ","ˈ","a","u","ː","l","ˌ","u"," ","m","ˈ","i","n"," ","ʕ","ˈ","u","m","a","r","ˌ","a"," ","m","ˈ","u","m","l","l","k","a","t","ˌ","i","n"," ","ʔ","a","ː","r","ˈ","a","θ","a","n","ˌ","a",".","q","ˈ","a","t","i","l","ˌ","a"," ","ʔ","ˈ","a","b","a","ː","h","ˌ","u"," ","l","i","ː","ˌ","a","ħ","k","u","m","ˌ","a"," ","m","ˌ","u","m","l","a","k","ˈ","a","t","a","h","ˌ","u",".","χ","ˈ","a","ː","n"," ","m","u","m","l","ˈ","i","k","a","t","ˌ","a","n"," ","k","a","ː","n","ˌ","a","t"," ","ʔ","ˈ","a","k","θ","a","r","ˌ","u"," ","a","l","ħ","u","l","ˈ","a","f","a","ː","ʔ","ˌ","i"," ","ʔ","χ","l","ˈ","a","ː","s","̪","a","n"," ","f","i","ː"," ","ʕ","ˈ","a","h","d","i"," ","ʔ","ˈ","a","b","i","ː","h","ˌ","i",".","ħ","ˈ","a","u","l","ˌ","a"," ","n","ˈ","a","f","s","i","h","ˌ","i"," ","ʔ","l","ˈ","a","ː"," ","t","ˈ","a","n","i","ː","n","ˌ","i","n"," ","w","a","t","ˈ","u","χ","a","l","l","ˌ","a"," ","ʕ","ˈ","a","n"," ","ʕ","a","ː","l","ˈ","i","m","i","h","ˌ","i"," ","l","a","ˌ","i","u","ʕ","ˌ","a","l","a","n","ˌ","a"," ","a","l","ħ","ˈ","a","r","b","a"," ","ʕ","ˈ","a","l","a","ː"," ","s","u","k","ː","ˌ","a","ː","n","i"," ","a","l","ʕ","ˈ","a","ː","l","i","m","ˌ","i"," ","a","l","l","ð","ˈ","i","ː"," ","l","a","d","ʒ","ˌ","a","ʔ","a"," ","ʔ","l","ˈ","a","i","h","ˌ","i",".","l","a","m"," ","j","ˈ","a","t","r","u","k"," ","m","ˈ","a","k","a","ː","n","ˌ","a","n"," ","ʔ","l","l","ˈ","a","ː"," ","w","ˌ","a","ʔ","a","χ","ˈ","a","ð","a","h","ˌ","u"," ","b","i","ˌ","a","ː","l","q","u","ː","t","ˌ","i"," ","ʔ","ˈ","a","u"," ","d","a","m","ˈ","a","r","i","h","ˌ","i"," ","ʕ","ˈ","a","n"," ","b","a","k","r","ˌ","a","t","i"," ","ʔ","ˈ","a","b","i","ː","h","ˌ","i",".","ʔ","n","n","h","ˈ","u"," ","a","l","m","ˈ","i","l","k","u"," ","a","l","m","ˈ","a","ʃ","ʔ","u","ː","m","ˌ","u",","," ","a","l","χ","ˈ","a","ː","ʔ","i","n","ˌ","u"," ","a","l","m","ˈ","a","ħ","r","u","ː","m","ˌ","a",","," ","ħ","a","d","ˈ","i","ː","z","a","s","ˌ","u","n"," ","b","i","ː","ˌ","u","ː","k","u","ː","r","ˌ","a","n","u","ː"," ","f","a","r","ˌ","a","z","a","l","ˌ","i","ː","u","ː","s","ˌ","u"," ","ˈ","a","b","n","i"," ","ʔ","a","s","b","ˈ","a","θ","i","ː","s","ˌ","i","n"," ","ʔ","a","s","s","s","ˈ","a","ː","b","i","ʕ","ˌ","i",","," ","w","a","l","m","ˈ","u","s","a","m","m","ˌ","a"," ","ħ","ˈ","a","d","i","ː","z","ˌ","a","."],"processed_text":"أَوَّلُ مِنْ عُمَرَ مُمْلَّكَةٍ آرَثَنَ. قَتِلَ أَبَاهُ لِيَحْكُمَ مُمْلَكَتَهُ. خَانْ مُمْلِكَةًً كَانَتْ أَكْثَرُ الْحُلَفَاءِ إخْلَاصًًا فِي عَهْدِ أَبِيهِ. حَوْلَ نَفْسِهِ إلَى تَنِينٍ وَتُخَلَّى عَنْ عَالِمِهِ لَيُعَلَنَ الْحَرْبَ عَلَى سُكَّانِ الْعَالِمِ الَّذِي لَجَأَ إلَيْهِ. لَمْ يَتْرُكْ مَكَانًًا إلَّا وَأَخَذَهُ بِالْقُوَّةِ أَوْ دَمَرِهِ عَنْ بَكْرَةِ أَبِيهِ. إنَّهُ الْمِلْكُ الْمَشْؤُومُ, الْخَائِنُ الْمَحْرُومَ, حَدِيزَسٌ بِيُوكُورَنُو فَرَزَلِيُوسُ ابْنِ أَسْبَثِيسٍ السَّابِعِ, وَالْمُسَمَّى حَدِيزَ.","text":"أَوَّلُ مَنْ عَمَّرَ مَمْلَكَةَ آرْثِنْ. قَتَل أَباهُ لِيَحْكُمَ مَمْلَكَتَهْ. خَانَ مَمْلَكَةً كانَتْ أَكْثَرَ الْحُلَفَاءِ إِخْلَاصًا فِي عَهْدِ أَبِيهْ. حَوَّلَ نَفْسَهُ إِلَى تِنِّينٍ وَتَخَلى عَنْ عَالَمِهِ لِيُعْلِنَ الْحَرْبَ عَلَى سُكّانِ الْعَالَمِ الَّذِي لَجَأَ إِلَيْهْ. لَمْ يَتْرُكْ مَكَانًا إِلَّا وَأَخَذَهُ بِالْقُوَّةِ أَو دَمّرهُ عَنْ بَكْرَةِ أَبِيهْ. إِنَّهُ الْمَلك الْمَشْؤُومْ, الْخَائِنُ الْمَحْرُومْ, حَدِيزُسْ بْيُوكُورْنُو فْرِزِلْيُوسْ اِبْنُ أَسْبُثْيُسْ السَّابِعْ, وَالْمُسَمَّى حَدِيزْ."} +{"phoneme_ids":[1,0,29,0,120,0,14,0,33,0,31,0,121,0,33,0,26,0,3,0,29,0,120,0,14,0,38,0,14,0,43,0,121,0,21,0,26,0,3,0,22,0,120,0,33,0,31,0,14,0,25,0,25,0,121,0,14,0,3,0,23,0,14,0,41,0,121,0,14,0,24,0,21,0,23,0,121,0,14,0,3,0,29,0,120,0,14,0,33,0,31,0,121,0,33,0,3,0,14,0,24,0,25,0,120,0,14,0,32,0,142,0,14,0,10,0,30,0,121,0,21,0,3,0,109,0,120,0,14,0,33,0,3,0,29,0,120,0,14,0,33,0,31,0,121,0,21,0,3,0,14,0,24,0,109,0,120,0,14,0,24,0,35,0,14,0,122,0,26,0,121,0,21,0,3,0,35,0,120,0,14,0,20,0,33,0,122,0,121,0,14,0,3,0,41,0,14,0,10,0,122,0,20,0,120,0,21,0,30,0,14,0,32,0,121,0,33,0,26,0,3,0,32,0,142,0,14,0,10,0,15,0,120,0,21,0,122,0,110,0,21,0,122,0,32,0,121,0,33,0,26,0,3,0,19,0,14,0,121,0,21,0,14,0,38,0,22,0,121,0,14,0,122,0,109,0,21,0,122,0,32,0,121,0,33,0,26,0,3,0,26,0,14,0,122,0,32,0,120,0,21,0,17,0,108,0,14,0,32,0,121,0,33,0,26,0,3,0,110,0,120,0,14,0,26,0,3,0,14,0,26,0,23,0,120,0,21,0,31,0,14,0,122,0,30,0,121,0,21,0,26,0,3,0,35,0,14,0,32,0,120,0,14,0,43,0,14,0,24,0,24,0,24,0,121,0,33,0,3,0,17,0,146,0,120,0,14,0,10,0,33,0,10,0,109,0,121,0,33,0,26,0,2],"phonemes":["q","ˈ","a","u","s","ˌ","u","n"," ","q","ˈ","a","z","a","ħ","ˌ","i","n"," ","j","ˈ","u","s","a","m","m","ˌ","a"," ","k","a","ð","ˌ","a","l","i","k","ˌ","a"," ","q","ˈ","a","u","s","ˌ","u"," ","a","l","m","ˈ","a","t","̪","a",".","r","ˌ","i"," ","ʔ","ˈ","a","u"," ","q","ˈ","a","u","s","ˌ","i"," ","a","l","ʔ","ˈ","a","l","w","a","ː","n","ˌ","i"," ","w","ˈ","a","h","u","ː","ˌ","a"," ","ð","a",".","ː","h","ˈ","i","r","a","t","ˌ","u","n"," ","t","̪","a",".","b","ˈ","i","ː","ʕ","i","ː","t","ˌ","u","n"," ","f","a","ˌ","i","a","z","j","ˌ","a","ː","ʔ","i","ː","t","ˌ","u","n"," ","n","a","ː","t","ˈ","i","d","ʒ","a","t","ˌ","u","n"," ","ʕ","ˈ","a","n"," ","a","n","k","ˈ","i","s","a","ː","r","ˌ","i","n"," ","w","a","t","ˈ","a","ħ","a","l","l","l","ˌ","u"," ","d","ˤ","ˈ","a",".","u",".","ʔ","ˌ","u","n"],"processed_text":"قَوْسٌ قَزَحٍ يُسَمَّى كَذَلِكَ قَوْسُ الْمَطَرِ أَوْ قَوْسِ الْأَلْوَانِ وَهُوَ ظَاهِرَةٌ طَبِيعِيَّةٌ فَيَزْيَائِيَّةٌ نَاتِجَةٌ عَنْ انْكِسَارٍ وَتَحَلَّلُ ضَوْءٌ","text":"قَوْسُ قُزح يسمى كذلك قوس المطر أو قوس الألوان وهو ظاهرة طبيعية فيزيائية ناتجة عن انكسار وتحلل ضوء"} +{"phoneme_ids":[1,0,109,0,14,0,96,0,96,0,25,0,31,0,120,0,33,0,3,0,127,0,120,0,21,0,24,0,14,0,122,0,24,0,121,0,33,0,26,0,3,0,29,0,120,0,14,0,32,0,142,0,30,0,14,0,32,0,121,0,21,0,3,0,25,0,120,0,14,0,122,0,109,0,21,0,3,0,14,0,24,0,25,0,120,0,14,0,32,0,142,0,14,0,10,0,30,0,121,0,14,0,8,0,3,0,22,0,120,0,14,0,41,0,20,0,14,0,30,0,121,0,33,0,3,0,29,0,120,0,14,0,33,0,31,0,121,0,33,0,3,0,14,0,24,0,25,0,120,0,14,0,32,0,142,0,14,0,10,0,30,0,121,0,21,0,3,0,15,0,14,0,110,0,17,0,121,0,14,0,3,0,31,0,33,0,29,0,121,0,33,0,122,0,32,0,142,0,21,0,10,0,3,0,14,0,24,0,25,0,120,0,14,0,32,0,142,0,14,0,10,0,30,0,121,0,21,0,3,0,109,0,120,0,14,0,33,0,3,0,127,0,120,0,21,0,24,0,14,0,122,0,24,0,121,0,21,0,3,0,31,0,33,0,29,0,121,0,33,0,122,0,32,0,142,0,21,0,10,0,3,0,14,0,24,0,25,0,120,0,14,0,32,0,142,0,14,0,10,0,30,0,121,0,21,0,3,0,35,0,14,0,96,0,96,0,25,0,31,0,120,0,21,0,3,0,25,0,33,0,96,0,30,0,120,0,21,0,29,0,14,0,32,0,121,0,14,0,26,0,8,0,3,0,32,0,120,0,14,0,23,0,33,0,122,0,26,0,121,0,33,0,2],"phonemes":["ʔ","a","ʃ","ʃ","m","s","ˈ","u"," ","χ","ˈ","i","l","a","ː","l","ˌ","u","n"," ","q","ˈ","a","t","̪","r","a","t","ˌ","i"," ","m","ˈ","a","ː","ʔ","i"," ","a","l","m","ˈ","a","t","̪","a",".","r","ˌ","a",","," ","j","ˈ","a","ð","h","a","r","ˌ","u"," ","q","ˈ","a","u","s","ˌ","u"," ","a","l","m","ˈ","a","t","̪","a",".","r","ˌ","i"," ","b","a","ʕ","d","ˌ","a"," ","s","u","q","ˌ","u","ː","t","̪","i","."," ","a","l","m","ˈ","a","t","̪","a",".","r","ˌ","i"," ","ʔ","ˈ","a","u"," ","χ","ˈ","i","l","a","ː","l","ˌ","i"," ","s","u","q","ˌ","u","ː","t","̪","i","."," ","a","l","m","ˈ","a","t","̪","a",".","r","ˌ","i"," ","w","a","ʃ","ʃ","m","s","ˈ","i"," ","m","u","ʃ","r","ˈ","i","q","a","t","ˌ","a","n",","," ","t","ˈ","a","k","u","ː","n","ˌ","u"],"processed_text":"الشَّمْسُ خِلَالٌ قَطْرَةِ مَاءِ الْمَطَرَ، يَظْهَرُ قَوْسُ الْمَطَرِ بَعْدَ سُقُوطِ الْمَطَرِ أَوْ خِلَالِ سُقُوطِ الْمَطَرِ وَالشَّمْسِ مُشْرِقَةً، تَكُونُ","text":"الشمس خلال قطرة ماء المطر، يظهر قوس المطر بعد سقوط المطر أو خلال سقوط المطر والشمس مشرقة، تكون"} +{"phoneme_ids":[1,0,14,0,24,0,109,0,120,0,14,0,24,0,35,0,14,0,122,0,26,0,121,0,21,0,3,0,19,0,21,0,122,0,3,0,14,0,24,0,29,0,120,0,14,0,33,0,31,0,121,0,21,0,3,0,109,0,14,0,24,0,24,0,24,0,35,0,26,0,120,0,33,0,3,0,14,0,24,0,109,0,120,0,14,0,43,0,25,0,14,0,30,0,121,0,33,0,3,0,25,0,120,0,21,0,26,0,3,0,14,0,24,0,127,0,120,0,14,0,122,0,30,0,21,0,17,0,108,0,121,0,21,0,3,0,35,0,121,0,14,0,21,0,14,0,32,0,120,0,14,0,17,0,14,0,30,0,30,0,17,0,108,0,121,0,33,0,3,0,109,0,24,0,120,0,14,0,122,0,3,0,14,0,24,0,15,0,33,0,30,0,32,0,120,0,14,0,29,0,14,0,122,0,24,0,121,0,21,0,122,0,3,0,19,0,14,0,24,0,109,0,120,0,14,0,31,0,142,0,19,0,14,0,30,0,121,0,33,0,3,0,19,0,14,0,24,0,109,0,120,0,14,0,127,0,17,0,146,0,14,0,10,0,30,0,121,0,33,0,3,0,19,0,14,0,24,0,109,0,120,0,14,0,38,0,30,0,14,0,29,0,121,0,33,0,3,0,19,0,14,0,109,0,121,0,14,0,38,0,30,0,14,0,29,0,121,0,14,0,3,0,68,0,120,0,14,0,122,0,25,0,21,0,29,0,121,0,33,0,26,0,3,0,26,0,120,0,21,0,122,0,24,0,21,0,122,0,2],"phonemes":["a","l","ʔ","ˈ","a","l","w","a","ː","n","ˌ","i"," ","f","i","ː"," ","a","l","q","ˈ","a","u","s","ˌ","i"," ","ʔ","a","l","l","l","w","n","ˈ","u"," ","a","l","ʔ","ˈ","a","ħ","m","a","r","ˌ","u"," ","m","ˈ","i","n"," ","a","l","χ","ˈ","a","ː","r","i","d","ʒ","ˌ","i"," ","w","ˌ","a","i","a","t","ˈ","a","d","a","r","r","d","ʒ","ˌ","u"," ","ʔ","l","ˈ","a","ː"," ","a","l","b","u","r","t","ˈ","a","q","a","ː","l","ˌ","i","ː"," ","f","a","l","ʔ","ˈ","a","s","̪","f","a","r","ˌ","u"," ","f","a","l","ʔ","ˈ","a","χ","d","ˤ","a",".","r","ˌ","u"," ","f","a","l","ʔ","ˈ","a","z","r","a","q","ˌ","u"," ","f","a","ʔ","ˌ","a","z","r","a","q","ˌ","a"," ","ɣ","ˈ","a","ː","m","i","q","ˌ","u","n"," ","n","ˈ","i","ː","l","i","ː"],"processed_text":"الْأَلْوَانِ فِي الْقَوْسِ اللَّوْنُ الْأَحْمَرُ مِنْ الْخَارِجِ وَيَتَدَرَّجُ إلَى الْبُرْتَقَالِيِّ فَالْأَصْفَرُ فَالْأَخْضَرُ فَالْأَزْرَقُ فَأَزْرَقَ غَامِقٌ (نِيلِي)","text":"الألوان في القوس اللون الأحمر من الخارج ويتدرج إلى البرتقالي فالأصفر فالأخضر فالأزرق فأزرق غامق (نيلي)"} +{"phoneme_ids":[1,0,19,0,14,0,15,0,121,0,21,0,26,0,14,0,19,0,31,0,121,0,14,0,17,0,108,0,21,0,122,0,3,0,25,0,120,0,21,0,26,0,3,0,109,0,14,0,17,0,17,0,122,0,120,0,14,0,122,0,127,0,21,0,24,0,121,0,21,0,8,0,3,0,17,0,146,0,120,0,14,0,10,0,33,0,10,0,109,0,121,0,33,0,3,0,109,0,14,0,96,0,96,0,25,0,31,0,120,0,21,0,3,0,22,0,14,0,43,0,32,0,120,0,14,0,33,0,121,0,21,0,122,0,3,0,110,0,120,0,14,0,24,0,14,0,122,0,3,0,14,0,24,0,110,0,120,0,14,0,17,0,21,0,122,0,17,0,121,0,21,0,3,0,25,0,120,0,21,0,26,0,3,0,14,0,24,0,109,0,120,0,14,0,24,0,35,0,14,0,122,0,26,0,121,0,21,0,3,0,109,0,14,0,32,0,142,0,122,0,22,0,19,0,120,0,21,0,122,0,32,0,21,0,3,0,35,0,120,0,14,0,20,0,21,0,122,0,121,0,14,0,3,0,110,0,21,0,15,0,120,0,14,0,122,0,30,0,14,0,32,0,121,0,33,0,26,0,3,0,110,0,120,0,14,0,26,0,3,0,109,0,120,0,14,0,96,0,110,0,14,0,32,0,121,0,21,0,3,0,41,0,120,0,14,0,122,0,32,0,21,0,3,0,109,0,120,0,14,0,32,0,142,0,35,0,14,0,122,0,24,0,121,0,21,0,26,0,3,0,25,0,33,0,122,0,17,0,108,0,120,0,21,0,122,0,14,0,32,0,121,0,21,0,26,0,2],"phonemes":["f","a","b","ˌ","i","n","a","f","s","ˌ","a","d","ʒ","i","ː"," ","m","ˈ","i","n"," ","ʔ","a","d","d","ː","ˈ","a","ː","χ","i","l","ˌ","i",","," ","d","ˤ","ˈ","a",".","u",".","ʔ","ˌ","u"," ","ʔ","a","ʃ","ʃ","m","s","ˈ","i"," ","j","a","ħ","t","ˈ","a","u","ˌ","i","ː"," ","ʕ","ˈ","a","l","a","ː"," ","a","l","ʕ","ˈ","a","d","i","ː","d","ˌ","i"," ","m","ˈ","i","n"," ","a","l","ʔ","ˈ","a","l","w","a","ː","n","ˌ","i"," ","ʔ","a","t","̪","ː","j","f","ˈ","i","ː","t","i"," ","w","ˈ","a","h","i","ː","ˌ","a"," ","ʕ","i","b","ˈ","a","ː","r","a","t","ˌ","u","n"," ","ʕ","ˈ","a","n"," ","ʔ","ˈ","a","ʃ","ʕ","a","t","ˌ","i"," ","ð","ˈ","a","ː","t","i"," ","ʔ","ˈ","a","t","̪","w","a","ː","l","ˌ","i","n"," ","m","u","ː","d","ʒ","ˈ","i","ː","a","t","ˌ","i","n"],"processed_text":"فَبِنَفْسَجِي مِنْ الدَّاخِلِ، ضَوْءُ الشَّمْسِ يَحْتَوِي عَلَى الْعَدِيدِ مِنْ الْأَلْوَانِ الطَّيْفِيَّةِ وَهِيَ عِبَارَةٌ عَنْ أَشْعَةِ ذَاتِ أَطْوَالٍ مُوْجِيَةٍ","text":"فبنفسجي من الداخل، ضوء الشمس يحتوي على العديد من الألوان الطيفية وهي عبارة عن أشعة ذات أطوال موجية"} +{"phoneme_ids":[1,0,25,0,121,0,33,0,127,0,32,0,14,0,24,0,120,0,21,0,19,0,14,0,32,0,121,0,33,0,26,0,8,0,3,0,22,0,120,0,14,0,41,0,20,0,14,0,30,0,121,0,33,0,3,0,29,0,120,0,14,0,33,0,31,0,121,0,33,0,3,0,14,0,24,0,29,0,120,0,14,0,38,0,43,0,21,0,3,0,110,0,120,0,14,0,122,0,17,0,14,0,32,0,121,0,14,0,26,0,3,0,15,0,21,0,96,0,121,0,14,0,23,0,24,0,21,0,3,0,26,0,120,0,21,0,31,0,142,0,19,0,21,0,3,0,17,0,120,0,14,0,122,0,109,0,21,0,30,0,121,0,21,0,122,0,3,0,35,0,120,0,14,0,19,0,21,0,122,0,3,0,43,0,120,0,14,0,122,0,24,0,14,0,122,0,32,0,121,0,21,0,26,0,3,0,26,0,14,0,122,0,17,0,120,0,21,0,30,0,14,0,32,0,121,0,21,0,26,0,3,0,22,0,120,0,14,0,23,0,33,0,122,0,26,0,121,0,33,0,3,0,29,0,120,0,14,0,25,0,30,0,21,0,122,0,121,0,14,0,122,0,3,0,43,0,120,0,14,0,21,0,126,0,121,0,33,0,3,0,22,0,120,0,14,0,23,0,33,0,122,0,26,0,121,0,33,0,3,0,14,0,26,0,23,0,120,0,21,0,31,0,14,0,122,0,30,0,121,0,33,0,3,0,17,0,146,0,120,0,14,0,10,0,33,0,10,0,109,0,121,0,21,0,3,0,14,0,24,0,29,0,120,0,14,0,25,0,14,0,30,0,121,0,21,0,2],"phonemes":["m","ˌ","u","χ","t","a","l","ˈ","i","f","a","t","ˌ","u","n",","," ","j","ˈ","a","ð","h","a","r","ˌ","u"," ","q","ˈ","a","u","s","ˌ","u"," ","a","l","q","ˈ","a","z","ħ","i"," ","ʕ","ˈ","a","ː","d","a","t","ˌ","a","n"," ","b","i","ʃ","ˌ","a","k","l","i"," ","n","ˈ","i","s","̪","f","i"," ","d","ˈ","a","ː","ʔ","i","r","ˌ","i","ː"," ","w","ˈ","a","f","i","ː"," ","ħ","ˈ","a","ː","l","a","ː","t","ˌ","i","n"," ","n","a","ː","d","ˈ","i","r","a","t","ˌ","i","n"," ","j","ˈ","a","k","u","ː","n","ˌ","u"," ","q","ˈ","a","m","r","i","ː","ˌ","a","ː"," ","ħ","ˈ","a","i","θ","ˌ","u"," ","j","ˈ","a","k","u","ː","n","ˌ","u"," ","a","n","k","ˈ","i","s","a","ː","r","ˌ","u"," ","d","ˤ","ˈ","a",".","u",".","ʔ","ˌ","i"," ","a","l","q","ˈ","a","m","a","r","ˌ","i"],"processed_text":"مُخْتَلِفَةٌ، يَظْهَرُ قَوْسُ الْقَزْحِ عَادَةً بِشَكْلِ نِصْفِ دَائِرِيٍّ وَفِي حَالَاتٍ نَادِرَةٍ يَكُونُ قَمْرِيًّاً حَيْثُ يَكُونُ انْكِسَارُ ضَوْءِ الْقَمَرِ","text":"مختلفة، يظهر قوس القزح عادة بشكل نصف دائري وفي حالات نادرة يكون قمرياً حيث يكون انكسار ضوء القمر"} +{"phoneme_ids":[1,0,14,0,24,0,25,0,120,0,33,0,31,0,14,0,15,0,122,0,15,0,121,0,33,0,3,0,24,0,14,0,20,0,121,0,33,0,3,0,110,0,120,0,14,0,15,0,122,0,30,0,33,0,3,0,29,0,120,0,14,0,32,0,142,0,30,0,14,0,32,0,121,0,21,0,3,0,14,0,24,0,25,0,120,0,14,0,122,0,109,0,21,0,3,0,25,0,33,0,24,0,120,0,14,0,122,0,109,0,21,0,25,0,121,0,14,0,122,0,3,0,25,0,120,0,14,0,110,0,14,0,3,0,25,0,120,0,14,0,23,0,14,0,122,0,26,0,121,0,21,0,3,0,35,0,120,0,33,0,17,0,108,0,33,0,122,0,17,0,121,0,21,0,3,0,14,0,24,0,29,0,120,0,14,0,25,0,14,0,30,0,121,0,21,0,3,0,19,0,21,0,122,0,3,0,32,0,120,0,21,0,24,0,23,0,14,0,3,0,109,0,14,0,24,0,24,0,24,0,43,0,120,0,14,0,41,0,14,0,10,0,122,0,32,0,121,0,21,0,10,0,2,1,0,35,0,121,0,14,0,21,0,120,0,14,0,41,0,20,0,14,0,30,0,121,0,33,0,3,0,24,0,21,0,24,0,25,0,121,0,33,0,96,0,14,0,122,0,20,0,121,0,14,0,17,0,21,0,3,0,26,0,14,0,32,0,120,0,21,0,122,0,17,0,108,0,14,0,32,0,121,0,33,0,26,0,3,0,24,0,21,0,17,0,146,0,121,0,14,0,10,0,33,0,10,0,109,0,121,0,21,0,20,0,21,0,3,0,14,0,24,0,127,0,120,0,14,0,122,0,19,0,14,0,32,0,121,0,33,0,3,0,109,0,120,0,14,0,15,0,22,0,14,0,17,0,146,0,121,0,14,0,10,0,2],"phonemes":["a","l","m","ˈ","u","s","a","b","ː","b","ˌ","u"," ","l","a","h","ˌ","u"," ","ʕ","ˈ","a","b","ː","r","u"," ","q","ˈ","a","t","̪","r","a","t","ˌ","i"," ","a","l","m","ˈ","a","ː","ʔ","i"," ","m","u","l","ˈ","a","ː","ʔ","i","m","ˌ","a","ː"," ","m","ˈ","a","ʕ","a"," ","m","ˈ","a","k","a","ː","n","ˌ","i"," ","w","ˈ","u","d","ʒ","u","ː","d","ˌ","i"," ","a","l","q","ˈ","a","m","a","r","ˌ","i"," ","f","i","ː"," ","t","ˈ","i","l","k","a"," ","ʔ","a","l","l","l","ħ","ˈ","a","ð","a",".","ː","t","ˌ","i",".","w","ˌ","a","i","ˈ","a","ð","h","a","r","ˌ","u"," ","l","i","l","m","ˌ","u","ʃ","a","ː","h","ˌ","a","d","i"," ","n","a","t","ˈ","i","ː","d","ʒ","a","t","ˌ","u","n"," ","l","i","d","ˤ","ˌ","a",".","u",".","ʔ","ˌ","i","h","i"," ","a","l","χ","ˈ","a","ː","f","a","t","ˌ","u"," ","ʔ","ˈ","a","b","j","a","d","ˤ","ˌ","a","."],"processed_text":"الْمُسَبَّبُ لَهُ عَبَّرُ قَطْرَةِ الْمَاءِ مُلَائِمًاً مَعَ مَكَانِ وُجُودِ الْقَمَرِ فِي تِلْكَ اللَّحَظَاتِ. وَيَظْهَرُ لِلْمُشَاهَدِ نَتِيجَةٌ لِضَوْئِهِ الْخَافَتُ أَبْيَضَ","text":"المسبب لهُ عبر قطرة الماء ملائماً مع مكان وجود القمر في تلك اللحظات. ويظهر للمشاهد نتيجة لضوئهِ الخافت أبيض"} +{"phoneme_ids":[1,0,24,0,21,0,109,0,121,0,14,0,26,0,26,0,3,0,14,0,24,0,110,0,120,0,14,0,21,0,26,0,121,0,14,0,3,0,14,0,24,0,15,0,14,0,96,0,120,0,14,0,30,0,21,0,122,0,32,0,121,0,14,0,3,0,24,0,14,0,122,0,3,0,32,0,14,0,31,0,32,0,120,0,14,0,32,0,142,0,21,0,10,0,122,0,110,0,121,0,33,0,3,0,109,0,120,0,14,0,26,0,3,0,32,0,120,0,14,0,30,0,14,0,122,0,3,0,14,0,24,0,109,0,120,0,14,0,24,0,35,0,14,0,122,0,26,0,121,0,21,0,3,0,19,0,21,0,122,0,3,0,109,0,14,0,24,0,24,0,24,0,22,0,24,0,120,0,21,0,10,0,2],"phonemes":["l","i","ʔ","ˌ","a","n","n"," ","a","l","ʕ","ˈ","a","i","n","ˌ","a"," ","a","l","b","a","ʃ","ˈ","a","r","i","ː","t","ˌ","a"," ","l","a","ː"," ","t","a","s","t","ˈ","a","t","̪","i",".","ː","ʕ","ˌ","u"," ","ʔ","ˈ","a","n"," ","t","ˈ","a","r","a","ː"," ","a","l","ʔ","ˈ","a","l","w","a","ː","n","ˌ","i"," ","f","i","ː"," ","ʔ","a","l","l","l","j","l","ˈ","i","."],"processed_text":"لِأَنَّ الْعَيْنَ الْبَشَرِيَّةَ لَا تَسْتَطِيعُ أَنْ تَرَى الْأَلْوَانِ فِي اللَّيْلِ.","text":"لأن العين البشرية لا تستطيع أن ترى الألوان في الليل."} diff --git a/etc/test_voice.onnx b/etc/test_voice.onnx new file mode 100644 index 0000000..575e2f0 Binary files /dev/null and b/etc/test_voice.onnx differ diff --git a/etc/test_voice.onnx.json b/etc/test_voice.onnx.json new file mode 100644 index 0000000..d64db2e --- /dev/null +++ b/etc/test_voice.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file