better time for listening

4th/create_data.py

@@ -0,0 +1,45 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Sun May 24 13:40:25 2020
+
+@author: qtckp
+"""
+
+
+import os, shutil
+import json
+import googletrans
+
+
+directory='./text_logger'
+
+def copy(filename):
+    shutil.copyfile(filename,os.path.join(directory,filename))
+
+
+if os.path.exists(directory):
+    shutil.rmtree(directory)
+
+os.makedirs(directory)
+
+
+copy('text_logger6.py')
+copy("languges_for_transcription.json")
+
+
+
+langs = {value: key for key, value in googletrans.LANGUAGES.items()}
+
+with open(os.path.join(directory,"languges.json"), "w") as write_file:
+    json.dump(langs, write_file, indent=4)
+
+
+settings = {
+    'languages':['ru','en','fa'],
+    'need_to_transcript':[True,False,True],
+    'listen_time':3,
+    'stop_word':'+'
+    }
+
+with open(os.path.join(directory,"settings.json"), "w") as write_file:
+    json.dump(settings, write_file, indent=4)

4th/epitran tables/all_supported.txt

@@ -0,0 +1,69 @@
+| aar-Latn    | Afar                    |
+| amh-Ethi    | Amharic                 |
+| ara-Arab    | Literary Arabic         |
+| aze-Cyrl    | Azerbaijani (Cyrillic)  |
+| aze-Latn    | Azerbaijani (Latin)     |
+| ben-Beng    | Bengali                 |
+| ben-Beng-red| Bengali (reduced)       |
+| cat-Latn    | Catalan                 |
+| ceb-Latn    | Cebuano                 |
+| cmn-Hans    | Mandarin (Simplified)\* |
+| cmn-Hant    | Mandarin (Traditional)\*|
+| ckb-Arab    | Sorani                  |
+| deu-Latn    | German                  |
+| deu-Latn-np | German†                 |
+| deu-Latn-nar| German (more phonetic)  |
+| eng-Latn    | English‡                |
+| fas-Arab    | Farsi (Perso-Arabic)    |
+| fra-Latn    | French                  |
+| fra-Latn-np | French†                 |
+| hau-Latn    | Hausa                   |
+| hin-Deva    | Hindi                   |
+| hun-Latn    | Hungarian               |
+| ilo-Latn    | Ilocano                 |
+| ind-Latn    | Indonesian              |
+| ita-Latn    | Italian                 |
+| jav-Latn    | Javanese                |
+| kaz-Cyrl    | Kazakh (Cyrillic)       |
+| kaz-Latn    | Kazakh (Latin)          |
+| kin-Latn    | Kinyarwanda             |
+| kir-Arab    | Kyrgyz (Perso-Arabic)   |
+| kir-Cyrl    | Kyrgyz (Cyrillic)       |
+| kir-Latn    | Kyrgyz (Latin)          |
+| kmr-Latn    | Kurmanji                |
+| lao-Laoo    | Lao                     |
+| mar-Deva    | Marathi                 |
+| mlt-Latn    | Maltese                 |
+| mya-Mymr    | Burmese                 |
+| msa-Latn    | Malay                   |
+| nld-Latn    | Dutch                   |
+| nya-Latn    | Chichewa                |
+| orm-Latn    | Oromo                   |
+| pan-Guru    | Punjabi (Eastern)       |
+| pol-Latn    | Polish                  |
+| por-Latn    | Portuguese              |
+| ron-Latn    | Romanian                |
+| rus-Cyrl    | Russian                 |
+| sna-Latn    | Shona                   |
+| som-Latn    | Somali                  |
+| spa-Latn    | Spanish                 |
+| swa-Latn    | Swahili                 |
+| swe-Latn    | Swedish                 |
+| tam-Taml    | Tamil                   |
+| tel-Telu    | Telugu                  |
+| tgk-Cyrl    | Tajik                   |
+| tgl-Latn    | Tagalog                 |
+| tha-Thai    | Thai                    |
+| tir-Ethi    | Tigrinya                |
+| tpi-Latn    | Tok Pisin               |
+| tuk-Cyrl    | Turkmen (Cyrillic)      |
+| tuk-Latn    | Turkmen (Latin)         |
+| tur-Latn    | Turkish (Latin)         |
+| ukr-Cyrl    | Ukranian                |
+| uig-Arab    | Uyghur (Perso-Arabic)   |
+| uzb-Cyrl    | Uzbek (Cyrillic)        |
+| uzb-Latn    | Uzbek (Latin)           |
+| vie-Latn    | Vietnamese              |
+| xho-Latn    | Xhosa                   |
+| yor-Latn    | Yoruba                  |
+| zul-Latn    | Zulu                    |

4th/epitran tables/create_tables.py

@@ -0,0 +1,41 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Tue May 26 13:54:12 2020
+
+@author: qtckp
+"""
+
+
+import json
+
+def to_pair(lst):
+    return lst[0], lst[1]
+
+with open('./epitran tables/all_supported.txt','r') as fl:
+    pairs = [to_pair(s[2:].split('|')) for s in fl.readlines()]
+    all_langs = {key.strip(): value.strip() for key, value in pairs}
+
+
+with open('./epitran tables/limited_supported.txt','r') as fl:
+    arr = [s.split('|')[1].strip() for s in fl.readlines()]
+
+
+for key, val in all_langs.items():
+    if key in arr:
+        all_langs[key]= (val, True)
+    else:
+        all_langs[key]= (val, False)
+
+
+
+with open("languges_for_transcription.json", "w") as write_file:
+    json.dump(all_langs, write_file, indent=4)
+
+
+
+
+
+
+
+
+

4th/epitran tables/limited_supported.txt

@@ -0,0 +1,8 @@
+| ara-Arab    | Arabic                  |
+| cat-Latn    | Catalan                 |
+| ckb-Arab    | Sorani                  |
+| fas-Arab    | Farsi (Perso-Arabic)    |
+| fra-Latn    | French                  |
+| fra-Latn-np | French†                 |
+| mya-Mymr    | Burmese                 |
+| por-Latn    | Portuguese              |