RASMUS commited on
Commit
56a3c45
1 Parent(s): ba10b90

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +96 -7
app.py CHANGED
@@ -42,20 +42,107 @@ headers = {'Authorization': os.environ['DeepL_API_KEY']}
42
  whisper_models = ["base", "small", "medium", "base.en"]
43
 
44
 
45
- source_languages = {
46
- "Arabic": "ar",
 
 
47
  "Asturian ":"st",
 
 
48
  "Belarusian":"be",
49
  "Bulgarian":"bg",
 
 
 
 
 
50
  "Czech":"cs",
 
51
  "Danish":"da",
52
  "German":"de",
53
  "Greeek":"el",
54
  "English":"en",
 
55
  "Estonian":"et",
 
 
56
  "Finnish":"fi",
57
- "Swedish": "sv",
58
- "Spanish":"es",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
  "Let the model analyze": "Let the model analyze"
60
  }
61
 
@@ -336,7 +423,8 @@ with demo:
336
  with gr.Column():
337
  gr.Markdown('''
338
  ##### Here you can start the transcription and translation process.
339
- ##### Be aware that processing will last some time. With base model it is around 3x speed
 
340
  ''')
341
  selected_source_lang.render()
342
  selected_whisper_model.render()
@@ -356,8 +444,9 @@ with demo:
356
  with gr.Row():
357
  with gr.Column():
358
  gr.Markdown('''
359
- ##### Here you will get translated transcriptions.
360
- ##### Please remember to select target language
 
361
  ##### ''')
362
  selected_translation_lang_2.render()
363
  translate_transcriptions_button = gr.Button("Step 3. Translate transcription")
 
42
  whisper_models = ["base", "small", "medium", "base.en"]
43
 
44
 
45
+ {
46
+ "Afrikaans":"af",
47
+ "Amharic":"am",
48
+ "Arabic":"ar",
49
  "Asturian ":"st",
50
+ "Azerbaijani":"az",
51
+ "Bashkir":"ba",
52
  "Belarusian":"be",
53
  "Bulgarian":"bg",
54
+ "Bengali":"bn",
55
+ "Breton":"br",
56
+ "Bosnian":"bs",
57
+ "Catalan; Valencian":"ca",
58
+ "Cebuano":"eb",
59
  "Czech":"cs",
60
+ "Welsh":"cy",
61
  "Danish":"da",
62
  "German":"de",
63
  "Greeek":"el",
64
  "English":"en",
65
+ "Spanish":"es",
66
  "Estonian":"et",
67
+ "Persian":"fa",
68
+ "Fulah":"ff",
69
  "Finnish":"fi",
70
+ "French":"fr",
71
+ "Western Frisian":"fy",
72
+ "Irish":"ga",
73
+ "Gaelic; Scottish Gaelic":"gd",
74
+ "Galician":"gl",
75
+ "Gujarati":"gu",
76
+ "Hausa":"ha",
77
+ "Hebrew":"he",
78
+ "Hindi":"hi",
79
+ "Croatian":"hr",
80
+ "Haitian; Haitian Creole":"ht",
81
+ "Hungarian":"hu",
82
+ "Armenian":"hy",
83
+ "Indonesian":"id",
84
+ "Igbo":"ig",
85
+ "Iloko":"lo",
86
+ "Icelandic":"is",
87
+ "Italian":"it",
88
+ "Japanese":"ja",
89
+ "Javanese":"jv",
90
+ "Georgian":"ka",
91
+ "Kazakh":"kk",
92
+ "Central Khmer":"km",
93
+ "Kannada":"kn",
94
+ "Korean":"ko",
95
+ "Luxembourgish; Letzeburgesch":"lb",
96
+ "Ganda":"lg",
97
+ "Lingala":"ln",
98
+ "Lao":"lo",
99
+ "Lithuanian":"lt",
100
+ "Latvian":"lv",
101
+ "Malagasy":"mg",
102
+ "Macedonian":"mk",
103
+ "Malayalam":"ml",
104
+ "Mongolian":"mn",
105
+ "Marathi":"mr",
106
+ "Malay":"ms",
107
+ "Burmese":"my",
108
+ "Nepali":"ne",
109
+ "Dutch; Flemish":"nl",
110
+ "Norwegian":"no",
111
+ "Northern Sotho":"ns",
112
+ "Occitan (post 1500)":"oc",
113
+ "Oriya":"or",
114
+ "Panjabi; Punjabi":"pa",
115
+ "Polish":"pl",
116
+ "Pushto; Pashto":"ps",
117
+ "Portuguese":"pt",
118
+ "Romanian; Moldavian; Moldovan":"ro",
119
+ "Russian":"ru",
120
+ "Sindhi":"sd",
121
+ "Sinhala; Sinhalese":"si",
122
+ "Slovak":"sk",
123
+ "Slovenian":"sl",
124
+ "Somali":"so",
125
+ "Albanian":"sq",
126
+ "Serbian":"sr",
127
+ "Swati":"ss",
128
+ "Sundanese":"su",
129
+ "Swedish":"sv",
130
+ "Swahili":"sw",
131
+ "Tamil":"ta",
132
+ "Thai":"th",
133
+ "Tagalog":"tl",
134
+ "Tswana":"tn",
135
+ "Turkish":"tr",
136
+ "Ukrainian":"uk",
137
+ "Urdu":"ur",
138
+ "Uzbek":"uz",
139
+ "Vietnamese":"vi",
140
+ "Wolof":"wo",
141
+ "Xhosa":"xh",
142
+ "Yiddish":"yi",
143
+ "Yoruba":"yo",
144
+ "Chinese":"zh",
145
+ "Zulu":"zu",
146
  "Let the model analyze": "Let the model analyze"
147
  }
148
 
 
423
  with gr.Column():
424
  gr.Markdown('''
425
  ##### Here you can start the transcription and translation process.
426
+ ##### Be aware that processing will last some time. With base model it is around 3x speed
427
+ ##### Please select source language for better transcriptions. Using 'Let the model analyze' makes mistakes sometimes and may lead to bad transcriptions
428
  ''')
429
  selected_source_lang.render()
430
  selected_whisper_model.render()
 
444
  with gr.Row():
445
  with gr.Column():
446
  gr.Markdown('''
447
+ ##### PLEASE READ BELOW
448
+ ##### Here you will can translate transcriptions to 26 languages.
449
+ ##### If spoken language is not in the list, translation might not work. In this case original transcriptions are used
450
  ##### ''')
451
  selected_translation_lang_2.render()
452
  translate_transcriptions_button = gr.Button("Step 3. Translate transcription")