Auto-Synced-Translated-Dubs icon indicating copy to clipboard operation
Auto-Synced-Translated-Dubs copied to clipboard

Can someone tell me why can't I run multiple languages separated by a comma? I can only run one language at a time

Open TharunDharmaraj opened this issue 2 years ago • 6 comments

----- Beginning Processing of Language: nl-NL ----- Translating text...

Trimmed Audio: 90 of 90

Calculated Speed Factor: 90 of 90

Trimmed Audio (2nd Pass): 90 of 90

Final Audio Processed: 90 of 90

----- Beginning Processing of Language: th-TH ----- Translating text... Traceback (most recent call last): File "c:\Users\tharu\AndroidStudioProjects\Auto-Synced-Translated-Dubs\main.py", line 350, in individualLanguageSubsDict = translate_dictionary(individualLanguageSubsDict, langDict, skipTranslation=skipTranslation) File "c:\Users\tharu\AndroidStudioProjects\Auto-Synced-Translated-Dubs\main.py", line 282, in translate_dictionary response = auth.TRANSLATE_API.projects().translateText( File "C:\Users\tharu\AppData\Roaming\Python\Python39\site-packages\googleapiclient_helpers.py", line 130, in positional_wrapper return wrapped(*args, **kwargs) File "C:\Users\tharu\AppData\Roaming\Python\Python39\site-packages\googleapiclient\http.py", line 923, in execute resp, content = _retry_request( File "C:\Users\tharu\AppData\Roaming\Python\Python39\site-packages\googleapiclient\http.py", line 222, in _retry_request raise exception File "C:\Users\tharu\AppData\Roaming\Python\Python39\site-packages\googleapiclient\http.py", line 191, in retry_request resp, content = http.request(uri, method, *args, **kwargs) File "C:\Users\tharu\AppData\Roaming\Python\Python39\site-packages\google_auth_httplib2.py", line 218, in request response, content = self.http.request( File "C:\Users\tharu\AppData\Roaming\Python\Python39\site-packages\httplib2_init.py", line 1720, in request
(response, content) = self.request( File "C:\Users\tharu\AppData\Roaming\Python\Python39\site-packages\httplib2_init.py", line 1440, in _request
(response, content) = self.conn_request(conn, request_uri, method, body, headers) File "C:\Users\tharu\AppData\Roaming\Python\Python39\site-packages\httplib2_init.py", line 1392, in _conn_request response = conn.getresponse() ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host

TharunDharmaraj avatar Jan 02 '23 12:01 TharunDharmaraj

Hm not sure what would cause the connection issue mentioned in the last line. Especially since it only happened after the first one worked. Does this happen every time you run it?

ThioJoe avatar Jan 02 '23 15:01 ThioJoe

Hm not sure what would cause the connection issue mentioned in the last line. Especially since it only happened after the first one worked. Does this happen every time you run it?

Yes it happens everytime I run

TharunDharmaraj avatar Jan 03 '23 13:01 TharunDharmaraj

Since it seems to only happen once it starts doing Thai, can you post that language entry you have set in batch.ini? The one that looks like this, except filled in for Thai:

[LANGUAGE-12]
# 
translation_target_language = 
synth_language_code = 
synth_voice_name = 
synth_voice_gender = 

Also what happens if you set Thai as the only language to be processed, does it still do it then?

ThioJoe avatar Jan 03 '23 14:01 ThioJoe

I processed about 10 languages before thai and it processed well i got the individual combined full mp3 audi files , but from reaching thai, this error keepes showing up no matter which language i use from then...now this error keeps coming for all the languages. Even I setup the whole program once again and it keeps showing the same for all the languages. The below is the "batch.ini" file

`#neural-voices #https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/language-support?tabs=stt-tts [SETTINGS] ; 0 - English(US) ; 1 - Spanish ; 2 - Hindi ; 3 - Arabic ; 4 - Russian ; 5 - Portuguese ; 6 - Italian ; 7 - Indonesian ; 8 - Japnese ; 9 - Korean ; 10 - German ; 11 - Chinese(Mandarin) ; 12 - Turkish ; 13 - Tamil ; 14 - French ; 15 - Urdu ; 16 - DUTCH ; 17 - SWEDISH ; 18 - Telugu ; 19 - Thai ; 20 - Vietnamese ; 21 - BULGARIAN ; 22 - Danish ; 23 - Norwegian ; 24 - Croatian ; 25 - Greek ; 26 - English(GB)

enabled_languages = 19 original_video_file_path = org_video.mp4 srt_file_path = eg.srt

[LANGUAGE-0]

English / Testing

# Remember, the translation target code may be different from synth_language_code because it is the one used by the translation service, not the TTS service
# See the codes here: https://cloud.google.com/translate/docs/languages

translation_target_language = en # The language of the synthesized voice. Might not necessarily be exactly the same as target_language variable below # Examples - English: en-US Spanish: es-us or es-mx synth_language_code = en-US # Choose one from here so it matches the target language: https://cloud.google.com/text-to-speech/docs/voices / https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/language-support?tabs=stt-tts # Examples - English: en-US-Neural2-I (Google) or en-US-JasonNeural (Azure) Spanish: es-US-Neural2-B (Google) or es-MX-CecilioNeural (Azure) synth_voice_name = en-US-JasonNeural # Google Only: Should match the gender of the chosen voice above synth_voice_gender = MALE

[LANGUAGE-1]

Spanish

translation_target_language = es synth_language_code = es-MX synth_voice_name = es-MX-CecilioNeural synth_voice_gender = MALE

[LANGUAGE-2]

Hindi

translation_target_language = hi synth_language_code = hi-IN synth_voice_name = hi-IN-MadhurNeural synth_voice_gender = MALE

[LANGUAGE-3]

Arabic

translation_target_language = ar synth_language_code = ar-EG synth_voice_name = ar-EG-ShakirNeural synth_voice_gender = MALE

[LANGUAGE-4]

Russian

translation_target_language = ru synth_language_code = ru-RU synth_voice_name = ru-RU-DmitryNeural synth_voice_gender = MALE

[LANGUAGE-5]

Portuguese

translation_target_language = pt synth_language_code = pt-BR synth_voice_name = pt-BR-FabioNeural synth_voice_gender = MALE

[LANGUAGE-6]

Italian

translation_target_language = it synth_language_code = it-IT synth_voice_name = it-IT-DiegoNeural synth_voice_gender = MALE

[LANGUAGE-7]

Indonesian

translation_target_language = id synth_language_code = id-ID synth_voice_name = id-ID-ArdiNeural synth_voice_gender = MALE

[LANGUAGE-8]

Japanese

translation_target_language = ja synth_language_code = ja-JP synth_voice_name = ja-JP-NaokiNeural synth_voice_gender = MALE

[LANGUAGE-9]

Korean

translation_target_language = ko synth_language_code = ko-KR synth_voice_name = ko-KR-BongJinNeural synth_voice_gender = MALE

[LANGUAGE-10]

German

translation_target_language = de synth_language_code = de-DE synth_voice_name = de-DE-KasperNeural synth_voice_gender = MALE

[LANGUAGE-11]

Chinese (Mandarin Simplified)

translation_target_language = zh synth_language_code = zh-CN synth_voice_name = zh-CN-YunyeNeural synth_voice_gender = MALE

[LANGUAGE-12]

Turkish

translation_target_language = tr synth_language_code = tr-TR synth_voice_name = tr-TR-AhmetNeural synth_voice_gender = MALE

[LANGUAGE-13]

TAMIL

translation_target_language = ta synth_language_code = ta-IN synth_voice_name = ta-IN-ValluvarNeural synth_voice_gender = MALE

[LANGUAGE-14]

FRENCE

translation_target_language = fr synth_language_code = fr-FR synth_voice_name = fr-FR-ClaudeNeural synth_voice_gender = MALE

[LANGUAGE-15]

URDU

translation_target_language = ur synth_language_code = ur-PK synth_voice_name = ur-PK-AsadNeural synth_voice_gender = MALE

[LANGUAGE-16]

DUTCH

translation_target_language = nl synth_language_code = nl-NL synth_voice_name = nl-NL-MaartenNeural synth_voice_gender = MALE

[LANGUAGE-17]

SWEDISH

translation_target_language = sv synth_language_code = sv-SE synth_voice_name = sv-SE-MattiasNeural synth_voice_gender = MALE

[LANGUAGE-18]

TELUGU

translation_target_language = te synth_language_code = te-IN synth_voice_name = te-IN-MohanNeural synth_voice_gender = MALE

[LANGUAGE-19]

THAI

translation_target_language = th synth_language_code = th-TH synth_voice_name = th-TH-NiwatNeural synth_voice_gender = MALE

[LANGUAGE-20]

VIETNAMESE

translation_target_language = vi synth_language_code = vi-VN synth_voice_name = vi-VN-NamMinhNeural synth_voice_gender = MALE

[LANGUAGE-21]

BULGARIAN

translation_target_language = bg synth_language_code = bg-BG synth_voice_name = bg-BG-BorislavNeural synth_voice_gender = MALE

[LANGUAGE-22]

DANISH

translation_target_language = da synth_language_code = da synth_voice_name = da-DK-JeppeNeural synth_voice_gender = MALE

[LANGUAGE-23]

NORWEGIAN

translation_target_language = nb synth_language_code = nb-NO synth_voice_name = nb-NO-FinnNeural synth_voice_gender = MALE

[LANGUAGE-24]

CROATIAN

translation_target_language = hr synth_language_code = hr-HR synth_voice_name = hr-HR-SreckoNeural synth_voice_gender = MALE

[LANGUAGE-25]

GREEK

translation_target_language = el synth_language_code = el-GR synth_voice_name = el-GR-NestorasNeural synth_voice_gender = MALE

[LANGUAGE-26]

translation_target_language = en synth_language_code = en-GB synth_voice_name = en-GB-AlfieNeural synth_voice_gender = MALE ` And it generates the translated srt file and all the mp3 files of that translated srt file in the working folder, but any of them cant be played. It shows that**"an error occured during opeing the file"**. I think these mp3 files cannot be read by the program.It cannot be even read by my system mp3 player. and if there is some way that can you suggest for me to correct it, as it was all working fine but suddenly it stared throwing this error and I even redone the setup but it keeps throwing the same. Pls suggest me some ways regarding this error.

I even tried Spanish, which worked at first time, but now the separate audios from the working folder can't be opened/played for any language.

Thank You

TharunDharmaraj avatar Jan 03 '23 18:01 TharunDharmaraj

Hi! Are you using the setting batch_tts_synthesize = False and tts_service = azure under cloud_service_settings.ini?

If yes, are you using the most recent version of the software? There was a bug patch regarding these specific settings causing unplayable audio files, and it seems related to me, but could you please verify that?

sofiadparamo avatar Jan 04 '23 03:01 sofiadparamo

Yeah, it said that batch synthesis is available only for Standard azure users. As I have a azure student plan, batch synthesis is set to false also I am using azure for text to speech. And yes, I am using the most recent one...just installed before a couple of days

TharunDharmaraj avatar Jan 04 '23 09:01 TharunDharmaraj

Worked at the stable version 0.8.0

TharunDharmaraj avatar Jan 07 '23 14:01 TharunDharmaraj