You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Another feature request. I regularly have to transcribe files with different languages (without translation) and I have to start for each language another batch. It would be really useful, if one could somehow define for each file on its own the language to be used. Some thoughts:
My first idea would be to have a dropdown menu in the file list to select a language, which can differ from the standard language picked below.
The second idea is based on using a language code in the filename, e.g. file1_en.mkv and file2_de.mkv. Then Whisperer could detect by the filename suffix which language should be used instead of the predefined standard language.
A different solution would be to enable the automatic language prediction of the whisper model by not enforcing the language, but since this is not working in the const-me version, I assume you cannot enable it as well, right?
The text was updated successfully, but these errors were encountered:
Hi tigros,
Another feature request. I regularly have to transcribe files with different languages (without translation) and I have to start for each language another batch. It would be really useful, if one could somehow define for each file on its own the language to be used. Some thoughts:
My first idea would be to have a dropdown menu in the file list to select a language, which can differ from the standard language picked below.
The second idea is based on using a language code in the filename, e.g.
file1_en.mkv
andfile2_de.mkv
. Then Whisperer could detect by the filename suffix which language should be used instead of the predefined standard language.A different solution would be to enable the automatic language prediction of the whisper model by not enforcing the language, but since this is not working in the const-me version, I assume you cannot enable it as well, right?
The text was updated successfully, but these errors were encountered: