Post by AlexData-Hawkhill in Private Transcriber Pro comments

Viewing post in Private Transcriber Pro comments

Hey! Great work!
The new GPU version (v241) is waaay faster than the older (v214)
(PS: important question below the picture, so view the rest of this post)

Is it possible to have it translate to other languages than "English" ?
I assume the AI is first transcribing the audio to text in original language, then the AI translates the sentence to English also using the AI, right?

If that is the case then a dropdown list of languages the AI supports would make it possible to translate a german video into norwegian subtitles, or as now getting the german video into an english subtitle.
Can you possibly add this? Or would it be more complicated than I think?

samontab11 days ago(+1)

Hi AlexData-Hawkhill,

Yeah, the GPU enabled version is much faster. Glad you got this update.

In terms of the translation, it actually doesn't work exactly like that. The model itself basically only does transcription to the same language. The model just has a "bonus" feature that allows direct translation from audio to English, no intermediary text to translate.

Having a full translation from any language to any other language is outside the scope for this app. If there's interest, I could publish an independent app that does full translation of subtitles and text from any language to any other one, which would complement this app.

AlexData-Hawkhill11 days ago

An independent app that does full translation of subtitles and text from any language to any other one, is indeed very interesting!
It should of course have GPU support as well as CPU support.
It would be truly awesome if it could also have the support for converting .SRT into .VTT (WebVTT). That format has a header (3 lines) and all dots in the time-stamp unlike .SRT that has one comma in their timestamp. It also has the ability to place text at different positions on the screen, but the normal/default captions/subs position we're all used to is: align:middle size:95% line:95
The incrementing block-numbering before each block of "timestamp+position+text" as one has in .SRT, is optional in .VTT
Example (WebVTT) .VTT Subtitle/Captions File:

WEBVTT
Kind: captions
Language: en

00:00:00.000 --> 00:00:08.380 align:middle size:95% line:95
So how do you make a web page that looks like this where you have a video and it shows a

00:00:08.380 --> 00:00:14.680 align:middle size:95% line:95
nice picture where you can put the title of the video or information about what the video

00:00:14.680 --> 00:00:23.560 align:middle size:95% line:95
is about and it has obviously this video player which has this hamburger menu over here

So as you see, very similar to the .SRT format, but the benefit of this format is that it can be used with HTML5 players, so you can upload it directly to youtube (or other services supporting sub/caption) and on your own homepage, if you need video with subtitles.
PS: I've made a python script doing this .SRT to .VTT conversion, that i can share it with you, if need be. (not C++ code, but just as easy to read, he he)

itch.io

Viewing post in Private Transcriber Pro comments