How to create subtitles for a scene (2024)

howto
22

Is there a way to quickly choose one source of translation so I don’t have to delete the others in each line in SubtitleEdit? For example, I would only want translations that are sourced from [claude-3-haiku]:

Original:
“[singlevad] 気持ちいい
[google] Feels good
[mergedvad] 気持ちいい [2/3, 85%]
[claude-3-haiku] Feels good.
[google] Feels good
[full] 気持ちいい
[google] Feels good”

Desired:
“Feels good.”

23

This is controlled by the WIPSrt output in the Config.json file:

    ...
    {
      "$type": "WIPSrt",
      "Description": "WIPSrt: .wip.srt",
      "Enabled": true,
      "FileSuffix": ".wip.srt",
      "TranscriptionsOrder": [
        "singlevad",
        "mergedvad",
        "*"
      ],
      "TranslationsOrder": [
        "claude-3-opus",
        "claude-3-sonnet",
        "claude-3-haiku-200k",
        "claude-3-haiku",
        "chatgpt-4",
        "mistral-large",
        "local-mistral-7b",
        "deepl",
        "deepl-files",
        "google",
        "*"
      ],
      ...

You could simplify it by removing all the transcriptionId & translationId (and the last “*”) that you don’t want to see (and then, rerun the application):

    {
      "$type": "WIPSrt",
      "Description": "WIPSrt: .wip.srt",
      "Enabled": true,
      "FileSuffix": ".wip.srt",
      "TranscriptionsOrder": [
        "mergedvad"
      ],
      "TranslationsOrder": [
        "claude-3-haiku"
      ],

In that case, you would get only:

[mergedvad] 気持ちいい [2/3, 85%]
    [claude-3-haiku] Feels good.

Right now, it’s not possible to reduce it even more (when using ‘perfect-vad/mergedvad/WIPSrt’ process, which gives the best result IMO).

At some point, I could add an option to detect if there is a single ‘choice’ for a subtitle and use it as-is (i.e. Feels good) and concatenate strings (i.e. Oh, I really like you.) if it has something like this (i.e. multiple transcriptions for a single ‘perfect-vad’ timing).:

[mergedvad,1/2] 気持ちいい
    [claude-3-haiku] Oh,
[mergedvad,2/2] 気持ちいい
    [claude-3-haiku] I really like you.

But I wouldn’t be able to simplify when a transcription overlaps multiple timings, or you would end up with 3 subtitles with the same text:

(subtitle #1)
    [mergedvad] 気持ちいい [1/3, 30%]
        [claude-3-haiku] This is a really long sentence, that overlap multiple timing and that should be split the user. 
(subtitle #2)
    [mergedvad] 気持ちいい [2/3, 36%]
        [claude-3-haiku] This is a really long sentence, that overlap multiple timing and that should be split the user. 
(subtitle #3)
    [mergedvad] 気持ちいい [3/3, 44%]
        [claude-3-haiku] This is a really long sentence, that overlap multiple timing and that should be split the user.
24

Have you tried the adobe premier pro method described in this post ( Transcribe, translate, and subtitles to most languages! (Adobe Premiere) )

Do you know how it compares to your method?

Thanks

25

Reading more on this, looks like the whisper model method is more effective
Thanks for the tutotial @Zalunda

1 Like
26

gonna sound of topic but will this work for “regular” non porn stuff or help with translations I’ve got lot of media that isnt in a language I can speak with no english subtitles

27

Yes, it could be used for transcribing/translating all types of content but the initial config that’s created when installing the application is ‘optimized’ for VR porn. The SystemPrompt/UserPrompt in the config tells the AI to play the role of a “translator specialized in adult film subtitles” with rules specific to that task. You would need to change the config to fit another domain (while keeping the rule about the format of the JSON).