[REL] Nie bede cie kochac (1974)

[endurro]

Like this post to see ed2k links  [67.0 Kb]

https://mega.nz/file/WRNH2CDK#7BWfF7QV2 ... XqHtd8bpvY

I have made a cosmetic correction to my subtitles.
I watched the film and checked the quality of the subtitles in the process.
I made connections between the lines. Originally, the subtitles consisted of short issues. After the merging, the display times became longer and the subtitles became more readable.

I have corrected the links in the original commentary.

[goku33]

Wow! Thanks everyone. Not sure how I missed this one when I crawled through all of deadman‘s post previously

[ghost]

WOW! Thanks for the subs. Now, we only need a good translation.

The ChatGPT app mentioned by DreamScape would be a good solution.

Even DeepL often gives you nonsense. Better than google, but far away from perfect.

[endurro]

WOW! Thanks for the subs. Now, we only need a good translation.

The ChatGPT app mentioned by DreamScape would be a good solution.

Even DeepL often gives you nonsense. Better than google, but far away from perfect.

When making this transcription, I wondered whether to insert the actual sentences spoken by the actors or perhaps not to process them for a foreign audience. So that it would be easier to translate these subtitles into other languages.
By this I mean that instead of idioms or slang I could insert their synonyms from the basics of the Polish language.

In the end, I stayed with the version of speech exactly as used by the actors.

[Night457]

In the end, I stayed with the version of speech exactly as used by the actors.

I like strict accuracy.

[endurro]

I like strict accuracy.

Ha ha.
Literal accuracy can generate comical situations after using a translator.

For example, in this film we have these lines of subtitles:

Spoiler: 748 00:58:58,574 --> 00:59:03,392 - Króle będę hodował. - Króliki? Zlituj się. 749 00:59:03,850 --> 00:59:07,371 Tak króle. A co ty wiesz o nich?

And Deepl translates it like this:

Spoiler: 748 00:58:58,574 --> 00:59:03,392 - Kings I will breed. - Rabbits? Have mercy. 749 00:59:03,850 --> 00:59:07,371 Yes kings. And what do you know about them?

Król (PL) = King (EN)
Królik (PL) = rabbit (EN)

But in this case the actor is using slang or local dialect and "król" is the equivalent of "królik" and it should be translated as "rabbit".

[pillowbaker]

Curious, endurro, is it possible that a pun is being used in this situation? Or did deepL simply misunderstand some local variation?

------

Anyways, everyone. We have endurro having quickly completing the base work. And who says will be available for any assistance needed with troublesome dialects and slang. This is a pretty prime moment. Anyone interested in picking up the project or assisting?

Give me some time, and you know, I'll be interested in working on it.

As ghost mentions, trying out the chatgpt method may be a good place to start, especially if comparing against a deepL reference.

[endurro]

As ghost mentions, trying out the chatgpt method may be a good place to start, especially if comparing against a deepL reference.

I have just compared the quality of the translation from PL to EN.

So far on a small sample of the text.

It seems that Deepl gives better translation quality than ChatGPT.

I still need to test ChatGPT when translating from EN to PL or from other languages to PL.

[Night457]

I definitely know how a literal translation can be ludicrous. I meant that I want strict accuracy in the source. Once that is tampered with, the meaning becomes corrupted.

Machines are only truly experts at machine language. Humans are needed to understand and express the intricacies of human language. Part of the fun of translation is figuring out the wordplay in an unfamiliar language. I don't think machines will get any pleasure in that.

If humans choose to sacrifice the eccentricities of their language to the demand for strict logic from their machine overlords, they are making a huge mistake.

***

The biggest criticism I have read of ChatGPT is that it is a brazen liar: it sometimes produces complete nonsense with utter conviction, and those who do not know better will find it thoroughly convincing because the results seem reasonable enough. In this case, someone who understands both Polish and English will recognize where the machine translation fails badly. If the goal is to translate a work of entertainment, then in the large scheme of things losing some accuracy to save time and effort is not such a big deal. People just need to realize that is happening, that's all. It is simply a question of whether or not a knowlegeable person is willing to put the time into correcting the idiot machine. Often they have other things they want or need to do. And I think in many cases, someone who is NOT a polyglot simply wants to get on with the job and make a subtitle that serves the purpose of expressing a meaning that is "close enough".

I think it is obvious what I consider the ideal kind of translation, but I am also a realist and accept the limitations of available time, energy, and human knowledge. I do not even understand much of what exactly people are going on about in my own language, so I will not stress too much if I don't fully understand what is being said in other languages too. I just will try and not get in any fistfights over those misunderstandings, and everything will be fine.

[DreamScape]

The biggest criticism I have read of ChatGPT is that it is a brazen liar: it sometimes produces complete nonsense with utter conviction, and those who do not know better will find it thoroughly convincing because the results seem reasonable enough. In this case, someone who understands both Polish and English will recognize where the machine translation fails badly. If the goal is to translate a work of entertainment, then in the large scheme of things losing some accuracy to save time and effort is not such a big deal. People just need to realize that is happening, that's all. It is simply a question of whether or not a knowlegeable person is willing to put the time into correcting the idiot machine. Often they have other things they want or need to do. And I think in many cases, someone who is NOT a polyglot simply wants to get on with the job and make a subtitle that serves the purpose of expressing a meaning that is "close enough".

I think it is obvious what I consider the ideal kind of translation, but I am also a realist and accept the limitations of available time, energy, and human knowledge. I do not even understand much of what exactly people are going on about in my own language, so I will not stress too much if I don't fully understand what is being said in other languages too. I just will try and not get in any fistfights over those misunderstandings, and everything will be fine.

Here is a fun thing that happened to me. I told ChatGPT to translate a Russian subtitle to English. However, I did not realize the Russian subtitle was saved with an improper encoding. As a result, ChatGPT was sent an unreadable file to translate. And translate it did! It just pulled 90 minutes of dialog directly from its ass - it made up every single damn line from nothing.

However, ChatGPT's tendency to make up what it doesn't know isn't always a bad thing. I think one of the things we pick up on when we watch a film with machine translated subtitles is bad grammar, for example. ChatGPT is less likely to generate bad grammar because it will make up details when it can't make sense of the input. And its inventions usually sound plausible enough to fool you. I also think using ChatGPT on Whisper subtitles works pretty well because of how ChatGPT can sometimes guess words where Whisper misheard and created an error.

Ultimately, I think ChatGPT is going to get really good at translations. Right now it's limited because 1) most of us, including myself, are using the older 3.5 models and not the new stuff and 2) the vast majority of the training set is English (over 90% of the training set for GPT 3.5) and the AI will need to be trained more in other languages to produce comparable results.