Hungarian translation of the essence of calculus video #36
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
MrExpertGitHub
suggested changes
Feb 5, 2024
|
Good to know that DeepL is a better starting point. As to how the TTS handles it, in a week or two we can make a few samples for you to see what it does by default, and perhaps that will inform how things should be corrected. Is this one good to merge? |
|
Not yet. We are still working on the full correction. |
# Conflicts: # 2017/essence-of-calculus/hungarian/sentence_translations.json
Co-authored-by: MrExpert <[email protected]>
MrExpertGitHub
approved these changes
Feb 11, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This translation was intended to be a quick suffix-fixing one, but instead it quickly went off the rails :D
Problems of the AI translation
Similarly to #13, the problem of the AI translating "you" as a formal you comes up in Hungarian as well, as well the problem of out of context words and mistranslated technical concepts. However, sometimes words, or even whole sentence clauses are omitted. Many sentences range from unnatural to incomprehensible.
Out of curiosity I tried feeding a couple strings to DeepL as proposed in #10 and it was better but wasn't quite there yet (we probably can't expect that from any tool tbh). In the end, I felt like there was something off in almost all of the sentences, so I corrected the whole thing as best as i could.
Dev experience
It wasn't absurd to edit a raw JSON file by hand, but for broader community contribution I believe it would be better to have an interface that only allows access to the relevant data, that way more non-technical people could contribute. Some kind of proofreading or peer review/voting for submitted fixes is also something that would be great to have in my opinion.
Questions
If these subtitles are going to be used for generating audio tracks, how should notation be transcribed in cases where writing it as you say it would negatively affect reading? (For example dA for small change in area could be pronounced as "daa" by the AI voice, but writing it any other way would cause a mismatch between the video and the subtitles). Maybe an optional pronunciation override?