[GUI Plugin] Ebook Translator

[dark76]

Hello, I'm using 1.3.8 version. After my first translation try using google free, nothing is generated and I get this message in the final part of the log, after many rows of original and translated text.

Spoiler:

Start to convert ebook format:
==============================
Traceback (most recent call last):
File "runpy.py", line 196, in _run_module_as_main
File "runpy.py", line 86, in _run_code
File "site.py", line 83, in <module>
File "site.py", line 78, in main
File "site.py", line 50, in run_entry_point
File "calibre\utils\ipc\worker.py", line 215, in main
File "calibre\utils\ipc\worker.py", line 150, in arbitrary_n
File "calibre_plugins.ebook_translator.convertion", line 123, in convert_book
File "calibre\ebooks\conversion\plumber.py", line 1281, in run
File "calibre_plugins.ebook_translator.convertion", line 120, in convert
File "calibre\ebooks\conversion\plugins\epub_output.py" , line 212, in convert
File "calibre\ebooks\oeb\transforms\rescale.py", line 20, in __call__
File "calibre\ebooks\oeb\transforms\rescale.py", line 60, in rescale
File "calibre\ebooks\oeb\base.py", line 1038, in data
File "calibre\ebooks\oeb\base.py", line 590, in read
FileNotFoundError: [Errno 2] No such file or directory: 'C:\\Users\\danie\\AppData\\Local\\Temp\\calibre_7 15f7v3v\\dhtblek1_plumber\\OEBPS/images/Russ_9780345510884_epub_003_r1.jpg'

In the original epub, calibre doesnt find any problem. That jpg is a referenced image. Any idea?


EDIT: Weird, I tried another time and this time, it worked :/ Sorry!

[kindlefere]

New version (v2.0.0) was released. Here are new/improved features and enhancements. You can also go to GitHub page to check out more.

1. Added "Advanced Mode" for translation fine-grain control.
2. Added more options such as endpoint/sampling/model to ChatGPT.
3. Supported multiple API keys for all built-in translation engines.
4. Added "Ignore Element" feature for excluding unneeded elements.
5. Enhanced cache feature to include more information for reviewing.
6. Added preferred input/output formats and preferred source language options.
7. Added Azure ChatGPT to built-in translation engines.
8. Added "Preferred Mode" for clicking icon button in general settings.
9. Added "Timeout" option to "HTTP Request" setting.
10. Optimized ChatGPT prompt for more accurate translating.
11. Fixed the bug that cannot filter paragraphs properly.
12. Optimized user experiences, improved features and fix bugs.

[Zetmolm]

It's getting better and better. Thanks for the new version.

I have a feature request: for target format EPUB (and perhaps other formats where this applies), could you add an option to automatically add a Language tag for the target language in the output ebook's metadata? E.g., if the target language is Dutch, add:

<dc:language>nl</dc:language>

.

It would also be nice to have an option to automatically add a subject tag to the output ebook, e.g. "bilingual" or "Translated by Ebook Translator". The text to be added as a subject should of course be editable as a setting in the plugin.

I hope you are willing consider these options.

[kindlefere]

@Zetmolm

Thanks for the advice, we will consider these options in the future version.

[ramses777]

When I try to translate with ChatGPT, the following error appears: HTTP Error 429: Too Many Requests . Can someone help me?

[kindlefere]

Error 429 is mostly caused by a network issue. You can try changing your IP address and attempt again.

[ramses777]

Originally Posted by kindlefere

Error 429 is mostly caused by a network issue. You can try changing your IP address and attempt again.

Do I need ChatGPT Plus for it to translate?

[kindlefere]

I don't think ChatGPT Plus is necessary for 429 error. However, we suggest keeping the Concurrency limit at 1 and enlarging the Max interval in the HTTP Request settings to avoid the same error happening again in the future.

[colinsky]

Just in case anyone finds it useful, I've found background striping makes the output of this plugin a bit more readable on an e-reader screen. Without it, I occasional had to struggle to notice where the language of the text had changed. (Paste the following in your CSS)

p[lang="en"] {
text-indent: 0;
}

p:not([lang="en"]) {
background-color: lightgrey;
margin: 0.5em 0 0.5em 0;
text-indent: 0;
}

span:not([lang="en"]) {
background-color: lightgrey;
}

I've also toyed with incremental numbering of each pair of translated text (as you might see in an academic dual-language book) which can be applied using the same approach.

[parataxia0]

Hi,

First of all, this plugin is brilliant and it has translated via Google Free for many of my e-books that needed it.

However, I am trying to use ChatGPT instead and I am receiving this error when it works for a few paragraphs, this error arises:



Below is the log:

calibre, version 6.22.0 (win32, embedded-python: True)
Translation Failed: Failed: 'choices'

Traceback (most recent call last):
File "calibre_plugins.ebook_translator.advanced", line 159, in translate_paragraphs
File "calibre_plugins.ebook_translator.translation" , line 149, in handle
File "calibre_plugins.ebook_translator.request", line 37, in run
File "asyncio\runners.py", line 44, in run
File "asyncio\base_events.py", line 641, in run_until_complete
File "calibre_plugins.ebook_translator.request", line 34, in create_tasks
File "calibre_plugins.ebook_translator.request", line 22, in create_worker
File "calibre_plugins.ebook_translator.translation" , line 144, in process_translation
File "calibre_plugins.ebook_translator.translation" , line 109, in _prepare_translation
File "calibre_plugins.ebook_translator.engines.chatgpt" , line 106, in parse_stream
KeyError: 'choices'


Unsure what I can do on my end, seems as though the dictionary and key is somehow invalid.. and I do not know how to reproduce it either... hopefully this thread is still active. Thank you!~!

[parataxia0]

OK - It was an encoding error and it works since unwrapping paragraphs and punctuation along with UTF-8 support... All is well! Thank you anyways!

[ukiman]

I can't find "advanced mode" for some reason, could someone please help?

1. Choose the ebook and enter "Advanced Mode" via either ways below:
click "Advanced Mode" from the drop-down list of the plugin icon
click the plugin icon button if "Advanced Mode" is your Preferred Mode in General Setting

[Comfy.n]

Hi!

Today I managed to get my first ebook translation done with this amazing plugin. I chose "Add after original" for Translation Position. Then, after the ~1950 queries were processed, and it successfully generated the EPUB output, I thought I'd have preferred to have chosen "Add without original" for this specific case.

So I wonder: would it be possible to save something like a translation "project" file, with a custom file extension, so that one could just open that already processed file and load it again in ET to have it generate a new output using a different "Translation Position" setting?

[kindlefere]

Originally Posted by ukiman

I can't find "advanced mode" for some reason, could someone please help?

What version you used? "Advanced Mode" started from version v2.0.0.

[kindlefere]

@Comfy.n

The plugin already supports this feature by cache.

You can just change the "Translation Position" setting, and "translate" it again. It will not re-translate the book all over again, but use the old cached translation result. For details:

1. Advanced Mode: All paragraph items will stay as Status "Translated". By clicking the [Output] button, it will use the new "Translation Position" setting to generate the desired book file.
   
2. Batch Mode: By clicking the [TRANSLATE] button, it will also use the cached translation result, and you will notice the process is much faster. The translation log will show its process in detail:
   
   

   you can check the translation process by clicking "Jobs" at the bottom right. Double clicking the job item, you can check the real-time translation log from the window it prompts.