Desktop app for automatically translating comics - BDs, Manga, Manhwa, Fumetti and more in a variety of formats (Image, Pdf, Epub, cbr, cbz, etc) and in multiple languages.
OCR-ing with Google Cloud Vision API doesn't seem to work for me.
I'm trying to OCR text from a french comic.
I got Comic-translate to work. There were errors during installation but prompt --user got it working.
I got an API key using the procedure explained on the main page of Comic-translate.
Cloud Vision API is enabled in my Google Cloud.
API key is inserted in Comic-translate under Credentials-Google Cloud API key.
I manually select text in an image for OCR-ing.
When language in source image is set to ENGLISH and OCR in settings is set to default, I get OCR-ed text.
However, when I set text to French and set OCR engine in settings to Google Cloud Vision and start OCR, I get no results.
There are no errors, just nothing is OCR-ed. No text, everything is blank.
Google cloud is detecting traffic (requests in Cloud Vision API exist) but there is no feedback with OCR-ed text.
I'm using Windows and python 3.9.13. Firewall is disabled.
Does Google Cloud Vision API work for you or it's something on my end?
ogkalu2
commented
2 months ago
OCR-ing with Google Cloud Vision API doesn't seem to work for me.
I'm trying to OCR text from a french comic. I got Comic-translate to work. There were errors during installation but prompt --user got it working. I got an API key using the procedure explained on the main page of Comic-translate. Cloud Vision API is enabled in my Google Cloud. API key is inserted in Comic-translate under Credentials-Google Cloud API key.
I manually select text in an image for OCR-ing. When language in source image is set to ENGLISH and OCR in settings is set to default, I get OCR-ed text. However, when I set text to French and set OCR engine in settings to Google Cloud Vision and start OCR, I get no results. There are no errors, just nothing is OCR-ed. No text, everything is blank. Google cloud is detecting traffic (requests in Cloud Vision API exist) but there is no feedback with OCR-ed text. I'm using Windows and python 3.9.13. Firewall is disabled. Does Google Cloud Vision API work for you or it's something on my end?
Best regards