We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
@VikParuchuri Currently batch size is set to 32 when device is cuda or mps, yes we can alter OcrBuilder but not able to do it when using PdfConverter.
cuda
mps
OcrBuilder
PdfConverter
Maybe reading these batch size form an env variable would be helpful
I can add if this sounds good
The text was updated successfully, but these errors were encountered:
Maybe i misinterpreted, we can set them from OcrBuilder.recognition_batch_size and so on..
OcrBuilder.recognition_batch_size
Sorry, something went wrong.
You can pass in the config via json file in the cli - --config_json PATH: Path to a JSON configuration file containing additional settings.
--config_json PATH: Path to a JSON configuration file containing additional settings.
If you have a json file with {"recognition_batch_size": 16}, that will override the setting
No branches or pull requests
@VikParuchuri
Currently batch size is set to 32 when device is
cuda
ormps
, yes we can alterOcrBuilder
but not able to do it when usingPdfConverter
.Maybe reading these batch size form an env variable would be helpful
I can add if this sounds good
The text was updated successfully, but these errors were encountered: