Samee Arif

`tesseract -v` `tesseract 5.2.0 leptonica-1.82.0 libgif 5.1.9 : libjpeg 8d (libjpeg-turbo 2.1.1) : libpng 1.6.37 : libtiff 4.3.0 : zlib 1.2.11 : libwebp 1.2.2 : libopenjp2 2.4.0 Found AVX512BW Found...

Can't encode transcription

1

Hello, I am trying to train form scratch/fine tune tesseract for "Jameel Noori Nastaleeq" font for Urdu. The steps i did for training from scratch: 1. Create unicharset from all...

How to create the files for running a custom model?

2

The EasyOCR ReadME states that the following three files are required to use a custom model: custom_model.pth, custom_model.yaml, and custom_model.py. How are we supposed to create the custom_model.yaml and custom_model.py...

How do we make the files required for running our custom model?

2

The EasyOCR ReadME states that the following three files are required to use a custom model: custom_model.pth, custom_model.yaml, and custom_model.py. How are we supposed to create the custom_model.yaml and custom_model.py...

TrOCR - Segmentation Issue

1

Do we need to manually segment the following image before we give it to the model for the final predictions? Is there a built-in segmentation module within TrOCR? If not,...

Variable length images

2

Can we train EasyOCR on variable length images?

4-bit quantization for OpenAI whisper and for Facebook MMS

3

### Feature request Implement 4 bit quantization technique for these automatic speech recognition models: 1. OpenAI Whisper 2. Facebook MMS ### Motivation I tested the 8 bit models on a...