Reading and storing transcripts to csv files using EasyOCR
To read more about EasyOCR, follow the link - https://github.com/JaidedAI/EasyOCR. This project was developed as a freelancing project. The OCR developed is able to read the transcripts while also identifying the line spacing and all the different characters in the word. The OCR can read characters of upto 40 languages. The scanned results are stored as a csv named output.csv. The test images are stored in a separate directory. The output.csv by default contains the output to one of the images in the text directory. The OCR can be tuned for any use case by changing the hyperparameters.