This project offers an efficient method for identifying and recognizing handwritten text from images. Using a Convolutional Recurrent Neural Network (CRNN) for Optical Character Recognition (OCR), it effectively extracts text from images, aiding in the digitization of handwritten documents and automated text extraction.

OCR 基于 Keras

My implementations of different deep learning architectures for text recognition with TensorFlow 2.

This project uses deep learning and NLP to classify songs by sentiment and genre through combined audio and text analysis. It processes lyrics and audio features, integrating both in a neural network for enhanced accuracy, providing a structured pipeline for data loading, training, and visualization.

CRNN implementation with TensorFlow 2

ctc decoder

CRNN (CNN+RNN) for OCR using Keras / License Plate Recognition