A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

⚡ TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords

Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon search, prefix search, and token passing. Implemented in Python.

End-to-end ASR/LM implementation with PyTorch

Tensorflow-based CNN+LSTM trained with CTC-loss for OCR

一个执着于让CPU\端侧-Model逼近GPU-Model性能的项目，CPU上的实时率(RTF)小于0.1

ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction

CNN+LSTM+CTC based OCR implemented using tensorflow.

A research project for text detection and recognition using PyTorch 1.2.

End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)

A TensorFlow implementation of https://github.com./bgshih/crnn

A Keras CTC implementation of Baidu's DeepSpeech for model experimentation

Recurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example.

CTC end -to-end ASR for timit and 863 corpus.

text_recognition_toolbox: The reimplementation of a series of classical scene text recognition papers with Pytorch in a uniform way.

基于卷积神经网络的语音识别声学模型的研究

Convolutional Recurrent Neural Network(CRNN) for End-to-End Text Recognition - TensorFlow 2

ASR with PyTorch

Application of Connectionist Temporal Classification (CTC) for Speech Recognition (Tensorflow 1.0 but compatible with 2.0).

Computer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection