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

主流ocr算法研究实验性的项目，目前实现了CNN+BLSTM+CTC架构

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

an open-source implementation of sequence-to-sequence based speech processing engine

Speech-to-text server framework with next-gen Kaldi

PyTorch CTC Decoder bindings

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

The official repository of the Eesen project

End-to-end ASR/LM implementation with PyTorch

Connectionist Temporal Classification (CTC) decoder with dictionary and language model.

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

A Deep-Learning-Based Persian Speech Recognition System

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.

基于卷积神经网络的语音识别声学模型的研究

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

基于Flask Web的中文自动语音识别演示系统,包含语音识别、语音合成、声纹识别之说话人识别。

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).

FEC Codec IP core library for a some famous codes (BCH, RS, LDPC, Turbo)

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

End-to-end trained speech recognition system, based on RNNs and the connectionist temporal classification (CTC) cost function.