rakeshvar/rnn_ctc
Recurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example.
This project helps researchers and machine learning engineers train neural networks to interpret sequences, particularly images of text. You provide images containing sequences (like 'tablets of text') along with their corresponding character labels, and the system trains a recurrent neural network to recognize these sequences. It's designed for those developing or researching optical character recognition (OCR) or sequence-to-sequence prediction models.
221 stars. No commits in the last 6 months.
Use this if you are developing or experimenting with neural networks for sequence recognition, especially for tasks like character recognition from images.
Not ideal if you need a ready-to-use OCR solution or if you are not comfortable working with neural network training parameters and Python scripts.
Stars
221
Forks
81
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 26, 2016
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/rakeshvar/rnn_ctc"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
githubharald/CTCDecoder
Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon...
githubharald/CTCWordBeamSearch
Connectionist Temporal Classification (CTC) decoder with dictionary and language model.
nl8590687/ASRT_SpeechRecognition
A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
athena-team/athena
an open-source implementation of sequence-to-sequence based speech processing engine
hirofumi0810/tensorflow_end2end_speech_recognition
End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)