TeaPoly/warp-ctc-crf
An extension of thu-spmi/CAT which contains a full-fledged implementation of CTC-CRF for Tensorflow.
This project provides an implementation of CTC-CRF for TensorFlow, which is a key component for training advanced speech recognition models. It takes audio features as input and outputs optimized neural network parameters that improve the accuracy of converting spoken language into text. Machine learning engineers and researchers working on automatic speech recognition (ASR) systems would use this to enhance their model training.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher developing custom automatic speech recognition (ASR) models with TensorFlow and need to implement CTC-CRF for improved performance.
Not ideal if you are looking for an out-of-the-box speech-to-text solution or do not have experience with TensorFlow, CUDA, and C++ extensions.
Stars
12
Forks
4
Language
Cuda
License
—
Category
Last pushed
Jul 05, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/TeaPoly/warp-ctc-crf"
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)