RSS Feed for This PostCurrent Article

Speech Recognition – warp-ctc

warp-ctc is a parallel implementation of CTC, on both CPU and GPU.

Connectionist Temporal Classification is a loss function useful for performing supervised learning on sequence data, without needing an alignment between input data and labels. For example, CTC can be used to train end-to-end systems for speech recognition, which has been used at Baidu’s Silicon Valley AI Lab.


Trackback URL


Sorry, comments for this entry are closed at this time.