Baidu Tech Blog

Today Baidu’s Silicon Valley AI Lab (SVAIL) released Warp-CTC, open source software for the machine learning community. Warp-CTC can be used to solve supervised problems that map an input sequence to an output sequence, such as speech recognition. 

Get Warp-CTC and read more here 

Warp-CTC Q&A

Q. What is Warp-CTC?

A. Warp-CTC is an open source implementation of the CTC algorithm for CPUs and NVIDIA GPUs.

Q. What is CTC?

A. CTC is an objective function that can be used while doing supervised training for sequence prediction, without knowing an alignment between the input and output.The CTC algorithm was developed at IDSIA by Alex Graves, Santiago Fernandez, Faustino Gomez and Jürgen Schmidhuber. 

Q. Why did SVAIL develop Warp-CTC?

A. SVAIL engineers developed Warp-CTC to improve the scalability of models trained using CTC while we were building our Deep Speech end-to-end speech recognition system. We found that currently available implementations of CTC generally required significantly more memory and/or were tens to hundreds of times slower.

Q. Why is SVAIL releasing Warp-CTC as open source software?

A. We want to make end-to-end deep learning easier and faster so researchers can make more rapid progress. A lot of open source software for deep learning exists, but previous code for training end-to-end networks for sequences (like our Deep Speech engine) has been too slow. We want to start contributing to the machine learning community by sharing an important piece of code that we created.

Q. Which machine learning frameworks does Warp-CTC support?

A. We are releasing Warp-CTC as a C library along with integration for Torch, a scientific computing framework. Additionally, Nervana Systems is integrating Warp-CTC into Neon, their machine learning framework.

Q. How can researchers use Warp-CTC?

A. Warp-CTC can be used to solve supervised problems that map an input sequence to an output sequence, such as speech recognition. 

Q. Can the machine learning community make improvements to Warp-CTC?

A. We have written Warp-CTC  so it can be easily integrated into many projects. We encourage developers who are interested in integrating Warp-CTC  into a machine learning framework to reach out to us. We are happy to accept pull requests.

Q. Do you expect to release additional open source AI tools?

A. Yes! 

Get Warp-CTC and read more here 

2018-01-17T17:25:37+00:00 January 14th, 2016|