Deep Speech: Accurate Speech Recognition with GPU-Accelerated Deep Learning

Originally published at: https://developer.nvidia.com/blog/deep-speech-accurate-speech-recognition-gpu-accelerated-deep-learning/

Speech recognition is an established technology, but it tends to fail when we need it the most, such as in noisy or crowded environments, or when the speaker is far away from the microphone. At Baidu we are working to enable truly ubiquitous, natural speech interfaces. In order to achieve this, we must improve the…

Is there any APIs available for developers to start experimenting/using Deep Speech?

Hi Anuroop - We are working on making a public API for Deep Speech. We'll make an announcement when it is ready. Thanks for your interest.

Any update and/or timeline?

Hey Pat, Not 1000% sure but I think https://api.ai/ may be helpful for you here

Is there any way to know more specific about this project?
I mean workloads, hardware you use, amount of data and how long did it take to complete process successfully?

What is the biggest speech\text database available?