Baidu’s AI Team Releases Key Deep-Learning Code
technologyreview.com
4 threads
Github [from article]: https://github.com/baidu-research/warp-ctc
From the GitHub page: "This project contains our high performance CPU and CUDA versions of the CTC loss, along with bindings for Torch. The library provides a simple C interface, so that it is easy to integrate into deep learning frameworks."
The hard part is not the technology, it's the large enough data sets. Perhaps finding good employees could also be a help
The point that's not stressed enough is the massive amounts of good data that is needed to fuel these kind of systems. Data collection, cleaning, aggregation and other processes itself are humungous tasks.