Mozilla's open-source speech recognition

Mitchell, Jess jmitchell at
Fri Dec 1 15:11:17 UTC 2017

> On Dec 1, 2017, at 5:20 AM, Tony Atkins <tony at> wrote:
> I also love that they provide not only the specific tool, but also the dataset they used to train it.  The same data can be used to find better answers to this problem, but can also be used in unexpected ways, for example, identifying and gaming an engine for specific accents.

This part sounds like a good practice in general for any “trained” service! Reuse, transparency, and all the good stuffs.

Thanks for the thoughts Tony :)


Jess Mitchell
(GMT - 4:00)
Senior Manager, R&D + Design
OCAD University, Toronto
Inclusive Design Research Centre
jmitchell at
skype: jesshmitchell

More information about the fluid-work mailing list