![]() This Week In Security: TPM And BootGuard, Drones, And Coverups 17 Comments It seams there is definitely a need to simplify the installation process…. so if some one was able to write a human readable tutorial on any one of the popular open source projects i am sure that project will become quite popular overall as i have tried to read and understand the jargon (quickly getting lost in web searches). i am not worried about how complex the setup might be but more about basic instructions that do not require a degree in rocket science. nothing i have found on the internet explaining the steps needed to setup such a machine, they always end with or start with creating a google account. i have been using Linux for several years now and had lots of fun learning from it, so i am not exactly a beginner but after several hours of trying to understand how to install/setup such a machine seams to be quite difficult. what i would like is some thing that is considered private (NO GOOGLE). I have been wanting to dive into a voice recognition project for home use for many years now… however the only thing that i can find that seams to work uses a third party for the translating. Posted in Linux Hacks Tagged deepspeech, json, linux, pocketsphinx, speech, voice Post navigation Of course, what we really want is speech commands like the USS Enterprise, and we have to admit it is getting closer. Meanwhile, we’ve been watching Linux speech for quite a while. If you do something interesting with it, be sure to drop us a tip so we can cover it. Overall, this looks like a fun tool to have in your kit. There are other features like mapping an object like living room lamp into something more computer-friendly. There are templating features so you can specify optional words and alternative words in a single rule. Here’s an example configuration from the project’s website: ![]() In addition, the tools are all made to work in Unix-style pipelines which is refreshing. So not only do you know there is a garage door, but you gain an understanding of the opening and closing of the garage door. The fast training process produces both a speech recognizer and an intent recognizer. However, the code is more than just a thin wrapper around these tools. The software can integrate with several backends to do offline speech recognition including CMU’s pocketsphinx, Dan Povey’s Kaldi, Mozilla’s DeepSpeech 0.9, and Kyoto University’s Julius. While it doesn’t provide the actual voice recognition, it does make it easier to get things going and then use speech in a natural way. ![]() However, that doesn’t mean it’s always easy to get it working, and speech recognition is just one of those difficult setups.Ī project called Voice2JSON is trying to simplify the use of voice workflows. For just about any task you care to name, a Linux-based desktop computer can get the job done using applications that rival or exceed those found on other platforms.
0 Comments
Leave a Reply. |