Today, I show you how you can create your own virtual assistant, similar to Google Now and Amazon Alexa, using a Raspberry Pi, and some cool open source software called Jasper!
I go through the hardware needed, the software, installation of jasper, the configuration, and finally, a demo of the usage at the end. If you would like to see a follow-up to this video, about creating your own modules, make sure to leave a comment down below!
These times may be off by a bit now, after I re-edited the video.
00:00 – Introduction
00:48 – Hardware and Software Overview
01:40 – Materials & Hardware
04:30 – Software
04:40 – Raspbian
05:44 – Jasper Overview
06:00 – Speech to Text Options
07:45 – Text to Speech Options
09:10 – Connecting Using SSH
09:15 – How To Obtain IP Address of Raspberry Pi
10:00 – SSH on Linux
11:00 – SSH Clients for Windows/Mac
11:47 – Configuring Raspbian using raspi-config
13:20 – Installing prerequisite programs (git, vim, python, pip, bison, libasound, pyaudio)
15:30 – Updating repository list
17:30 – Configuring audio devices using alsamixer
18:40 – Optionally test the audio setup
18:50 – Downloading Jasper using Git
19:40 – Installing Jasper dependencies using pip
22:10 – Enable execution on Jasper.py
22:55 – Dependencies for Google TTS
25:25 – Configuring Jasper
28:00 – Creating and configuring wit.ai STT
Jasper Project: http://jasperproject.github.io/
Jasper Installation: http://jasperproject.github.io/documentation/installation/
Jasper SST and TTS Configuration: http://jasperproject.github.io/documentation/configuration/
– Raspberry Pi 2
– Behringer UCA200 as ADC and DAC
– Epidemic Sound
– Audio Micro
Thanks for watching! If you enjoyed this video, press that like button any maybe share it with your friends that are interested in creating their own website! If you didn’t enjoy it, leave me a suggestion down in the comments along with an improvement!
Facebook’s Caffe2 AI tools go to iPhone, Android, and also Raspberry Pi
Your phone may soon be capable of determine items in images without the need for gaining access to the cloud
New intelligence can be included with mobile devices just like the iPhone, Android products, and low-power computers like Raspberry Pi with Facebook’s new open-source Caffe2 deep-learning framework.
Caffe2 can be used to program artificial intelligence features into smartphones and tablets, permitting them to understand photos, movie, text message, and speech and be more situationally aware.
It is important to be aware that Caffe2 is not an AI program, but a tool permitting AI to be programmed into mobile phones. It takes just a couple of lines of code to write learning models, which can then be bundled into apps.
The release of Caffe2 is critical. This means people will be in a position to get image identification, natural language processing, and computer vision right on their mobile. That task is usually offloaded to remote servers in the cloud, with mobile phones then connecting to it.
Mobile devices are receiving more artificial intelligence functions. More mobiles are being bundled with Amazon’s Alexa and Google Assistant, while Apple’s Siri has been a staple in the iPhone for a long time. Samsung’s Galaxy S8 mobile phones are going to get the Bixby voice assistant, which should make using the handsets easier.
Caffe2 can work within the power constraints of mobile devices. It works with mobile hardware to hasten AI apps and create neural networks.
Caffe2 uses the computing power of latest mobile hardware to speed up deep-learning jobs. To illustrate, in mobile phones, Caffe2 will take advantage of the computing power of Adreno GPUs and Hexagon DSPs on Qualcomm’s Snapdragon mobile chips.