Somewhat fancy voice command recognition software

Clara Hobbs 2a641364bf Removed QT interface, renamed interfaces to Kaylee I'm a GTK man myself. I don't know if I have Python QT bindings installed on any of my computers. It follows then that I would not maintain the QT interface well, let alone use it at all. It has therefore been removed to avoid having someone try to use it only to find that it's broken.		8 anni fa
assets	Added Gtk Tray UI (thanks padfoot)	10 anni fa
data	Added Gtk Tray UI (thanks padfoot)	10 anni fa
.gitignore	Ported to new pocketsphinx and pygi	8 anni fa
README.md	Ported to new pocketsphinx and pygi	8 anni fa
blather.py	Removed QT interface, renamed interfaces to Kaylee	8 anni fa
commands.tmp	added gstreamer0.10-base-plugins to the requirements in the README	10 anni fa
gpl-3.0.txt	licensing	11 anni fa
gtktrayui.py	Removed QT interface, renamed interfaces to Kaylee	8 anni fa
gtkui.py	Removed QT interface, renamed interfaces to Kaylee	8 anni fa
language_updater.sh	The updater uses the correct commands file	11 anni fa
options.yaml.tmp	Added invalid sentence command and valid sentence command to the documentation	9 anni fa
recognizer.py	Removed QT interface, renamed interfaces to Kaylee	8 anni fa

Kaylee

Kaylee is a somewhat fancy speech recognizer that will run commands and perform other functions when a user speaks loosely preset sentences. It is based on Blather by Jezra, but adds a lot of features that go beyond the original purpose of Blather.

Requirements

pocketsphinx
gstreamer-1.0 (and what ever plugin has pocket sphinx support)
gstreamer-1.0 base plugins (required for alsa)
pyside (only required for the Qt based UI)
pygtk (only required for the Gtk based UI)
pyyaml (only required for reading the options file)

Note: it may also be required to install pocketsphinx-hmm-en-hub4wsj

Usage

Move commands.tmp to ~/.config/blather/commands.conf and fill the file with sentences and command to run
Run Blather.py, this will generate ~/.config/blather/sentences.corpus based on sentences in the ‘commands’ file
Quit blather (there is a good chance it will just segfault)
Go to http://www.speech.cs.cmu.edu/tools/lmtool.html and upload the sentences.corpus file
Download the resulting XXXX.lm file to the ~/.config/blather/language directory and rename to file to ‘lm’
Download the resulting XXXX.dic file to the ~/.config/blather/language directory and rename to file to ‘dic’
Run Blather.py
- For Qt GUI, run Blather.py -i q
- For Gtk GUI, run Blather.py -i g
- To start a UI in ‘continuous’ listen mode, use the -c flag
- To use a microphone other than the system default, use the -m flag
Start talking

Note: to start Blather without needing to enter command line options all the time, copy options.yaml.tmp to ~/.config/blather/options.yaml and edit accordingly.

Bonus

Once the sentences.corpus file has been created, run the language_updater.sh script to automate the process of creating and downloading language files.

Examples

To run blather with the GTK UI and start in continuous listen mode: ./Blather.py -i g -c
To run blather with no UI and using a USB microphone recognized and device 2: ./Blather.py -m 2
To have blather pass the matched sentence to the executing command: ./Blather.py -p

explanation: if the commands.conf contains: good morning world : example_command.sh then 3 arguments, ‘good’, ‘morning’, and ‘world’ would get passed to example_command.sh as example_command.sh good morning world
To run a command when a valid sentence has been detected: ./Blather.py --valid-sentence-command=/path/to/command note: this can be set in the options.yml file
To run a command when a invalid sentence has been detected: ./Blather.py --invalid-sentence-command=/path/to/command note: this can be set in the options.yml file

Finding the Device Number of a USB microphone

There are a few ways to find the device number of a USB microphone.

cat /proc/asound/cards
arecord -l

README.md