When I was doing some research on speech recognition, I saw some articles about the google speech recognition service on android being able to be downloaded and used offline on android. I also saw some stuff about using the google speech service over the computer, but it involved querying the google server. So here's my question: is there any way to use the google speech recognition service offline over the computer, specifically on linux?
Asked
Active
Viewed 5,547 times
9
-
2The issue with Palaver is that it requires connectivity to Google. There's a few variants of Sphinx (CMU Sphinx, Sphinx-4, etc.) that work offline. They are much more difficult to set up and train. – joat Jul 04 '13 at 03:13
1 Answers
1
Use the Palaver developed by James McClain.
For more details look this video(http://www.youtube.com/watch?v=pxom292XW_g).
Dependencies:
$ sudo apt-get install sox python-argparse libsox-fmt-mp3 mutt xvkbd xautomation
The current code is beta, and will be going through restructuring changes as it moves from git to launchpad, so expect a lot of changes in the near future.
The beta can actually do quite a lot at the moment, especially if you add your own dictionary.
Have a look at the docs (/opt/Palaver/Docs) for setting up a dictionary of commands. It is very easy to do. Also, have a look at the default dictionary for a list of inbuilt commands.
stderr
- 10,264
- 2
- 32
- 49