| 1 |
PocketSphinx Documentation |
| 2 |
============================ |
| 3 |
|
| 4 |
Welcome to the documentation for the Python interface to the |
| 5 |
PocketSphinx speech recognizer! |
| 6 |
|
| 7 |
Quick Start |
| 8 |
----------- |
| 9 |
|
| 10 |
To install PocketSphinx on most recent versions of Python, you should |
| 11 |
be able to simply use `pip`:: |
| 12 |
|
| 13 |
pip install pocketsphinx |
| 14 |
|
| 15 |
This is a (somewhat) "batteries-included" install, which comes with a |
| 16 |
default model and dictionary. Sadly, this model is specifically for |
| 17 |
US (and, by extension Canadian) English, so it may not work well for |
| 18 |
your dialect and certainly won't work for your native language. |
| 19 |
|
| 20 |
On Unix-like platforms you may need to install `PortAudio |
| 21 |
<https://portaudio.com>`_ for live audio input to work. Now you can |
| 22 |
try the simplest possible speech recognizer:: |
| 23 |
|
| 24 |
from pocketsphinx import LiveSpeech |
| 25 |
for phrase in LiveSpeech(): |
| 26 |
print(phrase) |
| 27 |
|
| 28 |
This will open the default audio device and start listening, detecting |
| 29 |
segments of speech and printing out the recognized text, which may or |
| 30 |
may not resemble what you actually said. |
| 31 |
|
| 32 |
There are of course many other things you can do with it. See |
| 33 |
the :ref:`apidoc` for more information. |
| 34 |
|
| 35 |
.. _apidoc: |
| 36 |
|
| 37 |
API Documentation |
| 38 |
----------------- |
| 39 |
|
| 40 |
.. toctree:: |
| 41 |
pocketsphinx |
| 42 |
config_params |
| 43 |
|
| 44 |
|
| 45 |
Indices and tables |
| 46 |
================== |
| 47 |
|
| 48 |
* :ref:`genindex` |
| 49 |
* :ref:`modindex` |
| 50 |
* :ref:`search` |