1Metadata-Version: 1.1
2Name: webrtcvad
3Version: 2.0.10
4Summary: Python interface to the Google WebRTC Voice Activity Detector (VAD)
5Home-page: https://github.com/wiseman/py-webrtcvad
6Author: John Wiseman
7Author-email: jjwiseman@gmail.com
8License: MIT
9Description: .. image:: https://travis-ci.org/wiseman/py-webrtcvad.svg?branch=master
10            :target: https://travis-ci.org/wiseman/py-webrtcvad
11
12        py-webrtcvad
13        ============
14
15        This is a python interface to the WebRTC Voice Activity Detector
16        (VAD).  It is compatible with Python 2 and Python 3.
17
18        A `VAD <https://en.wikipedia.org/wiki/Voice_activity_detection>`_
19        classifies a piece of audio data as being voiced or unvoiced. It can
20        be useful for telephony and speech recognition.
21
22        The VAD that Google developed for the `WebRTC <https://webrtc.org/>`_
23        project is reportedly one of the best available, being fast, modern
24        and free.
25
26        How to use it
27        -------------
28
29        0. Install the webrtcvad module::
30
31            pip install webrtcvad
32
33        1. Create a ``Vad`` object::
34
35            import webrtcvad
36            vad = webrtcvad.Vad()
37
38        2. Optionally, set its aggressiveness mode, which is an integer
39           between 0 and 3. 0 is the least aggressive about filtering out
40           non-speech, 3 is the most aggressive. (You can also set the mode
41           when you create the VAD, e.g. ``vad = webrtcvad.Vad(3)``)::
42
43            vad.set_mode(1)
44
45        3. Give it a short segment ("frame") of audio. The WebRTC VAD only
46           accepts 16-bit mono PCM audio, sampled at 8000, 16000, or 32000 Hz.
47           A frame must be either 10, 20, or 30 ms in duration::
48
49            # Run the VAD on 10 ms of silence. The result should be False.
50            sample_rate = 16000
51            frame_duration = 10  # ms
52            frame = b'\x00\x00' * (sample_rate * frame_duration / 1000)
53            print 'Contains speech: %s' % (vad.is_speech(frame, sample_rate)
54
55
56        See `example.py
57        <https://github.com/wiseman/py-webrtcvad/blob/master/example.py>`_ for
58        a more detailed example that will process a .wav file, find the voiced
59        segments, and write each one as a separate .wav.
60
61
62        How to run unit tests
63        ---------------------
64
65        To run unit tests::
66
67            pip install -e ".[dev]"
68            python setup.py test
69
70Keywords: speechrecognition asr voiceactivitydetection vad webrtc
71Platform: UNKNOWN
72Classifier: Development Status :: 4 - Beta
73Classifier: Intended Audience :: Developers
74Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
75Classifier: Topic :: Scientific/Engineering :: Information Analysis
76Classifier: Topic :: Scientific/Engineering :: Human Machine Interfaces
77Classifier: License :: OSI Approved :: MIT License
78Classifier: Programming Language :: Python :: 2
79Classifier: Programming Language :: Python :: 2.7
80Classifier: Programming Language :: Python :: 3
81Classifier: Programming Language :: Python :: 3.2
82Classifier: Programming Language :: Python :: 3.3
83Classifier: Programming Language :: Python :: 3.4
84Classifier: Programming Language :: Python :: 3.5
85