Meta

• License: BSD License (BSD)
• Author: Dmitry Prazdnichnov
• Maintainer: Dmitry Prazdnichnov
• Tags sphinxbase , pocketsphinx

Classifiers

• Development Status
  • 2 - Pre-Alpha
• Intended Audience
  • Developers
• License
  • OSI Approved :: BSD License
• Operating System
  • MacOS
  • Microsoft :: Windows
  • POSIX :: Linux
• Programming Language
  • C
  • Python :: 2
  • Python :: 2.7
  • Python :: 3
  • Python :: 3.5
  • Python :: 3.6
• Topic
  • Multimedia :: Sound/Audio :: Speech
  • Software Development :: Libraries :: Python Modules

Pocketsphinx Python

👁 Latest Version
👁 Development Status
👁 Supported Python Versions
👁 Travis Build Status
👁 AppVeyor Build Status
👁 License

Pocketsphinx is a part of the CMU Sphinx Open Source Toolkit For Speech Recognition.

This package provides a python interface to CMU Sphinxbase and Pocketsphinx libraries created with SWIG and Setuptools.

Supported platforms

• Windows
• Linux
• Mac OS X

Installation

# Make sure we have up-to-date versions of pip, setuptools and wheel
python-mpipinstall--upgradepipsetuptoolswheel
pipinstall--upgradepocketsphinx

More binary distributions for manual installation are available here.

Usage

LiveSpeech

It's an iterator class for continuous recognition or keyword search from a microphone.

from pocketsphinx import LiveSpeech
for phrase in LiveSpeech(): print(phrase)

An example of a keyword search:

from pocketsphinx import LiveSpeech

speech = LiveSpeech(lm=False, keyphrase='forward', kws_threshold=1e+20)
for phrase in speech:
 print(phrase.segments(detailed=True))

With your model and dictionary:

import os
from pocketsphinx import LiveSpeech, get_model_path

model_path = get_model_path()

speech = LiveSpeech(
 verbose=False,
 sampling_rate=16000,
 buffer_size=2048,
 no_search=False,
 full_utt=False,
 hmm=os.path.join(model_path, 'en-us'),
 lm=os.path.join(model_path, 'en-us.lm.bin'),
 dic=os.path.join(model_path, 'cmudict-en-us.dict')
)

for phrase in speech:
 print(phrase)

AudioFile

It's an iterator class for continuous recognition or keyword search from a file.

from pocketsphinx import AudioFile
for phrase in AudioFile(): print(phrase) # => "go forward ten meters"

An example of a keyword search:

from pocketsphinx import AudioFile

audio = AudioFile(lm=False, keyphrase='forward', kws_threshold=1e+20)
for phrase in audio:
 print(phrase.segments(detailed=True)) # => "[('forward', -617, 63, 121)]"

With your model and dictionary:

import os
from pocketsphinx import AudioFile, get_model_path, get_data_path

model_path = get_model_path()
data_path = get_data_path()

config = {
 'verbose': False,
 'audio_file': os.path.join(data_path, 'goforward.raw'),
 'buffer_size': 2048,
 'no_search': False,
 'full_utt': False,
 'hmm': os.path.join(model_path, 'en-us'),
 'lm': os.path.join(model_path, 'en-us.lm.bin'),
 'dict': os.path.join(model_path, 'cmudict-en-us.dict')
}

audio = AudioFile(**config)
for phrase in audio:
 print(phrase)

Pocketsphinx

It's a simple and flexible proxy class to pocketsphinx.Decode.

from pocketsphinx import Pocketsphinx
print(Pocketsphinx().decode()) # => "go forward ten meters"

A more comprehensive example:

from __future__ import print_function
import os
from pocketsphinx import Pocketsphinx, get_model_path, get_data_path

model_path = get_model_path()
data_path = get_data_path()

config = {
 'hmm': os.path.join(model_path, 'en-us'),
 'lm': os.path.join(model_path, 'en-us.lm.bin'),
 'dict': os.path.join(model_path, 'cmudict-en-us.dict')
}

ps = Pocketsphinx(**config)
ps.decode(
 audio_file=os.path.join(data_path, 'goforward.raw'),
 buffer_size=2048,
 no_search=False,
 full_utt=False
)

print(ps.segments()) # => ['<s>', '<sil>', 'go', 'forward', 'ten', 'meters', '</s>']
print('Detailed segments:', *ps.segments(detailed=True), sep='\n') # => [
# word, prob, start_frame, end_frame
# ('<s>', 0, 0, 24)
# ('<sil>', -3778, 25, 45)
# ('go', -27, 46, 63)
# ('forward', -38, 64, 116)
# ('ten', -14105, 117, 152)
# ('meters', -2152, 153, 211)
# ('</s>', 0, 212, 260)
# ]

print(ps.hypothesis()) # => go forward ten meters
print(ps.probability()) # => -32079
print(ps.score()) # => -7066
print(ps.confidence()) # => 0.04042641466841839

print(*ps.best(count=10), sep='\n') # => [
# ('go forward ten meters', -28034)
# ('go for word ten meters', -28570)
# ('go forward and majors', -28670)
# ('go forward and meters', -28681)
# ('go forward and readers', -28685)
# ('go forward ten readers', -28688)
# ('go forward ten leaders', -28695)
# ('go forward can meters', -28695)
# ('go forward and leaders', -28706)
# ('go for work ten meters', -28722)
# ]

Default config

If you don't pass any argument while creating an instance of the Pocketsphinx, AudioFile or LiveSpeech class, it will use next default values:

verbose = False
logfn = /dev/null or nul
audio_file = site-packages/pocketsphinx/data/goforward.raw
audio_device = None
sampling_rate = 16000
buffer_size = 2048
no_search = False
full_utt = False
hmm = site-packages/pocketsphinx/model/en-us
lm = site-packages/pocketsphinx/model/en-us.lm.bin
dict = site-packages/pocketsphinx/model/cmudict-en-us.dict

Any other option must be passed into the config as is, without using symbol -.

If you want to disable default language model or dictionary, you can change the value of the corresponding options to False:

lm = False
dict = False

Verbose

Send output to stdout:

from pocketsphinx import Pocketsphinx

ps = Pocketsphinx(verbose=True)
ps.decode()

print(ps.hypothesis())

Send output to file:

from pocketsphinx import Pocketsphinx

ps = Pocketsphinx(verbose=True, logfn='pocketsphinx.log')
ps.decode()

print(ps.hypothesis())

Compatibility

Parent classes are still available:

import os
from pocketsphinx import DefaultConfig, Decoder, get_model_path, get_data_path

model_path = get_model_path()
data_path = get_data_path()

# Create a decoder with a certain model
config = DefaultConfig()
config.set_string('-hmm', os.path.join(model_path, 'en-us'))
config.set_string('-lm', os.path.join(model_path, 'en-us.lm.bin'))
config.set_string('-dict', os.path.join(model_path, 'cmudict-en-us.dict'))
decoder = Decoder(config)

# Decode streaming data
buf = bytearray(1024)
with open(os.path.join(data_path, 'goforward.raw'), 'rb') as f:
 decoder.start_utt()
 while f.readinto(buf):
 decoder.process_raw(buf, False, False)
 decoder.end_utt()
print('Best hypothesis segments:', [seg.word for seg in decoder.seg()])

Install development version

Install requirements

Windows requirements:

• Python
• Git
• Swig
• Visual Studio Community

Ubuntu requirements:

sudoapt-getinstall-qqpythonpython-devpython-pipbuild-essentialswiggitlibpulse-dev

Install with pip

pipinstallhttps://github.com/bambocher/pocketsphinx-python/archive/master.zip

Install with distutils

gitclone--recursivehttps://github.com/bambocher/pocketsphinx-python
cdpocketsphinx-python
pythonsetup.pyinstall

Projects using pocketsphinx-python

• SpeechRecognition - Library for performing speech recognition, with support for several engines and APIs, online and offline.

License

The BSD License

Verified details

These details have been verified by PyPI

Maintainers

👁 Avatar for bambucha from gravatar.com
bambucha 👁 Avatar for dhdaines from gravatar.com
dhdaines

Unverified details

These details have not been verified by PyPI

Project links

• Homepage
• Download

• Download URL: pocketsphinx-0.1.10.tar.gz
• Upload date: Jun 3, 2018
• Size: 29.1 MB
• Tags: Source
• Uploaded using Trusted Publishing? No

Hashes for pocketsphinx-0.1.10.tar.gz

Algorithm	Hash digest
SHA256	3a368a5241d91b14e3241f04b53a8f4cb4955bc69fe28fa446442da34ac5c828
MD5	e333ac68daa7d5ed0cea4b7840e5fa30
BLAKE2b-256	8fda2cfb289f0ba6cc59b610bbe386f0a75ec779cc3d4363aeb5f039bd5e8113

See more details on using hashes here.

• Download URL: pocketsphinx-0.1.10.win-amd64-py3.6.exe
• Upload date: Jun 3, 2018
• Size: 29.7 MB
• Tags: Source
• Uploaded using Trusted Publishing? No

Hashes for pocketsphinx-0.1.10.win-amd64-py3.6.exe

Algorithm	Hash digest
SHA256	d74c352905f9410e9b7adb93be47d15879710ac2870ad5e96ffeb58935ecb7c4
MD5	5c9aa17515649e17fae2bb19f80cfc2a
BLAKE2b-256	dec9c6bc99d2e6fe68ce1e0a3babb65ea5e19b145137f0de2965f7e087f2f1b6

See more details on using hashes here.

• Download URL: pocketsphinx-0.1.10.win-amd64-py3.5.exe
• Upload date: Jun 3, 2018
• Size: 29.7 MB
• Tags: Source
• Uploaded using Trusted Publishing? No

Hashes for pocketsphinx-0.1.10.win-amd64-py3.5.exe

Algorithm	Hash digest
SHA256	b16bcf09946b46de6acce8bb35d6454b2be07a6ec3107e2e44898b49185b1c4a
MD5	ab1fc2abbc89be1881844f92a2ef2abd
BLAKE2b-256	8f8ebee80a6e93d1c78ab8fa95e034b3e93dbe3003016e268e33d82843d4e8b1

See more details on using hashes here.

• Download URL: pocketsphinx-0.1.10.win-amd64-py2.7.exe
• Upload date: Jun 3, 2018
• Size: 29.3 MB
• Tags: Source
• Uploaded using Trusted Publishing? No

Hashes for pocketsphinx-0.1.10.win-amd64-py2.7.exe

Algorithm	Hash digest
SHA256	3496ada3c4f041244f81dbb18b8b76bda6cb9c438ff881cc5c6a2e68be959627
MD5	2721d418e926d1987310f629e14f0f12
BLAKE2b-256	33714f9f39043f6c4a0b2c12d43a2630abbccddab50d7d38e303f654e77a4aae

See more details on using hashes here.

• Download URL: pocketsphinx-0.1.10.win32-py3.6.exe
• Upload date: Jun 3, 2018
• Size: 29.5 MB
• Tags: Source
• Uploaded using Trusted Publishing? No

Hashes for pocketsphinx-0.1.10.win32-py3.6.exe

Algorithm	Hash digest
SHA256	23d1ad97c7f346e2b04b8d2aa2120741ffdf381231e18e4b693cd5082a2f3f9b
MD5	921574623a48a0f17c1748c62ad1a6f4
BLAKE2b-256	5cba338012d72310f1cd40183b9e01acd35e515d3209895188c21f1831858692

See more details on using hashes here.

• Download URL: pocketsphinx-0.1.10.win32-py3.5.exe
• Upload date: Jun 3, 2018
• Size: 29.5 MB
• Tags: Source
• Uploaded using Trusted Publishing? No

Hashes for pocketsphinx-0.1.10.win32-py3.5.exe

Algorithm	Hash digest
SHA256	2e83eac4e4df23c62d351134f832210557d126a756b168596dbe13de2e284264
MD5	d4e4b226ae7e44b14fb65addea396769
BLAKE2b-256	5436203c62c457ff6bd28fe9eb17a82102bcbecfda6d6487a36253c9c46d1ab2

See more details on using hashes here.

• Download URL: pocketsphinx-0.1.10.win32-py2.7.exe
• Upload date: Jun 3, 2018
• Size: 29.2 MB
• Tags: Source
• Uploaded using Trusted Publishing? No

Hashes for pocketsphinx-0.1.10.win32-py2.7.exe

Algorithm	Hash digest
SHA256	5214d7eaec5650f00401e90f8bbb921bdfc475973af35897482fdba6c15fd484
MD5	94afaea6224d67c2522a9da0a6f3f3a8
BLAKE2b-256	c34b3b0f614c628b2c599cfdbc2db9d351083ec2b8fd1018bc33674ade980b42

See more details on using hashes here.

• Download URL: pocketsphinx-0.1.10-cp36-cp36m-win_amd64.whl
• Upload date: Jun 3, 2018
• Size: 29.1 MB
• Tags: CPython 3.6m, Windows x86-64
• Uploaded using Trusted Publishing? No

Hashes for pocketsphinx-0.1.10-cp36-cp36m-win_amd64.whl

Algorithm	Hash digest
SHA256	8e07e1016a3d46f4c8e88eae9b69799d50430759071e5f7e9773088aab6fb9a9
MD5	50af1a8635d3398f1e0a5b2daa474c4f
BLAKE2b-256	72138748d22cb8f91e1dc970c7134e262f0a377c666d9852a4eedbdc3791a318

See more details on using hashes here.

• Download URL: pocketsphinx-0.1.10-cp36-cp36m-win32.whl
• Upload date: Jun 3, 2018
• Size: 29.0 MB
• Tags: CPython 3.6m, Windows x86
• Uploaded using Trusted Publishing? No

Hashes for pocketsphinx-0.1.10-cp36-cp36m-win32.whl

Algorithm	Hash digest
SHA256	694cf1b53658810956e14a80e53cd6de296caaafea5bd747d316a32f1f6c2c07
MD5	b2ae6c4c87b61d2e6bf40782dbffa757
BLAKE2b-256	e8ef477fcb4fac255f706bed84b8d59dccfd9d72efb52d8498c9e55e201c9439

See more details on using hashes here.

• Download URL: pocketsphinx-0.1.10-cp35-cp35m-win_amd64.whl
• Upload date: Jun 3, 2018
• Size: 29.1 MB
• Tags: CPython 3.5m, Windows x86-64
• Uploaded using Trusted Publishing? No

Hashes for pocketsphinx-0.1.10-cp35-cp35m-win_amd64.whl

Algorithm	Hash digest
SHA256	d91f2068780a6fbf0663b857d8c9c03ea7e0598794dd04506f61af098e434542
MD5	2f9504e2816eacddcb53d873e643bacb
BLAKE2b-256	b7dde616cadca1a1d4424f8681b72cad2a956909d5bd4323cec350f235c69974

See more details on using hashes here.

• Download URL: pocketsphinx-0.1.10-cp35-cp35m-win32.whl
• Upload date: Jun 3, 2018
• Size: 29.0 MB
• Tags: CPython 3.5m, Windows x86
• Uploaded using Trusted Publishing? No

Hashes for pocketsphinx-0.1.10-cp35-cp35m-win32.whl

Algorithm	Hash digest
SHA256	ab1bb66459400fae97927f55007d9b54996c0b92dd1984423c407733a9792c23
MD5	0bfdb9761e8b41c764c44e69f78e2ac4
BLAKE2b-256	13ebbc93ea2ad2875e6ebf022e0a03be24b8a2fad2ae64531228f1e8c3b2ae07

See more details on using hashes here.

• Download URL: pocketsphinx-0.1.10-cp27-cp27m-win_amd64.whl
• Upload date: Jun 3, 2018
• Size: 29.1 MB
• Tags: CPython 2.7m, Windows x86-64
• Uploaded using Trusted Publishing? No

Hashes for pocketsphinx-0.1.10-cp27-cp27m-win_amd64.whl

Algorithm	Hash digest
SHA256	743a3fc9df3849c4040d9e875b1752070a2cbe6bbc482ba213a2da29ba46866a
MD5	705bf3329cd537ccafbb7fcabf3e6cb1
BLAKE2b-256	08234b6f112048c906c8c33e6b7a78992df504f398e243b40fb1a68bcc94a904

See more details on using hashes here.

• Download URL: pocketsphinx-0.1.10-cp27-cp27m-win32.whl
• Upload date: Jun 3, 2018
• Size: 29.0 MB
• Tags: CPython 2.7m, Windows x86
• Uploaded using Trusted Publishing? No

Hashes for pocketsphinx-0.1.10-cp27-cp27m-win32.whl

Algorithm	Hash digest
SHA256	cecfe5bfd51d4694e367294c63dfbcf6be052d8b6bc450f8c9fedce21cbdc72f
MD5	3c28af86feabed0d780febeaa72a8b7d
BLAKE2b-256	12762786da5b29a1d918103b16dceb30de7a3216d6c5c1efc06a1369d6f44adc

See more details on using hashes here.