pocketsphinx 5.1.1

pip install pocketsphinx

Latest release

Released: Jun 6, 2026

Official Python bindings for PocketSphinx

Navigation

Verified details

These details have been verified by PyPI

Project links

GitHub Statistics

Repository

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

Documentation

Classifiers

Development Status
- 6 - Mature
License
- OSI Approved :: BSD License
Operating System
- OS Independent
Programming Language
Topic
- Multimedia :: Sound/Audio :: Speech

Report project as malware

Project description

PocketSphinx 5.1.1

This is PocketSphinx, one of Carnegie Mellon University's open source large vocabulary, speaker-independent continuous speech recognition engines.

Although this was at one point a research system, active development has largely ceased and it has become very, very far from the state of the art. I am making a release, because people are nonetheless using it, and there are a number of historical errors in the build system and API which needed to be corrected.

The version number is strangely large because there was a "release" that people are using called 5prealpha, and we will use proper semantic versioning from now on.

Please see the LICENSE file for terms of use.

Installation

You should be able to install this with pip for recent platforms and versions of Python:

pip3 install pocketsphinx

Alternately, you can also compile it from the source tree. I highly suggest doing this in a virtual environment (replace ~/ve_pocketsphinx with the virtual environment you wish to create), from the top level directory:

python3 -m venv ~/ve_pocketsphinx
. ~/ve_pocketsphinx/bin/activate
pip3 install .

On GNU/Linux and maybe other platforms, you must have PortAudio installed for the LiveSpeech class to work (we may add a fall-back to sox in the near future). On Debian-like systems this can be achieved by installing the libportaudio2 package:

sudo apt-get install libportaudio2

Usage

See the examples directory for a number of examples of using the library from Python. You can also read the documentation for the Python API or the C API.

It also mostly supports the same APIs as the previous pocketsphinx-python module, as described below.

LiveSpeech

An iterator class for continuous recognition or keyword search from a microphone. For example, to do speech-to-text with the default (some kind of US English) model:

frompocketsphinximport LiveSpeech
for phrase in LiveSpeech(): print(phrase)

Or to do keyword search:

frompocketsphinximport LiveSpeech

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

With your model and dictionary:

importos
frompocketsphinximport LiveSpeech, get_model_path

speech = LiveSpeech(
 sampling_rate=16000, # optional
 hmm=get_model_path('en-us'),
 lm=get_model_path('en-us.lm.bin'),
 dic=get_model_path('cmudict-en-us.dict')
)

for phrase in speech:
 print(phrase)

AudioFile

This is an iterator class for continuous recognition or keyword search from a file. Currently it supports only raw, single-channel, 16-bit PCM data in native byte order.

frompocketsphinximport AudioFile
for phrase in AudioFile("goforward.raw"): print(phrase) # => "go forward ten meters"

An example of a keyword search:

frompocketsphinximport AudioFile

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

With your model and dictionary:

importos
frompocketsphinximport AudioFile, get_model_path

model_path = get_model_path()

config = {
 'verbose': False,
 'audio_file': 'goforward.raw',
 'hmm': get_model_path('en-us'),
 'lm': get_model_path('en-us.lm.bin'),
 'dict': get_model_path('cmudict-en-us.dict')
}

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

Convert frame into time coordinates:

frompocketsphinximport AudioFile

# Frames per Second
fps = 100

for phrase in AudioFile(frate=fps): # frate (default=100)
 print('-' * 28)
 print('| %5s | %3s | %4s |' % ('start', 'end', 'word'))
 print('-' * 28)
 for s in phrase.seg():
 print('| %4ss | %4ss | %8s |' % (s.start_frame / fps, s.end_frame / fps, s.word))
 print('-' * 28)

# ----------------------------
# | start | end | word |
# ----------------------------
# | 0.0s | 0.24s | <s> |
# | 0.25s | 0.45s | <sil> |
# | 0.46s | 0.63s | go |
# | 0.64s | 1.16s | forward |
# | 1.17s | 1.52s | ten |
# | 1.53s | 2.11s | meters |
# | 2.12s | 2.6s | </s> |
# ----------------------------

Authors

PocketSphinx is ultimately based on Sphinx-II which in turn was based on some older systems at Carnegie Mellon University, which were released as free software under a BSD-like license thanks to the efforts of Kevin Lenzo. Much of the decoder in particular was written by Ravishankar Mosur (look for "rkm" in the comments), but various other people contributed as well, see the AUTHORS file for more details.

David Huggins-Daines (the author of this document) is guilty^H^H^H^H^Hresponsible for creating PocketSphinx which added various speed and memory optimizations, fixed-point computation, JSGF support, portability to various platforms, and a somewhat coherent API. He then disappeared for a while.

Nickolay Shmyrev took over maintenance for quite a long time afterwards, and a lot of code was contributed by Alexander Solovets, Vyacheslav Klimkov, and others. The pocketsphinx-python module was originally written by Dmitry Prazdnichnov.

Currently this is maintained by David Huggins-Daines again.

Project details

Verified details

These details have been verified by PyPI

Project links

GitHub Statistics

Repository

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

Documentation

Classifiers

Development Status
- 6 - Mature
License
- OSI Approved :: BSD License
Operating System
- OS Independent
Programming Language
Topic
- Multimedia :: Sound/Audio :: Speech

Release history Release notifications | RSS feed

This version

Algorithm	Hash digest
SHA256	`675778b309a22dfc9b7d37f7621976bba491d2a5f8c59696bd77fd6d07271355`
MD5	`726fe0e3fae63a26609ec4030c731e59`
BLAKE2b-256	`61e713e0e787ff467218de880310d79cba14424f13b87171ac44af0bde1e428c`

Algorithm	Hash digest
SHA256	`2ba7e6789a67119f581b85d156e523cd1876af5d30ebacbf7ed3cd85f61ec382`
MD5	`87731d9a0ceaf0f3869654432b865599`
BLAKE2b-256	`43d32ba1b70b1995f298bdc2430e78d40bb989fe390f685153c59513692e67bd`

Algorithm	Hash digest
SHA256	`0ffe854397b11546a9f629472367c8b668583a5ebfefbc129a80875e0ec70bee`
MD5	`0606187e8c1070db0a4f124ab41c31cd`
BLAKE2b-256	`6af5b29391d051323e95f3408b2400f459f6e86e5b8449bfd38f80eb18bb3e63`

Algorithm	Hash digest
SHA256	`9328118d15c150b88885d79765e663f3c42a3601bb8c15e9ff42f44428b10d61`
MD5	`d5792298b96a1b546eba364dbc9f6132`
BLAKE2b-256	`17cc082f70632d6474052cace9c4cc4b0ce8666eb4b52553187b05d15c0e65d6`

Algorithm	Hash digest
SHA256	`38ff34e47b35f0caa1b58939806c4ab86c234a13536299c8c929a3cb45761941`
MD5	`9949e6aae47a4fa8defcb7ad37af3024`
BLAKE2b-256	`d132630fb5b204d354fbf408218e8c9019354d33c70d0b647eb52f8d4d0ab86e`

Algorithm	Hash digest
SHA256	`c6741bebbec5a10d08971bd2fdc0a6c1f876ad20a27f73c598e81654612794d6`
MD5	`93f54c987de543e3e6c227a39ba07794`
BLAKE2b-256	`209f74d921c7338dbd7cd40609b0a1b5e7a5e5a2acd23aaa2f6004fb729639cc`

Algorithm	Hash digest
SHA256	`8de78671858278dbe97bf9578ea25a70ac2162d49a3218155c874058ba4554fc`
MD5	`9495117b22179b9f73faee33b40cd24a`
BLAKE2b-256	`06e1c2820011a5a1c8931f50d9add2af4591a0f531b2d810bc0fe1bf048079ef`

Algorithm	Hash digest
SHA256	`08e4d5cc7377932dae2e55191b34f9939d73bf2401046ca2bd03be6daf21ac3b`
MD5	`4bbb4eaa648a19cc9f86c99d0a9b9782`
BLAKE2b-256	`70f3a44c87be7e434866bf575c343fddc8f2b61065f831c747dd6af3d3702f21`

Algorithm	Hash digest
SHA256	`00fc4a43cbb2d2620557603c9d1d6a1d54998b13e1406d449a5d674a5309893c`
MD5	`55865e237cd561a535cd38d461c8edfa`
BLAKE2b-256	`93215b75e1487b98de1442ffbcb2df704beedf22905011d40c3cc1d99ebb76f0`

Algorithm	Hash digest
SHA256	`b29b014241edce4437a55b8743a3156deb0d383c919e923eac099e2fb16f8c14`
MD5	`16102941ec5fe130bc88887ad6f52938`
BLAKE2b-256	`49948d3beb892983cc44098a93ffd54241047902c347accb991669029497943f`

Algorithm	Hash digest
SHA256	`bb8fd0fc7fb08dd8f85da21f5121f34ebf4186a5bee91ce85e2d358e69a448bf`
MD5	`66f75c138a1c4d6a1fd857faf927f735`
BLAKE2b-256	`7434d9db696560de8ea7347f630630b9f9e988093dc52ff02ea6bf1b6d41f21c`

Algorithm	Hash digest
SHA256	`4742dc42c010caf5a2558cac910b0856d85c94e9bb0357ed4ff32f1f0d0837f9`
MD5	`e75d518f7123cf53dfd1c65b43c6d71b`
BLAKE2b-256	`9556e0da7c96e3af9b0fbca3db46a9a6c5389642ec17ff4a7fb1cde592db023b`

Algorithm	Hash digest
SHA256	`8cd1ae6f236c2d1941643d87b9136317f628878892fbcb873ab2795f715144d3`
MD5	`ca93b93fc9b554b783b7dcc6b50da16c`
BLAKE2b-256	`2acf1493946809382b0d60319fe338efb5141173ec58eb9ab5ca8c211d7cae4f`

URL: https://pypi.org/project/pocketsphinx/

⇱ pocketsphinx · PyPI

pocketsphinx 5.1.1

Navigation

Verified details

Project links

GitHub Statistics

Maintainers

Unverified details

Project links

Meta

Classifiers

Project description

PocketSphinx 5.1.1

Installation

Usage

LiveSpeech

AudioFile

Authors

Project details

Verified details

Project links

GitHub Statistics

Maintainers

Unverified details

Project links

Meta

Classifiers

Release history Release notifications | RSS feed

Download files

Source Distribution

Built Distributions

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance