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.
- Windows
- Linux
- Mac OS X
# Make sure we have up-to-date versions of pip, setuptools and wheel:
$ pip install --upgrade pip setuptools wheel
$ pip install --upgrade pocketsphinxMore binary distributions for manual installation are available here.
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)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)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)
# ]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.dictAny 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 = FalseSend 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())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()])Windows requirements:
Ubuntu requirements:
$ sudo apt-get install -qq python python-dev python-pip build-essential swig git libpulse-dev$ pip install https://github.com/bambocher/pocketsphinx-python/archive/master.zip$ git clone --recursive https://github.com/bambocher/pocketsphinx-python
$ cd pocketsphinx-python
$ python setup.py install- SpeechRecognition - Library for performing speech recognition, with support for several engines and APIs, online and offline.