85 lines
3.2 KiB
Python
85 lines
3.2 KiB
Python
# ====================================================================
|
|
# Copyright (c) 2013 Carnegie Mellon University. All rights
|
|
# reserved.
|
|
#
|
|
# Redistribution and use in source and binary forms, with or without
|
|
# modification, are permitted provided that the following conditions
|
|
# are met:
|
|
#
|
|
# 1. Redistributions of source code must retain the above copyright
|
|
# notice, this list of conditions and the following disclaimer.
|
|
#
|
|
# 2. Redistributions in binary form must reproduce the above copyright
|
|
# notice, this list of conditions and the following disclaimer in
|
|
# the documentation and/or other materials provided with the
|
|
# distribution.
|
|
#
|
|
# This work was supported in part by funding from the Defense Advanced
|
|
# Research Projects Agency and the National Science Foundation of the
|
|
# United States of America, and the CMU Sphinx Speech Consortium.
|
|
#
|
|
# THIS SOFTWARE IS PROVIDED BY CARNEGIE MELLON UNIVERSITY ``AS IS'' AND
|
|
# ANY EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
|
|
# THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
|
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL CARNEGIE MELLON UNIVERSITY
|
|
# NOR ITS EMPLOYEES BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
|
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
#
|
|
# ====================================================================
|
|
|
|
|
|
from os import environ, path
|
|
|
|
|
|
from pocketsphinx.pocketsphinx import *
|
|
from sphinxbase.sphinxbase import *
|
|
|
|
MODELDIR = "../../../model"
|
|
DATADIR = "../../../test/data"
|
|
|
|
# Create a decoder with certain model
|
|
config = Decoder.default_config()
|
|
config.set_string('-hmm', path.join(MODELDIR, 'en-us/en-us'))
|
|
config.set_string('-lm', path.join(MODELDIR, 'en-us/en-us.lm.bin'))
|
|
config.set_string('-dict', path.join(MODELDIR, 'en-us/cmudict-en-us.dict'))
|
|
|
|
# Decode streaming data.
|
|
decoder = Decoder(config)
|
|
|
|
print ("Pronunciation for word 'hello' is ", decoder.lookup_word("hello"))
|
|
print ("Pronunciation for word 'abcdf' is ", decoder.lookup_word("abcdf"))
|
|
|
|
decoder.start_utt()
|
|
stream = open(path.join(DATADIR, 'goforward.raw'), 'rb')
|
|
while True:
|
|
buf = stream.read(1024)
|
|
if buf:
|
|
decoder.process_raw(buf, False, False)
|
|
else:
|
|
break
|
|
decoder.end_utt()
|
|
|
|
hypothesis = decoder.hyp()
|
|
print ('Best hypothesis: ', hypothesis.hypstr, " model score: ", hypothesis.best_score, " confidence: ", hypothesis.prob)
|
|
|
|
print ('Best hypothesis segments: ', [seg.word for seg in decoder.seg()])
|
|
|
|
# Access N best decodings.
|
|
print ('Best 10 hypothesis: ')
|
|
for best, i in zip(decoder.nbest(), range(10)):
|
|
print (best.hypstr, best.score)
|
|
|
|
stream = open(path.join(DATADIR, 'goforward.mfc'), 'rb')
|
|
stream.read(4)
|
|
buf = stream.read(13780)
|
|
decoder.start_utt()
|
|
decoder.process_cep(buf, False, True)
|
|
decoder.end_utt()
|
|
hypothesis = decoder.hyp()
|
|
print ('Best hypothesis: ', hypothesis.hypstr, " model score: ", hypothesis.best_score, " confidence: ", hypothesis.prob)
|