从麦克风识别蟒蛇口袋斯芬克斯

Question

我已经在python中安装和安装了pocketsphinx和sphinxbase包。我还为github获取了语音识别代码，并根据需要更改了数据和模式目录，但当我试图通过“python test.py”运行它时，它仍然无法通过语音进行流式传输。下面是代码：

#!/usr/bin/env python
import os
import sphinxbase as sb
import pocketsphinx as ps

MODELDIR = '/usr/lib/python2.7/site-packages/speech_recognition/pocketsphinx-data'
DATADIR='/usr/lib/python2.7/site-packages/speech_recognition/pocketsphinx-data'
# Create a decoder with certain model
config = ps.Decoder.default_config()
config.set_string('-hmm', "/usr/lib/python2.7/site-packages/speech_recognition/pocketsphinx-data/en-US/acoustic-model")
config.set_string('-lm', os.path.join(MODELDIR, 'en-US/language-model.lm.bin'))
config.set_string('-dict', os.path.join(MODELDIR, 'en-US/pronounciation-dictionary.dict'))
decoder = ps.Decoder(config)

# Decode streaming data.
decoder.start_utt()
stream = open(os.path.join(DATADIR, 'en-US/goforward.raw'), 'rb')
while True: 
    buf = stream.read(1024)
    if buf:
        decoder.process_raw(buf, False, False)
    else:
        break
decoder.end_utt()
stream.close()
print('Best hypothesis segments:', [seg.word for seg in decoder.seg()])

请告诉我如何执行它。

Answer 1

麦克风的持续识别应该如下所示：

#!/usr/bin/python

from os import environ, path
import pyaudio

from pocketsphinx.pocketsphinx import *
from sphinxbase.sphinxbase import *

MODELDIR = "../../../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'))
decoder = Decoder(config)

p = pyaudio.PyAudio()
stream = p.open(format=pyaudio.paInt16, channels=1, rate=16000, input=True, frames_per_buffer=1024)
stream.start_stream() 

in_speech_bf = False
decoder.start_utt()
while True:
    buf = stream.read(1024)
    if buf:
        decoder.process_raw(buf, False, False)
        if decoder.get_in_speech() != in_speech_bf:
            in_speech_bf = decoder.get_in_speech()
            if not in_speech_bf:
                decoder.end_utt()
                print 'Result:', decoder.hyp().hypstr
                decoder.start_utt()
    else:
        break
decoder.end_utt()