Speech recognition 口袋狮身人面像切割文字

我有个问题。当我通过控制台打开pocketsphinx时，一切正常：

pi@raspberrypi:~ $ pocketsphinx_continuous -hmm /usr/local/share/pocketsphinx/model/en-us/en-us -lm 6764.lm -dict 6764.dic -samprate 16000 -inmic yes -adcdev plughw:0,0

然而，当我尝试用python脚本运行它时，pocketsphinx识别出错误的单词

这是python脚本的代码：

import sys, os, pyaudio
from pocketsphinx.pocketsphinx import *
from sphinxbase.sphinxbase import *

modeldir = "/home/pi/Downloads/sphinx4-5prealpha-src/sphinx4-data/src/main/resources/edu/cmu/sphinx/models/"

# Create a decoder with certain model
config = Decoder.default_config()
config.set_string('-hmm', os.path.join(modeldir, 'en-us/en-us'))
config.set_string('-dict', '/home/pi/Downloads/6764.dic')
config.set_string('-lm', '/home/pi/Downloads/6764.lm')
config.set_string('-samprate', '16000')

config.set_string('-adcdev', 'plughw:0,0')         

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

decoder = Decoder(config)
decoder.start_utt()
print ("RECOGNITION STARTED")


while True:
    buf = stream.read(1024)


    decoder.process_raw(buf, False, False)

    if decoder.hyp() != None:
        print ([(seg.word, seg.prob, seg.start_frame, seg.end_frame) for seg in decoder.seg()])
        print ("Detected keyword, restarting search")          

        decoder.end_utt()
        decoder.start_utt()

---

我不知道怎么了。

试着用r.recognizer\u sphinx（音频）来识别，而不是

decoder.start_utt() try 
stream.recognize_sphinx(audio)

您也可以尝试以下方法：

import speech_recognition
import pyttsx3

speech_engine = pyttsx3.init('sapi5') 
speech_engine.setProperty('rate', 150)

def speak(text):
     speech_engine.say(text)
     speech_engine.runAndWait()

recognizer = speech_recognition.Recognizer()

def listen():
    with speech_recognition.Microphone() as source:
        recognizer.adjust_for_ambient_noise(source)
        audio = recognizer.listen(source)

    try:
        return recognizer.recognize_sphinx(audio)

    except speech_recognition.UnknownValueError:
        print("Could not understand audio")
    except speech_recognition.RequestError as e:
        print("Recog Error; {0}".format(e))

    return ""

speak("Say something!")
speak("I heard you say " + listen())
print(listen())

---

对于连续示例，您使用了错误的代码。正确的代码如下：