时间戳

首页 > 解决方案 > 辣椒机器人语音识别

python - 辣椒机器人语音识别

问题描述

import os
import sys
import time
from naoqi import ALProxy
from naoqi import ALBroker
from naoqi import ALModule
import speech_recognition as sr

record = ALProxy("ALAudioRecorder", "192.168.8.104", 9559)
record.stopMicrophonesRecording()
print('Start recording...')
# tts.say("start recording...")

record.startMicrophonesRecording('/home/nao/recordings/cameras/maha1', 'wav', 16000, (0,0, 1, 0))
time.sleep(5)
record.stopMicrophonesRecording()

audio_player_service = ALProxy("ALSpeechRecognition", "192.168.8.104", 9559)

recognizer = sr.Recognizer()
audio_file_ = sr.AudioFile('/home/nao/recordings/cameras/maha1.wav') #problem is here
print(type(audio_file_))

with audio_file_ as source:
  audio_file = recognizer.record(source, duration = 8.0)
  result = recognizer.recognize_google(audio_data=audio_file, language="ar")

print(result)

这是我的代码我必须从胡椒云中检索录音，但它似乎看不到这条路径，因为它在我的笔记本电脑上运行，所以我怎样才能从胡椒云中检索音频文件

标签： pythonrobotpepper

解决方案

您可以查看包含语音识别实现的Pepper Controller Python 库（请参阅robots.py:listen()）。

推荐阅读