我的目标是制作我的贾维斯，它会一直监听并在我打招呼时激活。我了解到 Google 云 Speech to Text API 的监听时间不会超过 60 秒，但后来我发现了这个不太出名的链接，它可以监听无限的持续时间。 github脚本的作者说，他玩了一个技巧，脚本在60秒后刷新，这样程序就不会崩溃。
以下是修改后的版本，因为我想让它回答我的问题，然后是“你好”，而不是一直回答我。现在，如果我问我的 Jarvis，一个问题，虽然回答需要 60 秒以上，而且没有时间刷新，但程序会崩溃:(
#!/usr/bin/env python
# Copyright 2018 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Google Cloud Speech API sample application using the streaming API.
NOTE: This module requires the additional dependency `pyaudio`. To install
using pip:
pip install pyaudio
Example usage:
python transcribe_streaming_indefinite.py
"""
# [START speech_transcribe_infinite_streaming]
from __future__ import division
import time
import re
import sys
import os
from google.cloud import speech
from pygame.mixer import *
from googletrans import Translator
# running=True
translator = Translator()
init()
import pyaudio
from six.moves import queue
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "C:\\Users\\mnauf\\Desktop\\rehandevice\\key.json"
from commands2 import commander
cmd=commander()
# Audio recording parameters
STREAMING_LIMIT = 55000
SAMPLE_RATE = 16000
CHUNK_SIZE = int(SAMPLE_RATE / 10) # 100ms
def get_current_time():
return int(round(time.time() * 1000))
def duration_to_secs(duration):
return duration.seconds + (duration.nanos / float(1e9))
class ResumableMicrophoneStream:
"""Opens a recording stream as a generator yielding the audio chunks."""
def __init__(self, rate, chunk_size):
self._rate = rate
self._chunk_size = chunk_size
self._num_channels = 1
self._max_replay_secs = 5
# Create a thread-safe buffer of audio data
self._buff = queue.Queue()
self.closed = True
self.start_time = get_current_time()
# 2 bytes in 16 bit samples
self._bytes_per_sample = 2 * self._num_channels
self._bytes_per_second = self._rate * self._bytes_per_sample
self._bytes_per_chunk = (self._chunk_size * self._bytes_per_sample)
self._chunks_per_second = (
self._bytes_per_second // self._bytes_per_chunk)
def __enter__(self):
self.closed = False
self._audio_interface = pyaudio.PyAudio()
self._audio_stream = self._audio_interface.open(
format=pyaudio.paInt16,
channels=self._num_channels,
rate=self._rate,
input=True,
frames_per_buffer=self._chunk_size,
# Run the audio stream asynchronously to fill the buffer object.
# This is necessary so that the input device's buffer doesn't
# overflow while the calling thread makes network requests, etc.
stream_callback=self._fill_buffer,
)
return self
def __exit__(self, type, value, traceback):
self._audio_stream.stop_stream()
self._audio_stream.close()
self.closed = True
# Signal the generator to terminate so that the client's
# streaming_recognize method will not block the process termination.
self._buff.put(None)
self._audio_interface.terminate()
def _fill_buffer(self, in_data, *args, **kwargs):
"""Continuously collect data from the audio stream, into the buffer."""
self._buff.put(in_data)
return None, pyaudio.paContinue
def generator(self):
while not self.closed:
if get_current_time() - self.start_time > STREAMING_LIMIT:
self.start_time = get_current_time()
break
# Use a blocking get() to ensure there's at least one chunk of
# data, and stop iteration if the chunk is None, indicating the
# end of the audio stream.
chunk = self._buff.get()
if chunk is None:
return
data = [chunk]
# Now consume whatever other data's still buffered.
while True:
try:
chunk = self._buff.get(block=False)
if chunk is None:
return
data.append(chunk)
except queue.Empty:
break
yield b''.join(data)
def search(responses, stream, code):
responses = (r for r in responses if (
r.results and r.results[0].alternatives))
num_chars_printed = 0
for response in responses:
if not response.results:
continue
# The `results` list is consecutive. For streaming, we only care about
# the first result being considered, since once it's `is_final`, it
# moves on to considering the next utterance.
result = response.results[0]
if not result.alternatives:
continue
# Display the transcription of the top alternative.
top_alternative = result.alternatives[0]
transcript = top_alternative.transcript
# music.load("/home/pi/Desktop/rehandevice/end.mp3")
# music.play()
# Display interim results, but with a carriage return at the end of the
# line, so subsequent lines will overwrite them.
# If the previous result was longer than this one, we need to print
# some extra spaces to overwrite the previous result
overwrite_chars = ' ' * (num_chars_printed - len(transcript))
if not result.is_final:
sys.stdout.write(transcript + overwrite_chars + '\r')
sys.stdout.flush()
num_chars_printed = len(transcript)
else:
#print(transcript + overwrite_chars)
# Exit recognition if any of the transcribed phrases could be
# one of our keywords.
if code=='ur-PK':
transcript=translator.translate(transcript).text
print("Your command: ", transcript + overwrite_chars)
if "hindi assistant" in (transcript+overwrite_chars).lower():
cmd.respond("Alright. Talk to me in urdu",code=code)
main('ur-PK')
elif "english assistant" in (transcript+overwrite_chars).lower():
cmd.respond("Alright. Talk to me in English",code=code)
main('en-US')
cmd.discover(text=transcript + overwrite_chars,code=code)
for i in range(10):
print("Hello world")
break
num_chars_printed = 0
def listen_print_loop(responses, stream, code):
"""Iterates through server responses and prints them.
The responses passed is a generator that will block until a response
is provided by the server.
Each response may contain multiple results, and each result may contain
multiple alternatives; for details, see https://cloud.google.com/speech-to-text/docs/reference/rpc/google.cloud.speech.v1#streamingrecognizeresponse. Here we
print only the transcription for the top alternative of the top result.
In this case, responses are provided for interim results as well. If the
response is an interim one, print a line feed at the end of it, to allow
the next result to overwrite it, until the response is a final one. For the
final one, print a newline to preserve the finalized transcription.
"""
responses = (r for r in responses if (
r.results and r.results[0].alternatives))
music.load(r"C:\\Users\\mnauf\\Desktop\\rehandevice\\coins.mp3")
num_chars_printed = 0
for response in responses:
if not response.results:
continue
# The `results` list is consecutive. For streaming, we only care about
# the first result being considered, since once it's `is_final`, it
# moves on to considering the next utterance.
result = response.results[0]
if not result.alternatives:
continue
# Display the transcription of the top alternative.
top_alternative = result.alternatives[0]
transcript = top_alternative.transcript
# Display interim results, but with a carriage return at the end of the
# line, so subsequent lines will overwrite them.
#
# If the previous result was longer than this one, we need to print
# some extra spaces to overwrite the previous result
overwrite_chars = ' ' * (num_chars_printed - len(transcript))
if not result.is_final:
sys.stdout.write(transcript + overwrite_chars + '\r')
sys.stdout.flush()
num_chars_printed = len(transcript)
else:
print("Listen print loop", transcript + overwrite_chars)
# Exit recognition if any of the transcribed phrases could be
# one of our keywords.
if re.search(r'\b(hello)\b', transcript.lower(), re.I):
#print("Give me order")
music.play()
search(responses, stream,code)
break
elif re.search(r'\b(ہیلو)\b', transcript, re.I):
music.play()
search(responses, stream,code)
break
num_chars_printed = 0
def main(code):
cmd.respond("I am Rayhaan dot A Eye. How can I help you?",code=code)
client = speech.SpeechClient()
config = speech.types.RecognitionConfig(
encoding=speech.enums.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=SAMPLE_RATE,
language_code='en-US',
max_alternatives=1,
enable_word_time_offsets=True)
streaming_config = speech.types.StreamingRecognitionConfig(
config=config,
interim_results=True)
mic_manager = ResumableMicrophoneStream(SAMPLE_RATE, CHUNK_SIZE)
print('Say "Quit" or "Exit" to terminate the program.')
with mic_manager as stream:
while not stream.closed:
audio_generator = stream.generator()
requests = (speech.types.StreamingRecognizeRequest(
audio_content=content)
for content in audio_generator)
responses = client.streaming_recognize(streaming_config,
requests)
# Now, put the transcription responses to use.
try:
listen_print_loop(responses, stream, code)
except:
listen
if __name__ == '__main__':
main('en-US')
# [END speech_transcribe_infinite_streaming]
您可以在不同线程中识别后调用您的函数。示例：
new_thread = Thread(target=music.play)
new_thread.daemon = True # Not always needed, read more about daemon property
new_thread.start()
或者如果你只是想防止异常 - 你可以随时使用 try/ except 。示例：
with mic_manager as stream:
while not stream.closed:
try:
audio_generator = stream.generator()
requests = (speech.types.StreamingRecognizeRequest(
audio_content=content)
for content in audio_generator)
responses = client.streaming_recognize(streaming_config,
requests)
# Now, put the transcription responses to use.
listen_print_loop(responses, stream, code)
except BaseException as e:
print("Exception occurred - {}".format(str(e)))
我认为目前此功能仅由语音 v2 提供，如语音 v1 文档所建议的那样
实际上指的是最新版本实现该功能。