我正在使用以下python脚本从实时流式音频输入中获取来自Google Speech API的预测。
问题是，我需要从Google语音API对每个语音进行预测，然后还要将语音的每个语音保存到磁盘中。
我不确定如何修改脚本以保存每个语音的实时音频，并打印每个语音的结果而不是连续预测。
#!/usr/bin/env python
import os
import re
import sys
import time
from google.cloud import speech
import pyaudio
from six.moves import queue
# Audio recording parameters
STREAMING_LIMIT = 240000 # 4 minutes
SAMPLE_RATE = 16000
CHUNK_SIZE = int(SAMPLE_RATE / 10) # 100ms
api_key = r'path_to_json_file\google.json'
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = api_key
RED = '\033[0;31m'
GREEN = '\033[0;32m'
YELLOW = '\033[0;33m'
def get_current_time():
"""Return Current Time in MS."""
return int(round(time.time() * 1000))
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._buff = queue.Queue()
self.closed = True
self.start_time = get_current_time()
self.restart_counter = 0
self.audio_input = []
self.last_audio_input = []
self.result_end_time = 0
self.is_final_end_time = 0
self.final_request_end_time = 0
self.bridging_offset = 0
self.last_transcript_was_final = False
self.new_stream = True
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,
)
def __enter__(self):
self.closed = False
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):
"""Stream Audio from microphone to API and to local buffer"""
while not self.closed:
data = []
if self.new_stream and self.last_audio_input:
chunk_time = STREAMING_LIMIT / len(self.last_audio_input)
if chunk_time != 0:
if self.bridging_offset < 0:
self.bridging_offset = 0
if self.bridging_offset > self.final_request_end_time:
self.bridging_offset = self.final_request_end_time
chunks_from_ms = round((self.final_request_end_time -
self.bridging_offset) / chunk_time)
self.bridging_offset = (round((
len(self.last_audio_input) - chunks_from_ms)
* chunk_time))
for i in range(chunks_from_ms, len(self.last_audio_input)):
data.append(self.last_audio_input[i])
self.new_stream = False
# 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()
self.audio_input.append(chunk)
if chunk is None:
return
data.append(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)
self.audio_input.append(chunk)
except queue.Empty:
break
yield b''.join(data)
def listen_print_loop(responses, stream):
"""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; 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.
"""
for response in responses:
if get_current_time() - stream.start_time > STREAMING_LIMIT:
stream.start_time = get_current_time()
break
if not response.results:
continue
result = response.results[0]
if not result.alternatives:
continue
transcript = result.alternatives[0].transcript
result_seconds = 0
result_nanos = 0
if result.result_end_time.seconds:
result_seconds = result.result_end_time.seconds
if result.result_end_time.nanos:
result_nanos = result.result_end_time.nanos
stream.result_end_time = int((result_seconds * 1000)
+ (result_nanos / 1000000))
corrected_time = (stream.result_end_time - stream.bridging_offset
+ (STREAMING_LIMIT * stream.restart_counter))
# Display interim results, but with a carriage return at the end of the
# line, so subsequent lines will overwrite them.
if result.is_final:
sys.stdout.write(GREEN)
sys.stdout.write('\033[K')
sys.stdout.write(str(corrected_time) + ': ' + transcript + '\n')
stream.is_final_end_time = stream.result_end_time
stream.last_transcript_was_final = True
# Exit recognition if any of the transcribed phrases could be
# one of our keywords.
if re.search(r'\b(exit|quit)\b', transcript, re.I):
sys.stdout.write(YELLOW)
sys.stdout.write('Exiting...\n')
stream.closed = True
break
else:
sys.stdout.write(RED)
sys.stdout.write('\033[K')
sys.stdout.write(str(corrected_time) + ': ' + transcript + '\r')
stream.last_transcript_was_final = False
def main():
"""start bidirectional streaming from microphone input to speech API"""
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)
streaming_config = speech.types.StreamingRecognitionConfig(
config=config,
interim_results=True)
mic_manager = ResumableMicrophoneStream(SAMPLE_RATE, CHUNK_SIZE)
print(mic_manager.chunk_size)
sys.stdout.write(YELLOW)
sys.stdout.write('\nListening, say "Quit" or "Exit" to stop.\n\n')
sys.stdout.write('End (ms) Transcript Results/Status\n')
sys.stdout.write('=====================================================\n')
with mic_manager as stream:
while not stream.closed:
sys.stdout.write(YELLOW)
sys.stdout.write('\n' + str(
STREAMING_LIMIT * stream.restart_counter) + ': NEW REQUEST\n')
stream.audio_input = []
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)
if stream.result_end_time > 0:
stream.final_request_end_time = stream.is_final_end_time
stream.result_end_time = 0
stream.last_audio_input = []
stream.last_audio_input = stream.audio_input
stream.audio_input = []
stream.restart_counter = stream.restart_counter + 1
if not stream.last_transcript_was_final:
sys.stdout.write('\n')
stream.new_stream = True
if __name__ == '__main__':
main()
答案 0 :(得分：2)
对于我来说，很难理解这段代码中发生的一切，并且我不想为尝试使用许可证而付钱，但是这里有一些想法。也许其他人会发现它们有用，并且可以为您提供进一步的帮助。
首先，将句子从语音中分离出来的一个大问题是，并不是每个人在句子之间都遵循相同的停顿。有些人将等待更长的时间，而另一些人将继续耕种下一个。有些人在句子中也会停顿。如果您要这样做，就很难从音频数据中检测句子的结尾，就像尝试检测暂停一样相对简单。
我能想到的最好的方法是使用从Google Speech API中获得的解释并在结束标点符号（!，?，.上拆分）。然后，您的问题将减少为将返回的响应与特定的音频数据块相关联。
看起来您可以将None返回给生成器，并且它已经可以正常结束了，所以应该不会太糟。当您决定结束句子时，您将想要保存生成成绩单的所有音频数据块。
这可能很难，因为当接收到更多音频时，Google Speech API可能会追溯地判断一个完整的句子实际上不是完整的，而是较长句子的一部分，因此您也需要注意这一点。
关于保存原始音频数据，一旦知道哪些块适用于什么转录，只需将它们全部附加到一个列表（例如list_of_chunks）上，然后使用wave：
import wave
with wave.open("foo.wav", 'wb') as f:
f.setnchannels(self._num_channels)
f.setsampwidth(audio.get_sample_size(pyaudio.paInt16))
f.setframerate(self._rate)
f.writeframes(b''.join(list_of_chunks))
如果您在num_channels类之外进行学习，当然必须使rate和ResumableMicrophoneStream可以访问。
答案 1 :(得分：0)
您可以使用“ StreamingRecognitionConfig”来检测单个话语。一旦检测到第一个暂停/静音，API就会停止并返回结果。这对于短命令很有用。除了单个语音，我还没有发现任何类似的选项可以检测多种语音。
https://cloud.google.com/speech-to-text/docs/basics
以下设置将为您提供所标识单词的标点符号和时间信息。也许您可以使用它们来完成@ matthew-salvatore-viglione的建议（即，通过标点符号分隔句子，然后使用单词时间列表来标识音频文件中的各个部分。如果您不使用流式识别，则不应该也不必担心追溯性语音识别问题。
{ “ enableWordTimeOffsets”：布尔值， “ enableAutomaticPunctuation”：布尔值， ..... }
https://cloud.google.com/speech-to-text/docs/reference/rest/v1/RecognitionConfig
在深入了解Google语音识别API之前，建议您还先看看其他语音识别服务，看看它们是否提供了喜欢的句子检测功能（发音与句子不同）。