Skip to content

Commit

Permalink
Move mic samples out of cloud-client so that cloud-client samples can…
Browse files Browse the repository at this point in the history
  • Loading branch information
nnegrey authored and busunkim96 committed Sep 3, 2020
1 parent 9789750 commit 26b530d
Show file tree
Hide file tree
Showing 7 changed files with 593 additions and 0 deletions.
82 changes: 82 additions & 0 deletions packages/google-cloud-speech/samples/microphone/README.rst
Original file line number Diff line number Diff line change
@@ -0,0 +1,82 @@
.. This file is automatically generated. Do not edit this file directly.
Google Cloud Speech API Python Samples
===============================================================================

.. image:: https://gstatic.com/cloudssh/images/open-btn.png
:target: https://console.cloud.google.com/cloudshell/open?git_repo=https://github.com/GoogleCloudPlatform/python-docs-samples&page=editor&open_in_editor=speech/microphone/README.rst


This directory contains samples for Google Cloud Speech API. The `Google Cloud Speech API`_ enables easy integration of Google speech recognition technologies into developer applications. Send audio and receive a text transcription from the Cloud Speech API service.

- See the `migration guide`_ for information about migrating to Python client library v0.27.

.. _migration guide: https://cloud.google.com/speech/docs/python-client-migration




.. _Google Cloud Speech API: https://cloud.google.com/speech/docs/

Setup
-------------------------------------------------------------------------------


Authentication
++++++++++++++

This sample requires you to have authentication setup. Refer to the
`Authentication Getting Started Guide`_ for instructions on setting up
credentials for applications.

.. _Authentication Getting Started Guide:
https://cloud.google.com/docs/authentication/getting-started

Install Dependencies
++++++++++++++++++++

#. Clone python-docs-samples and change directory to the sample directory you want to use.

.. code-block:: bash
$ git clone https://github.com/GoogleCloudPlatform/python-docs-samples.git
#. Install `pip`_ and `virtualenv`_ if you do not already have them. You may want to refer to the `Python Development Environment Setup Guide`_ for Google Cloud Platform for instructions.

.. _Python Development Environment Setup Guide:
https://cloud.google.com/python/setup

#. Create a virtualenv. Samples are compatible with Python 2.7 and 3.4+.

.. code-block:: bash
$ virtualenv env
$ source env/bin/activate
#. Install the dependencies needed to run the samples.

.. code-block:: bash
$ pip install -r requirements.txt
.. _pip: https://pip.pypa.io/
.. _virtualenv: https://virtualenv.pypa.io/



The client library
-------------------------------------------------------------------------------

This sample uses the `Google Cloud Client Library for Python`_.
You can read the documentation for more details on API usage and use GitHub
to `browse the source`_ and `report issues`_.

.. _Google Cloud Client Library for Python:
https://googlecloudplatform.github.io/google-cloud-python/
.. _browse the source:
https://github.com/GoogleCloudPlatform/google-cloud-python
.. _report issues:
https://github.com/GoogleCloudPlatform/google-cloud-python/issues


.. _Google Cloud SDK: https://cloud.google.com/sdk/
24 changes: 24 additions & 0 deletions packages/google-cloud-speech/samples/microphone/README.rst.in
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
# This file is used to generate README.rst

product:
name: Google Cloud Speech API
short_name: Cloud Speech API
url: https://cloud.google.com/speech/docs/
description: >
The `Google Cloud Speech API`_ enables easy integration of Google speech
recognition technologies into developer applications. Send audio and receive
a text transcription from the Cloud Speech API service.


- See the `migration guide`_ for information about migrating to Python client library v0.27.


.. _migration guide: https://cloud.google.com/speech/docs/python-client-migration

setup:
- auth
- install_deps

cloud_client_library: true

folder: speech/microphone
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
google-cloud-speech==0.36.3
pyaudio==0.2.11
six==1.12.0
Binary file not shown.
Original file line number Diff line number Diff line change
@@ -0,0 +1,223 @@
#!/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

from google.cloud import speech

import pyaudio
from six.moves import queue

# 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 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; for details, see https://goo.gl/tjCPAU. 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))

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(transcript + overwrite_chars)

# 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):
print('Exiting..')
stream.closed = True
break

num_chars_printed = 0


def main():
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.
listen_print_loop(responses, stream)


if __name__ == '__main__':
main()
# [END speech_transcribe_infinite_streaming]
Loading

0 comments on commit 26b530d

Please sign in to comment.