Stream.py

"""
Code Adapted from Google Cloud API Tutorials for use in
TamuHack 2020 by Jack Wang
January 20th, 2020
"""

from __future__ import division

import re
import sys
import os

from google.cloud import speech
from google.cloud.speech import enums
from google.cloud.speech import types
from gtts import gTTS
import nltk

import pyaudio
from pydub import AudioSegment
from pydub.playback import play


from six.moves import queue

# Manually setting environment variable
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = os.path.join(os.getcwd(), "Google_Key/Blind_Assistance.json")


# Audio recording parameters
RATE = 16000
CHUNK = int(RATE / 10)  # 100ms


class MicrophoneStream(object):
    """Opens a recording stream as a generator yielding the audio chunks."""
    def __init__(self, rate, chunk):
        self._rate = rate
        self._chunk = chunk

        # Create a thread-safe buffer of audio data
        self._buff = queue.Queue()
        self.closed = True
        self.obj = ""

    def __enter__(self):
        self._audio_interface = pyaudio.PyAudio()
        self._audio_stream = self._audio_interface.open(
            format=pyaudio.paInt16,
            # The API currently only supports 1-channel (mono) audio
            # https://goo.gl/z757pE
            channels=1, rate=self._rate,
            input=True, frames_per_buffer=self._chunk,
            # 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,
        )

        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, frame_count, time_info, status_flags):
        """Continuously collect data from the audio stream, into the buffer."""
        self._buff.put(in_data)
        return None, pyaudio.paContinue

    def play_audio(self, text):
        output = gTTS(text=text, lang='en', slow=False)
        output.save("Temp/output.mp3")
        song = AudioSegment.from_mp3("Temp/output.mp3")
        self._audio_stream.stop_stream()
        play(song)
        self._audio_stream.start_stream()
        os.remove("Temp/output.mp3")

    def generator(self):
        while not self.closed:
            # 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)
                    if len(data) > 1:
                        break
                except queue.Empty:
                    break

            yield b''.join(data)


def listen_print_loop(responses, stream, category_index):
    """Iterates through server responses and prints them.

    The responses passed is a generator that will block until a response
    is provided by the server. *Modifed to stop at only one full response*

    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.
    """
    num_chars_printed = 0
    prompted = False
    listening = False
    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.
        transcript = result.alternatives[0].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:
            is_noun = lambda pos: pos == 'NN'
            is_bin_response = lambda pos: pos == 'UH'or pos == 'NNS'
            is_command = lambda pos: pos == 'VB' or pos == 'RP'
            print(transcript + overwrite_chars)
            if not prompted:
                tokenized = nltk.word_tokenize(transcript)
                nouns = [word for (word, pos) in nltk.pos_tag(tokenized) if is_command(pos)]
                if "wake" in nouns and "up" in nouns:
                    stream.play_audio('Listening, what are you looking for?')
                    prompted = True
            elif prompted and not listening:
                # confirmation
                tokenized = nltk.word_tokenize(transcript)
                nouns = [word for (word, pos) in nltk.pos_tag(tokenized) if is_noun(pos)]
                if len(nouns) > 0:
                    stream.obj = nouns[0]
                if stream.obj not in category_index:
                    stream.play_audio("Sorry, I cannot detect " + stream.obj + ". Please ask for a different object." )
                else:
                    stream.play_audio("Are you looking for "+stream.obj+"?")
                    listening = True
            elif prompted and listening:
                tokenized = nltk.word_tokenize(transcript)
                responses = [word for (word, pos) in nltk.pos_tag(tokenized) if is_bin_response(pos)]
                print(responses)
                if re.search(r'\b(Yes|Yeah|Sure|Yep)\b', " ".join(responses), re.I):
                    stream.play_audio("Okay, looking for "+stream.obj)
                    return str.strip(stream.obj)
                elif re.search(r'\b(No|no|nope|nah)\b', " ".join(responses), re.I):
                    stream.play_audio("What are you looking for?")
                    listening = False
                else:
                    listening = False
                    stream.play_audio("Didn't understand. What are you looking for?")


def main(category_index):
    category_index = [val['name'] for val in category_index.values()]
    # See http://g.co/cloud/speech/docs/languages
    # for a list of supported languages.
    language_code = 'en-US'  # a BCP-47 language tag
    client = speech.SpeechClient()
    config = types.RecognitionConfig(
        encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
        sample_rate_hertz=RATE,
        language_code=language_code)
    streaming_config = types.StreamingRecognitionConfig(
        config=config,
        interim_results=True)

    print("##########Begining Stream##########")
    with MicrophoneStream(RATE, CHUNK) as stream:

        audio_generator = stream.generator()
        requests = (types.StreamingRecognizeRequest(audio_content=content)
                    for content in audio_generator)

        responses = client.streaming_recognize(streaming_config, requests)
        # Now, put the transcription responses to use.
        return listen_print_loop(responses, stream, category_index)


if __name__ == '__main__':

    print(main())