speech.py

import six
import os
import io
from google.cloud import speech

credential_path = "creds.json"
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = credential_path


# for result in response.results:
#     print("Transcript: {}".format(result.alternatives[0].transcript))


async def transcribe_streaming(ctx,stream_file):

    """Transcribe the given audio file."""
    from google.cloud import speech
    import io

    client = speech.SpeechClient()

    with io.open(stream_file, "rb") as audio_file:
        content = audio_file.read()

    audio = speech.RecognitionAudio(content=content)
    config = speech.RecognitionConfig(
        encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
        sample_rate_hertz=16000,
        language_code="en-US",
    )

    response = client.recognize(config=config, audio=audio)

    # Each result is for a consecutive portion of the audio. Iterate through
    # them to get the transcripts for the entire audio file.
    for result in response.results:
        # The first alternative is the most likely one for this portion.
        print(u"Transcript: {}".format(result.alternatives[0].transcript))