def transcribe_file(speech_file):
"""Transcribe the given audio file."""
from google.cloud import speech
from google.cloud.speech import enums
from google.cloud.speech import types
client = speech.SpeechClient()
with io.open(speech_file, 'rb') as audio_file:
content = audio_file.sread()
audio = types.RecognitionAudio(content=content)
config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=16000,
language_code='en-US')
response = client.recognize(config, audio)
# Each result is for a consecutive portion of the audio. Iterate through
# them to get the transcripts for the entire audio file.
full_text = ""
for result in response.results:
# The first alternative is the most likely one for this portion.
full_text += format(result.alternatives[0].transcript)
print(u'Transcript: {}'.format(result.alternatives[0].transcript))
return full_text
def transcribe_gcs(gcs_uri):
from google.cloud import speech
from google.cloud.speech import enums
from google.cloud.speech import types
client = speech.SpeechClient()
audio = types.RecognitionAudio(uri=gcs_uri)
config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=16000,
language_code='ko-KR')
operation = client.long_running_recognize(config, audio)
response = operation.result()
return response
def transcribe_gcs(gcs_url):
from google.cloud import speech
from google.cloud.speech import enums
from google.cloud.speech import types
client = speech.SpeechClient()
audio = types.RecognitionAudio(uri=gcs_url)
config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=16000,
enable_automatic_punctuation=True,
language_code='zh-TW')
operation = client.long_running_recognize(config, audio)
response = operation.result(timeout=90)
toexcel(response, gcs_url)