def speech_to_text(path, lang):
import io
import os
# Imports the Google Cloud client library
from google.cloud import speech
from google.cloud.speech import enums
from google.cloud.speech import types
# Instantiates a client
client = speech.SpeechClient()
# Loads the audio into memory
with io.open(path, 'rb') as audio_file:
content = audio_file.read()
audio = types.RecognitionAudio(content=content)
config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=16000,
language_code=lang)
# Detects speech in the audio file
response = client.recognize(config, audio)
responseString = ""
for result in response.results:
responseString += result.alternatives[0].transcript
return responseString
def transcribe_sync(audio_file):
client = speech_v1p1beta1.SpeechClient()
encoding = enums.RecognitionConfig.AudioEncoding.LINEAR16
config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.MP3,
sample_rate_hertz=48000,
language_code='en-US')
with io.open(audio_file, "rb") as f:
content = f.read()
audio = {"content": content}
response = client.recognize(config, audio)
for result in response.results:
alternative = result.alternatives[0]
print(u"Transcript: {}".format(alternative.transcript))
def transcribe_gcs_with_word_time_offsets(gcs_uri):
"""Transcribe the given audio file asynchronously and output the word time
offsets."""
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.FLAC,
sample_rate_hertz=16000,
language_code='en-US',
enable_word_time_offsets=True)
operation = client.long_running_recognize(config, audio)
print('Waiting for operation to complete...')
result = operation.result(timeout=90)
return result.results
def transcribe_file_with_word_time_offsets(speech_file):
"""Transcribe the given audio file synchronously and output the word time
offsets."""
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.read()
audio = types.RecognitionAudio(content=content)
config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=16000,
language_code='en-US',
enable_word_time_offsets=True)
response = client.recognize(config, audio)
return response