我一直试图将一个60m的音频文件转录为文本,但是在使用gs url时遇到了麻烦。 错误消息显示协议消息RecognitionConfig没有“ uri”字段 我尝试了几种将gs uri放在此处的方法,但似乎没有用。
from google.cloud import speech_v1p1beta1 as speech
import os
import io
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "./SpeechToText-32140aeda073.json"
client = speech.SpeechClient()
encoding = speech.enums.RecognitionConfig.AudioEncoding.AMR
audio_source = speech.types.RecAognitionConfig(uri=gsc_uri)
gsc_uri = 'gs://interview_uio/Han.wav'
with io.open(audio_source, 'rb') as audio_file:
content = audio_file.read()
config = speech.types.RecognitionConfig(
encoding=speech.enums.RecognitionConfig.AudioEncoding.AMR,
sample_rate_hertz=8000,
language_code='en-US',
audio_channel_count=1,
enable_automatic_punctuation=True)
uri = 'gs://interview_uio/Han.wav'
audio = {'uri': uri}
operation = client.long_running_recognize(config, audio)
print('Waiting for operation to complete...')
response = operation.result(timeout=90)
for i, result in enumerate(response.results):
alternative = result.alternatives[0]
print('-' * 20)
print('First alternative of result {}'.format(i))
print('Transcript: {}'.format(alternative.transcript))