-
Notifications
You must be signed in to change notification settings - Fork 6.4k
/
transcribe_enhanced_model.py
66 lines (51 loc) · 2.1 KB
/
transcribe_enhanced_model.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
# Copyright 2018 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Google Cloud Speech API sample that demonstrates enhanced models
and recognition metadata.
Example usage:
python transcribe_enhanced_model.py resources/commercial_mono.wav
"""
import argparse
def transcribe_file_with_enhanced_model(path):
"""Transcribe the given audio file using an enhanced model."""
# [START speech_transcribe_enhanced_model]
import io
from google.cloud import speech
client = speech.SpeechClient()
# path = 'resources/commercial_mono.wav'
with io.open(path, "rb") as audio_file:
content = audio_file.read()
audio = speech.RecognitionAudio(content=content)
config = speech.RecognitionConfig(
encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=8000,
language_code="en-US",
use_enhanced=True,
# A model must be specified to use enhanced model.
model="phone_call",
)
response = client.recognize(config=config, audio=audio)
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))
# [END speech_transcribe_enhanced_model]
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
)
parser.add_argument("path", help="File to stream to the API")
args = parser.parse_args()
transcribe_file_with_enhanced_model(args.path)