FilesExpand file tree

 main

/

transcribe.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

102 lines (78 loc) · 3.36 KB

 main

/

transcribe.py

Copy path

Top

File metadata and controls

• Code
• Blame

102 lines (78 loc) · 3.36 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

102

# Copyright 2017 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 application using the REST API for batch

processing.

Example usage:

python transcribe.py resources/audio.raw

python transcribe.py gs://cloud-samples-tests/speech/brooklyn.flac

"""

# [START speech_transcribe_sync]

import argparse

from google.cloud import speech

def transcribe_file(speech_file: str) -> speech.RecognizeResponse:

"""Transcribe the given audio file."""

client = speech.SpeechClient()

# [START speech_python_migration_sync_request]

# [START speech_python_migration_config]

with open(speech_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",

)

# [END speech_python_migration_config]

# [START speech_python_migration_sync_response]

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

# [END speech_python_migration_sync_request]

# 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(f"Transcript: {result.alternatives[0].transcript}")

# [END speech_python_migration_sync_response]

return response

# [END speech_transcribe_sync]

# [START speech_transcribe_sync_gcs]

def transcribe_gcs(gcs_uri: str) -> speech.RecognizeResponse:

"""Transcribes the audio file specified by the gcs_uri."""

from google.cloud import speech

client = speech.SpeechClient()

# [START speech_python_migration_config_gcs]

audio = speech.RecognitionAudio(uri=gcs_uri)

config = speech.RecognitionConfig(

encoding=speech.RecognitionConfig.AudioEncoding.FLAC,

sample_rate_hertz=16000,

language_code="en-US",

)

# [END speech_python_migration_config_gcs]

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(f"Transcript: {result.alternatives[0].transcript}")

return response

# [END speech_transcribe_sync_gcs]

if __name__ == "__main__":

parser = argparse.ArgumentParser(

description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter

)

parser.add_argument("path", help="File or GCS path for audio file to be recognized")

args = parser.parse_args()

if args.path.startswith("gs://"):

transcribe_gcs(args.path)

else:

transcribe_file(args.path)