blackteay/ffmpeg-python
1
0
Fork 0
mirror of https://github.com/kkroening/ffmpeg-python.git synced 2025-04-06 04:15:44 +08:00
Code Issues Projects Releases Wiki Activity

Add --timing option to transcribe.py; output json

Browse Source
This commit is contained in:
Karl Kroening 2018-01-14 22:48:11 -08:00
parent de1ec94be9
commit 87f85000ac
1 changed files with 11 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
examples/transcribe.py
View File

@ -1,6 +1,7 @@
#!/usr/bin/env python #!/usr/bin/env python
from __future__ import unicode_literals from __future__ import unicode_literals
from google.protobuf.json_format import MessageToJson
from google.cloud import speech from google.cloud import speech
from google.cloud.speech import enums from google.cloud.speech import enums
from google.cloud.speech import types from google.cloud.speech import types
@ -9,6 +10,7 @@ import ffmpeg
import logging import logging
import subprocess import subprocess
import sys import sys
import IPython
logging.basicConfig(level=logging.INFO, format='%(message)s') logging.basicConfig(level=logging.INFO, format='%(message)s')
@ -18,6 +20,7 @@ logger.setLevel(logging.INFO)
parser = argparse.ArgumentParser(description='Convert speech audio to text using Google Speech API') parser = argparse.ArgumentParser(description='Convert speech audio to text using Google Speech API')
parser.add_argument('in_filename', help='Input filename (`-` for stdin)') parser.add_argument('in_filename', help='Input filename (`-` for stdin)')
parser.add_argument('--timing', action='store_true', help='Include timing info')
def decode_audio(in_filename, **input_kwargs): def decode_audio(in_filename, **input_kwargs):
@ -38,25 +41,24 @@ def decode_audio(in_filename, **input_kwargs):
return out[0] return out[0]
def get_transcripts(audio_data): def get_transcripts(audio_data, include_timing_info=False):
client = speech.SpeechClient() client = speech.SpeechClient()
audio = types.RecognitionAudio(content=audio_data) audio = types.RecognitionAudio(content=audio_data)
config = types.RecognitionConfig( config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16, encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=16000, sample_rate_hertz=16000,
language_code='en-US' language_code='en-US',
enable_word_time_offsets=include_timing_info,
) )
response = client.recognize(config, audio) return client.recognize(config, audio)
return [result.alternatives[0].transcript for result in response.results]
def transcribe(in_filename): def transcribe(in_filename, include_timing_info=False):
audio_data = decode_audio(in_filename) audio_data = decode_audio(in_filename)
transcripts = get_transcripts(audio_data) response = get_transcripts(audio_data, include_timing_info)
for transcript in transcripts: print(MessageToJson(response, sort_keys=True))
print(repr(transcript.encode('utf-8')))
if __name__ == '__main__': if __name__ == '__main__':
args = parser.parse_args() args = parser.parse_args()
transcribe(args.in_filename) transcribe(args.in_filename, args.timing)