Example code: Returning all speech transcriptions via loop #1782
Description
Example code to return all transcriptions
This entry provides an example for returning all speech transcriptions in a GCS stored video. The current example code for speech transcription only returns the first item:
[...]
# There is only one annotation_result since only
# one video is processed.
annotation_results = result.annotation_results[0]
speech_transcription = annotation_results.speech_transcriptions[0]
alternative = speech_transcription.alternatives[0]
print('Transcript: {}'.format(alternative.transcript))
[...]
In order to store and return all transcriptions (first alternative), here is a quick example for a loop:
def speech_transcription(path):
"""Transcribe speech from a video stored on GCS."""
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.enums.Feature.SPEECH_TRANSCRIPTION]
config = videointelligence.types.SpeechTranscriptionConfig(
language_code='en-US',
enable_automatic_punctuation=True)
video_context = videointelligence.types.VideoContext(
speech_transcription_config=config)
operation = video_client.annotate_video(
path, features=features,
video_context=video_context)
result = operation.result()
# Make list, loop over entries, store each entry in list, return list.
all_transcriptions = []
entries = result.annotation_results[0].speech_transcriptions[0].alternatives
for i, entry in enumerate(entries):
all_transcriptions.append(entry.transcript)
return(all_transcriptions)
Hope this helps some of you!
Activity
nnegrey commentedon Oct 24, 2018
Hi, thanks for sharing.
If you feel the sample should be updated, feel free to open a PR for review. :)
Since this isn't a explicit error with the sample or ask for help with the sample, I'm gonna close this. Feel free to re-open if needed.
Thanks