Created
October 10, 2017 21:32
-
-
Save samuelcouch/117546c4254f0f3096cc79effc79ac2c to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from watson_developer_cloud import SpeechToTextV1 as SpeechToText | |
# Use this method to send the audio to Watson and save the response | |
def get_and_save_transcript(audio_file, transcript_file): | |
with open(audio_file, 'rb') as af: | |
resp = stt.recognize(af, | |
content_type='audio/wav', | |
timestamps=True, | |
continuous=True, | |
word_confidence=True, | |
profanity_filter=False, | |
word_alternatives_threshold=0.4) | |
with open(transcript_file, 'w') as tf: | |
tf.write(json.dumps(resp)) | |
stt = SpeechToText( | |
username='<YOUR SERVICE USERNAME>', | |
password='<YOUR SERVICE PASSWORD>') | |
# Make a directory to save our transcripts | |
if not os.path.exists(join(project_dir, 'split_transcripts')): | |
os.makedirs(join(project_dir, 'split_transcripts')) | |
trancription_jobs = [] | |
transcript_files = [] | |
# Create a new job for each audio segment | |
for chunk in segment_files: | |
transcript_file = '{}.json'.format(splitext(basename(chunk))[0]) | |
full_transcript_file = join(project_dir, 'split_transcripts', transcript_file) | |
transcript_files.append(full_transcript_file) | |
job = Process(target=get_and_save_transcript, | |
args=(chunk,full_transcript_file)) | |
job.start() | |
trancription_jobs.append(job) | |
for job in trancription_jobs: | |
job.join() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment