Proof of concept AWS Transcribe Diarization Display

convert.py

from __future__ import print_function
import json

# Proof of concept AWS Transcribe Diarization Display
# Expects "asrOutput.json" to be in the same directory as thie file
# https://docs.aws.amazon.com/transcribe/latest/dg/how-it-works.html#how-diarization

with open('asrOutput.json', 'r') as f:
    data = f.read()

data = json.loads(data)

transcript = data['results']['transcripts'][0]['transcript']
wordList = transcript.split()
# print(wordList)
counter = 0

for segment in data['results']['speaker_labels']['segments']:
    numWords = len(segment['items'])
    speaker = segment['speaker_label'].replace("spk_", "Speaker ") + ":"
    print(speaker)
    segmentText = wordList[counter:counter + numWords]

    for x in segmentText:
        print(x, end=" ")
    print("\n")

    counter = counter + numWords

gistfile1.txt

from __future__ import print_function
import json

# Proof of concept AWS Transcribe Diarization Display
# Expects "asrOutput.json" to be in the same directory as thie file
# https://docs.aws.amazon.com/transcribe/latest/dg/how-it-works.html#how-diarization

with open('asrOutput.json', 'r') as f:
    data = f.read()

data = json.loads(data)

transcript = data['results']['transcripts'][0]['transcript']
wordList = transcript.split()
# print(wordList)
counter = 0

for segment in data['results']['speaker_labels']['segments']:
    numWords = len(segment['items'])
    speaker = segment['speaker_label'].replace("spk_", "Speaker ") + ":"
    print(speaker)
    segmentText = wordList[counter:counter + numWords]

    for x in segmentText:
        print(x, end=" ")
    print("\n")

    counter = counter + numWords