transcript_split.py

#-*- coding: utf-8 -*-
__author__ = "Chirag Rathod (Srce Cde)"
__license__ = "MIT"
__email__ = "[email protected]"
__maintainer__ = "Chirag Rathod (Srce Cde)"

import json
with open("sample.json", "r") as f:
    json_load = json.load(f)

channels = json_load["results"]["channel_labels"]
items = json_load["results"]["items"]

speaker_text = []
flag = False

temp = None

for word in items:
    with open("transcribe.txt", "a") as f:
        for seg in channels["channels"]:
            for seg_item in seg["items"]:
                # print(word["type"])
                if "start_time" in seg_item and word["type"] != "punctuation":
                    if word["end_time"] == seg_item["end_time"] and word["start_time"] == seg_item["start_time"]:
                        # if word["alternatives"][0]["content"]:
                        if temp != seg["channel_label"]:
                            f.write("{} : ".format(seg["channel_label"]))
                            speaker_text.append(word["alternatives"][0]["content"])
                            flag = True
                            temp = seg["channel_label"]
                        else:
                            speaker_text.append(word["alternatives"][0]["content"])
                            flag = True

        if word["type"] == "punctuation":
            f.write(word["alternatives"][0]["content"])
        f.write(" {}".format(' '.join(speaker_text)))
        speaker_text = []

# sample output
"""
ch_1 :  Good afternoon.  You know,  factories. ch_0 :  Yes.  Hi.  I was gonna see if Travis weekends available. ch_1 :  Uh,  he is not in today.  He'll be back Monday. ch_0 :  Alright,  I'll try back down.  Thanks. ch_1 :  Thank you. ch_0 :  Thank you. 
"""