You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
31 lines
1.0 KiB
Python
31 lines
1.0 KiB
Python
#!/usr/bin/env python
|
|
import json
|
|
import argparse
|
|
import sys
|
|
|
|
# requires: timecode.py
|
|
# some functions to help working with (srt/vtt) timecodes
|
|
from timecode import timecode_fromsecs
|
|
|
|
ap = argparse.ArgumentParser("convert VOSK json output into a special vtt with timed json per word")
|
|
ap.add_argument('infile', nargs='?', type=argparse.FileType('r'), default=sys.stdin)
|
|
ap.add_argument('outfile', nargs='?', type=argparse.FileType('w'), default=sys.stdout)
|
|
args = ap.parse_args()
|
|
|
|
|
|
data = json.load(args.infile)
|
|
|
|
def tc(s):
|
|
return timecode_fromsecs(s, alwaysfract=True, fractdelim=".")
|
|
|
|
print ("WEBVTT", file=args.outfile)
|
|
print (file=args.outfile)
|
|
for m in data['monologues']:
|
|
for term in m['terms']:
|
|
if term['type'] == "WORD":
|
|
print (f"{tc(term['start'])} --> {tc(term['end'])}", file=args.outfile)
|
|
# print (f"{term['text']}")
|
|
tterm = {'text': term['text'], 'confidence': term['confidence']}
|
|
print (json.dumps(tterm), file=args.outfile)
|
|
print (file=args.outfile)
|