50 lines
1.7 KiB
Python
Executable File
50 lines
1.7 KiB
Python
Executable File
#!/bin/env python3
|
|
|
|
# Copyright (C) 2021 Tessa Nordgren
|
|
#
|
|
# This program is free software: you can redistribute it and/or modify
|
|
# it under the terms of the GNU Affero General Public License as
|
|
# published by the Free Software Foundation, version 3.
|
|
#
|
|
# This program is distributed in the hope that it will be useful,
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
# GNU Affero General Public License for more details.
|
|
#
|
|
# You should have received a copy of the GNU Affero General Public License
|
|
# along with this program. If not, see <https://www.gnu.org/licenses/>.
|
|
|
|
import argparse
|
|
from datetime import timedelta
|
|
from pathlib import Path
|
|
import srt
|
|
from yaml import load as yload
|
|
try:
|
|
from yaml import CLoader as Loader
|
|
except ImportError:
|
|
from yaml import Loader
|
|
|
|
|
|
def init():
|
|
parser = argparse.ArgumentParser(description='converts `glcoud ml speech` yaml into srt subtitles')
|
|
parser.add_argument('yml', nargs='+', help='yaml file(s) to convert')
|
|
return parser.parse_args()
|
|
|
|
|
|
args = init()
|
|
for in_filename in args.yml:
|
|
out_filename = Path(in_filename).with_suffix('.srt')
|
|
input = open(in_filename)
|
|
data = yload(input, Loader=Loader)
|
|
subs = []
|
|
index = 1
|
|
for sentence in [x['alternatives'][0] for x in data['results']]:
|
|
start = timedelta(seconds=float(sentence['words'][0]['startTime'].strip('s')))
|
|
end = timedelta(seconds=float(sentence['words'][-1]['endTime'].strip('s')))
|
|
sub = srt.Subtitle(index=index, start=start, end=end, content=sentence['transcript'])
|
|
subs.append(sub)
|
|
sub_data = srt.compose(subs)
|
|
output = open(out_filename, 'w')
|
|
output.write(sub_data)
|
|
output.close()
|