add argument to enable output of .srt file

enable srt only output
case insensitive string to bool conversion for arg
This commit is contained in:
Kevin Le 2022-10-05 23:55:41 +08:00 committed by Miguel Piedrafita
parent 9f692d4d60
commit cfafce9ccf
2 changed files with 18 additions and 6 deletions

View File

@ -16,8 +16,12 @@ def main():
choices=whisper.available_models(), help="name of the Whisper model to use") choices=whisper.available_models(), help="name of the Whisper model to use")
parser.add_argument("--output_dir", "-o", type=str, parser.add_argument("--output_dir", "-o", type=str,
default=".", help="directory to save the outputs") default=".", help="directory to save the outputs")
parser.add_argument("--output_srt", type=str2bool, default=False,
help="whether to output the .srt file along with the video files")
parser.add_argument("--srt_only", type=str2bool, default=False,
help="only generate the .srt file and not create overlayed video")
parser.add_argument("--verbose", type=str2bool, default=False, parser.add_argument("--verbose", type=str2bool, default=False,
help="Whether to print out the progress and debug messages") help="whether to print out the progress and debug messages")
parser.add_argument("--task", type=str, default="transcribe", choices=[ parser.add_argument("--task", type=str, default="transcribe", choices=[
"transcribe", "translate"], help="whether to perform X->X speech recognition ('transcribe') or X->English translation ('translate')") "transcribe", "translate"], help="whether to perform X->X speech recognition ('transcribe') or X->English translation ('translate')")
@ -25,6 +29,8 @@ def main():
args = parser.parse_args().__dict__ args = parser.parse_args().__dict__
model_name: str = args.pop("model") model_name: str = args.pop("model")
output_dir: str = args.pop("output_dir") output_dir: str = args.pop("output_dir")
output_srt: bool = args.pop("output_srt")
srt_only: bool = args.pop("srt_only")
os.makedirs(output_dir, exist_ok=True) os.makedirs(output_dir, exist_ok=True)
if model_name.endswith(".en"): if model_name.endswith(".en"):
@ -35,8 +41,12 @@ def main():
model = whisper.load_model(model_name) model = whisper.load_model(model_name)
audios = get_audio(args.pop("video")) audios = get_audio(args.pop("video"))
subtitles = get_subtitles( subtitles = get_subtitles(
audios, lambda audio_path: model.transcribe(audio_path, **args) audios, output_srt or srt_only, output_dir, lambda audio_path: model.transcribe(audio_path, **args)
) )
if srt_only:
return
# bash command to download a youtube video with `youtube-dl` and save it as `video.mp4`: # bash command to download a youtube video with `youtube-dl` and save it as `video.mp4`:
# youtube-dl -f 22 -o video.mp4 https://www.youtube.com/watch?v=QH2-TGUlwu4 # youtube-dl -f 22 -o video.mp4 https://www.youtube.com/watch?v=QH2-TGUlwu4
@ -74,12 +84,12 @@ def get_audio(paths):
return audio_paths return audio_paths
def get_subtitles(audio_paths: list, transcribe: callable): def get_subtitles(audio_paths: list, output_srt: bool, output_dir: str, transcribe: callable):
temp_dir = tempfile.gettempdir() srt_path = output_dir if output_srt else tempfile.gettempdir()
subtitles_path = {} subtitles_path = {}
for path, audio_path in audio_paths.items(): for path, audio_path in audio_paths.items():
srt_path = os.path.join(temp_dir, f"{filename(path)}.srt") srt_path = os.path.join(srt_path, f"{filename(path)}.srt")
print( print(
f"Generating subtitles for {filename(path)}... This might take a while." f"Generating subtitles for {filename(path)}... This might take a while."

View File

@ -3,7 +3,9 @@ from typing import Iterator, TextIO
def str2bool(string): def str2bool(string):
str2val = {"True": True, "False": False} string = string.lower()
str2val = {"true": True, "false": False}
if string in str2val: if string in str2val:
return str2val[string] return str2val[string]
else: else: