add support for specifying the model_dir

This commit is contained in:
James Betker 2022-05-01 17:29:25 -06:00
parent 0ffc191408
commit b1fc2b13c9
2 changed files with 7 additions and 2 deletions

View File

@ -16,10 +16,12 @@ if __name__ == '__main__':
help='How to balance vocal diversity with the quality/intelligibility of the spoken text. 0 means highly diverse voice (not recommended), 1 means maximize intellibility',
default=.5)
parser.add_argument('--output_path', type=str, help='Where to store outputs.', default='results/')
parser.add_argument('--model_dir', type=str, help='Where to find pretrained model checkpoints. Tortoise automatically downloads these to .models, so this'
'should only be specified if you have custom checkpoints.', default='.models')
args = parser.parse_args()
os.makedirs(args.output_path, exist_ok=True)
tts = TextToSpeech()
tts = TextToSpeech(models_dir=args.model_dir)
selected_voices = args.voice.split(',')
for voice in selected_voices:

View File

@ -37,13 +37,17 @@ if __name__ == '__main__':
parser.add_argument('--voice_diversity_intelligibility_slider', type=float,
help='How to balance vocal diversity with the quality/intelligibility of the spoken text. 0 means highly diverse voice (not recommended), 1 means maximize intellibility',
default=.5)
parser.add_argument('--model_dir', type=str, help='Where to find pretrained model checkpoints. Tortoise automatically downloads these to .models, so this'
'should only be specified if you have custom checkpoints.', default='.models')
args = parser.parse_args()
tts = TextToSpeech(models_dir=args.model_dir)
outpath = args.output_path
selected_voices = args.voice.split(',')
regenerate = args.regenerate
if regenerate is not None:
regenerate = [int(e) for e in regenerate.split(',')]
for selected_voice in selected_voices:
voice_outpath = os.path.join(outpath, selected_voice)
os.makedirs(voice_outpath, exist_ok=True)
@ -51,7 +55,6 @@ if __name__ == '__main__':
with open(args.textfile, 'r', encoding='utf-8') as f:
text = ''.join([l for l in f.readlines()])
texts = split_and_recombine_text(text)
tts = TextToSpeech()
if '&' in selected_voice:
voice_sel = selected_voice.split('&')