This commit is contained in:
Super Chiba 2023-11-23 12:50:23 +08:00
parent b14573f7b2
commit f63818d68a

View file

@ -13,15 +13,15 @@ if __name__ == '__main__':
parser.add_argument('--voice', type=str, help='Selects the voice to use for generation. See options in voices/ directory (and add your own!) '
'Use the & character to join two voices together. Use a comma to perform inference on multiple voices.', default='random')
parser.add_argument('--preset', type=str, help='Which voice preset to use.', default='fast', choices=['high_quality' , 'standard', 'fast', 'ultra_fast'])
parser.add_argument('--use_deepspeed', type=str, help='Which voice preset to use. Default to False', default='False', choices=['True', 'False'])
parser.add_argument('--kv_cache', type=bool, help='If you disable this please wait for a long a time to get the output. Default to True', default='True', choices=['True', 'False'])
parser.add_argument('--half', type=bool, help="float16(half) precision inference if True it's faster and take less vram and ram. Default to True", default='True', choices=['True', 'False'])
parser.add_argument('--use_deepspeed', type=bool, help='Which voice preset to use. Default to False', default=False, choices=[True, False])
parser.add_argument('--kv_cache', type=bool, help='If you disable this please wait for a long a time to get the output. Default to True', default=True, choices=[True, False])
parser.add_argument('--half', type=bool, help="float16(half) precision inference if True it's faster and take less vram and ram. Default to True", default=True, choices=[True, False])
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_DIR)
parser.add_argument('--candidates', type=int, help='How many output candidates to produce per-voice. Default to 3', default=3)
parser.add_argument('--seed', type=int, help='Random seed which can be used to reproduce results.', default=None)
parser.add_argument('--produce_debug_state', type=bool, help='Whether or not to produce debug_state.pth, which can aid in reproducing problems. Defaults to true.', default='True', choices=['True', 'False'])
parser.add_argument('--produce_debug_state', type=bool, help='Whether or not to produce debug_state.pth, which can aid in reproducing problems. Defaults to true.', default=True, choices=[True, False])
parser.add_argument('--cvvp_amount', type=float, help='How much the CVVP model should influence the output.'
'Increasing this can in some cases reduce the likelihood of multiple speakers. Defaults to 0 (disabled)', default=.0)
parser.add_argument('--batch_size', type=int, help='(Optional) If you want to specify the batch size to use for autoregression. Usually, VRAM-2GB if half=True, VRAM/2 if half=False')