Add new dataset support to preprocess parameter

This commit is contained in:
babysor00 2021-10-17 17:21:49 +08:00
parent 724809abf4
commit b0c156a537

2
pre.py
View File

@ -41,7 +41,7 @@ if __name__ == "__main__":
"Use this option when dataset does not include alignments\ "Use this option when dataset does not include alignments\
(these are used to split long audio files into sub-utterances.)") (these are used to split long audio files into sub-utterances.)")
parser.add_argument("-d", "--dataset", type=str, default="aidatatang_200zh", help=\ parser.add_argument("-d", "--dataset", type=str, default="aidatatang_200zh", help=\
"Name of the dataset to process, allowing values: magicdata, aidatatang_200zh, aishell3.") "Name of the dataset to process, allowing values: magicdata, aidatatang_200zh, aishell3, data_aishell.")
parser.add_argument("-e", "--encoder_model_fpath", type=Path, default="encoder/saved_models/pretrained.pt", help=\ parser.add_argument("-e", "--encoder_model_fpath", type=Path, default="encoder/saved_models/pretrained.pt", help=\
"Path your trained encoder model.") "Path your trained encoder model.")
parser.add_argument("-ne", "--n_processes_embed", type=int, default=1, help=\ parser.add_argument("-ne", "--n_processes_embed", type=int, default=1, help=\