search

azraelkuan / FFTNet

FFTNet: a Real-Time Speaker-Dependent Neural Vocoder
64 stars 10 forks source link

Training with a new dataset #4

Open buscon opened 5 years ago

buscon commented 5 years ago

hi,

I tried to train using a new datasets of audiofiles, but I run into problems already by preprocess: python preprocess.py --name=my_dataset --in_dir=path_to_my_dataset_files/ --out_dir=feature_dir/ --hparams "input_type=mulaw-quantize" but I get a :

Traceback (most recent call last): File "preprocess.py", line 53, in assert name in ["cmu_arctic", "ljspeech"] AssertionError

YuzukiTsuru commented 5 years ago

You need to add your dataset to preprocess and then edit the list of related references.

你需要在preprocess里增加你的数据集，然后编辑相关引用列表

https://github.com/azraelkuan/FFTNet/blob/b182e3955dc626810d0d16e89c232e509a146043/preprocess.py#L53