Closed mysxs closed 7 months ago
Hi @mysxs !
I think simply run command with --infer_target_speaker '[ESD]_0017' \
may sovle your problem.
Actually we will look up [ESD]_0017
in singer.json
to get 16
which is the index of the target singer's embedding in your trained model.
Hi @Lokshaw-Chau ! Ok, it worked, then a new problem appeared, I continued to solve it, thank you for your reply!
Problem Overview
An error occurred in infer_target_speaker while inferring with own data set
Steps Taken
When I did the inference/conversion, I was told that the problem corresponding to target_speaker could not be found The error appears in infer_target_speaker. Execute the infer_target_speaker command as follows:
--infer_target_speaker 16 \
Because my singers.json is like this, I chose"[ESD]_0017": 16
as my target_speaker, but I don't have a folder for"[ESD]_0017": 16
under the data path Only'[ESD]'
(all my CustomSVCDataset) and0004_000563
(my source_audio) in the data pathIn
data/[ESD]/mel_min_max_stats
, there aremel_max.npy
andmel_min.npy
, and indata/[ESD]/mels
, there are all the.npy files for my CustomSVCDataset So I can't find the infer_target_speaker.npy file