Error Synthesize How can I resolve this error? about nnsvs HOT 6 CLOSED

After all stream size 6 was good　I was able to learn for the time being Can I fix the poor timing model estimation?There are many error estimates such as long vowels😂

from nnsvs.

https://github.com/r9y9/nnsvs/blob/08fc11dde67a11d810df92d91b43ac1e50c47ac9/nnsvs/multistream.py#L113-L114

Please check the error message.

from nnsvs.

stream_sizes: [180, 3, 1, 15]
has_dynamic_features: [True, True, False, True]

Error

stream_sizes: [180, 3, 1, 3]
Error

I don't know which parameter is correct because the stream size is unknown
I did it with the default value, but I get an error

from nnsvs.

I'm sorry
Did not add vibrato to StreamSize
I checked the operation

from nnsvs.

I see. I'll share you my config for vibrato modeling. Please hold on.

from nnsvs.

This is an example of conf/train/acoustic/model/acoustic_conv.yaml for testing vibrato modeling with #73

# @package _group_
# (mgc, lf0, vuv, bap, vib)
stream_sizes: [180, 3, 1, 15, 6]
has_dynamic_features: [true, true, false, true, true]
num_windows: 3
# If None, automatically set based on stream sizes
stream_weights:

netG:
  _target_: nnsvs.model.Conv1dResnet
  in_dim: 348
  out_dim: 205
  hidden_dim: 128
  num_layers: 6
  dropout: 0.1

NOTE: in_dim may differ depending on what hed file you use.

from nnsvs.