-
Notifications
You must be signed in to change notification settings - Fork 19
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
pyworld vocoder (with SVSCollector bugs) #65
base: master
Are you sure you want to change the base?
Conversation
support mac anaconda installation
Update scheme for loader
add oniku_kurumi_utagoe_db prepare data
apply black
jimmylitest-1
Can convert npy files to labels txt files and convert label txt files to npy file.
Please fix the CI bugs |
Please fix the conflict as soon as possible, thanks! |
SVS/bin/train.py
Outdated
@@ -218,6 +218,14 @@ | |||
type=int, | |||
help="how many learning_steps use lr_decay", | |||
) | |||
|
|||
parser.add_argument("--vocoder_category", type=str, help="The vocoder to be used (e.g., pyworld).") |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
please uniform the interface with current vocoder
@@ -812,6 +813,10 @@ def __init__( | |||
|
|||
self.use_asr_post = use_asr_post | |||
self.d_model = d_model | |||
self.feat_dim_pw = feat_dim_pw | |||
self.vocoder_category = vocoder_category | |||
self.output_fc_pw = nn.Linear(d_output, self.feat_dim_pw*2+1) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this depends on the vocoder category right? add a if
here
align_root_path=args.train_align, | ||
pitch_beat_root_path=args.train_pitch, | ||
wav_root_path=args.train_wav, | ||
pw_f0_root_path=args.train_pw_f0, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think we can uniform this right? Don't need to check vocoder category here, but check it inside the initialization of SVSDataset (init)
…nto SJTMusicTeam-master
No description provided.