-
Notifications
You must be signed in to change notification settings - Fork 1.9k
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
[TTS]add vits network scripts, test=tts #1855
Conversation
This pull request is now in conflict :( |
self.pad_mode = "reflect" | ||
|
||
def _stft(self, wav: np.ndarray): | ||
D = librosa.core.stft( |
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.
这里变量用D感觉是不是不太直观?
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.
这里 librosa stft 本身返回就是这么定义的
D : np.ndarray [shape=(1 + n_fft/2, n_frames), dtype=dtype]
Complex-valued matrix of short-term Fourier transform
coefficients.
dropout_rate=flow_dropout_rate, | ||
use_weight_norm=use_weight_norm_in_flow, | ||
use_only_mean=use_only_mean_in_flow, ) | ||
# TODO: Add deterministic version as an option |
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.
这个是后续要加的还是已经加了忘记删掉注释?
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.
后续要加的,现在的 duration_predictor 是不确定性的,就是同样的输入每次的输出都不一样(VITS 的风格),类似于 FastSpeech2 的 duration_predictor 是确定的,同样的输入每次的结果都一样
fix #1699