Unverified Commit e82cc350 authored by jimchen90's avatar jimchen90 Committed by GitHub
Browse files

Update default form in docstring (#802)



* Update default form in docstring
Co-authored-by: default avatarJi Chen <jimchen90@devfair0160.h2.fair>
parent 4b8aad7a
...@@ -13,7 +13,7 @@ class _ResBlock(nn.Module): ...@@ -13,7 +13,7 @@ class _ResBlock(nn.Module):
The paper link is https://arxiv.org/pdf/1512.03385.pdf. The paper link is https://arxiv.org/pdf/1512.03385.pdf.
Args: Args:
n_freq: the number of bins in a spectrogram (default=128) n_freq: the number of bins in a spectrogram. (Default: ``128``)
Examples Examples
>>> resblock = _ResBlock() >>> resblock = _ResBlock()
...@@ -48,11 +48,11 @@ class _MelResNet(nn.Module): ...@@ -48,11 +48,11 @@ class _MelResNet(nn.Module):
r"""MelResNet layer uses a stack of ResBlocks on spectrogram. r"""MelResNet layer uses a stack of ResBlocks on spectrogram.
Args: Args:
n_res_block: the number of ResBlock in stack (default=10) n_res_block: the number of ResBlock in stack. (Default: ``10``)
n_freq: the number of bins in a spectrogram (default=128) n_freq: the number of bins in a spectrogram. (Default: ``128``)
n_hidden: the number of hidden dimensions of resblock (default=128) n_hidden: the number of hidden dimensions of resblock. (Default: ``128``)
n_output: the number of output dimensions of melresnet (default=128) n_output: the number of output dimensions of melresnet. (Default: ``128``)
kernel_size: the number of kernel size in the first Conv1d layer (default=5) kernel_size: the number of kernel size in the first Conv1d layer. (Default: ``5``)
Examples Examples
>>> melresnet = _MelResNet() >>> melresnet = _MelResNet()
...@@ -129,12 +129,12 @@ class _UpsampleNetwork(nn.Module): ...@@ -129,12 +129,12 @@ class _UpsampleNetwork(nn.Module):
r"""Upscale the dimensions of a spectrogram. r"""Upscale the dimensions of a spectrogram.
Args: Args:
upsample_scales: the list of upsample scales upsample_scales: the list of upsample scales.
n_res_block: the number of ResBlock in stack (default=10) n_res_block: the number of ResBlock in stack. (Default: ``10``)
n_freq: the number of bins in a spectrogram (default=128) n_freq: the number of bins in a spectrogram. (Default: ``128``)
n_hidden: the number of hidden dimensions of resblock (default=128) n_hidden: the number of hidden dimensions of resblock. (Default: ``128``)
n_output: the number of output dimensions of melresnet (default=128) n_output: the number of output dimensions of melresnet. (Default: ``128``)
kernel_size: the number of kernel size in the first Conv1d layer (default=5) kernel_size: the number of kernel size in the first Conv1d layer. (Default: ``5``)
Examples Examples
>>> upsamplenetwork = _UpsampleNetwork(upsample_scales=[4, 4, 16]) >>> upsamplenetwork = _UpsampleNetwork(upsample_scales=[4, 4, 16])
...@@ -204,16 +204,16 @@ class _WaveRNN(nn.Module): ...@@ -204,16 +204,16 @@ class _WaveRNN(nn.Module):
`upsample_scales` must equal `hop_length`. `upsample_scales` must equal `hop_length`.
Args: Args:
upsample_scales: the list of upsample scales upsample_scales: the list of upsample scales.
n_classes: the number of output classes n_classes: the number of output classes.
hop_length: the number of samples between the starts of consecutive frames hop_length: the number of samples between the starts of consecutive frames.
n_res_block: the number of ResBlock in stack (default=10) n_res_block: the number of ResBlock in stack. (Default: ``10``)
n_rnn: the dimension of RNN layer (default=512) n_rnn: the dimension of RNN layer. (Default: ``512``)
n_fc: the dimension of fully connected layer (default=512) n_fc: the dimension of fully connected layer. (Default: ``512``)
kernel_size: the number of kernel size in the first Conv1d layer (default=5) kernel_size: the number of kernel size in the first Conv1d layer. (Default: ``5``)
n_freq: the number of bins in a spectrogram (default=128) n_freq: the number of bins in a spectrogram. (Default: ``128``)
n_hidden: the number of hidden dimensions of resblock (default=128) n_hidden: the number of hidden dimensions of resblock. (Default: ``128``)
n_output: the number of output dimensions of melresnet (default=128) n_output: the number of output dimensions of melresnet. (Default: ``128``)
Example Example
>>> wavernn = _waveRNN(upsample_scales=[5,5,8], n_classes=512, hop_length=200) >>> wavernn = _waveRNN(upsample_scales=[5,5,8], n_classes=512, hop_length=200)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment