testadmin
/
ParakeetEricRoss
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

note on conv queue

This commit is contained in:
Kexin Zhao 2020-03-09 23:32:22 -07:00
parent d16abc4952
commit c7176a8712
2 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
examples/waveflow/README.md
View File

@ -22,11 +22,13 @@ PaddlePaddle dynamic graph implementation of [WaveFlow: A Compact Flow-based Mod
There are many hyperparameters to be tuned depending on the specification of model and dataset you are working on.
We provide `wavenet_ljspeech.yaml` as a hyperparameter set that works well on the LJSpeech dataset.
Note that we use [convolutional queue](https://arxiv.org/abs/1611.09482) at audio synthesis to cache the intermediate hidden states, which will speed up the autoregressive inference over the height dimension. Current implementation only supports height dimension equals 8 or 16, i.e., where there is no dilation on the height dimension. Therefore, you can only set value of `n_group` key in the yaml config file to be either 8 or 16.
Note that `train.py`, `synthesis.py`, and `benchmark.py` all accept a `--config` parameter. To ensure consistency, you should use the same config yaml file for both training, synthesizing and benchmarking. You can also overwrite these preset hyperparameters with command line by updating parameters after `--config`.
Also note that `train.py`, `synthesis.py`, and `benchmark.py` all accept a `--config` parameter. To ensure consistency, you should use the same config yaml file for both training, synthesizing and benchmarking. You can also overwrite these preset hyperparameters with command line by updating parameters after `--config`.
For example `--config=${yaml} --batch_size=8` can overwrite the corresponding hyperparameters in the `${yaml}` config file. For more details about these hyperparameters, check `utils.add_config_options_to_parser`.
Note that you also need to specify some additional parameters for `train.py`, `synthesis.py`, and `benchmark.py`, and the details can be found in `train.add_options_to_parser`, `synthesis.add_options_to_parser`, and `benchmark.add_options_to_parser`, respectively.
Additionally, you need to specify some additional parameters for `train.py`, `synthesis.py`, and `benchmark.py`, and the details can be found in `train.add_options_to_parser`, `synthesis.add_options_to_parser`, and `benchmark.add_options_to_parser`, respectively.
### Dataset

6
parakeet/models/waveflow/waveflow_modules.py
View File

@ -391,6 +391,12 @@ class WaveFlowModule(dg.Layer):
These hidden states along with initial random gaussian latent variable
are passed to a stack of Flow modules to obtain the audio output.
Note that we use convolutional queue (https://arxiv.org/abs/1611.09482)
to cache the intermediate hidden states, which will speed up the
autoregressive inference over the height dimension. Current
implementation only supports height dimension (self.n_group) equals
8 or 16, i.e., where there is no dilation on the height dimension.
Args:
mel (obj): mel spectrograms.
sigma (float, optional): standard deviation of the guassian latent