config update for r=2

pull/10/head
Eren Golge 2019-02-16 03:17:59 +01:00
parent 90f0cd640b
commit 11b6080cfd
2 changed files with 6 additions and 4 deletions

View File

@ -1,6 +1,6 @@
{
"model_name": "embed_init_loss_weight",
"model_description": "Lower loss freq is weight 0.0, higher weight decay, ref_level_db: 40->20, sample_rate:16000 -> 22050",
"model_name": "queue",
"model_description": "Queue memory and change lower r incrementatlly",
"audio":{
"audio_processor": "audio", // to use dictate different audio processors, if available.
@ -28,15 +28,16 @@
"embedding_size": 256, // Character embedding vector length. You don't need to change it in general.
"text_cleaner": "phoneme_cleaners",
"epochs": 1000, // total number of epochs to train.
"lr": 0.001, // Initial learning rate. If Noam decay is active, maximum learning rate.
"lr": 0.0001, // Initial learning rate. If Noam decay is active, maximum learning rate.
"lr_decay": false, // if true, Noam learning rate decaying is applied through training.
"loss_weight": 0.0, // loss weight to emphasize lower frequencies. Lower frequencies are in general more important for speech signals.
"warmup_steps": 4000, // Noam decay steps to increase the learning rate from 0 to "lr"
"windowing": false, // Enables attention windowing. Used only in eval mode.
"memory_size": 5, // memory queue size used to queue network predictions to feed autoregressive connection. Useful if r < 5.
"batch_size": 32, // Batch size for training. Lower values than 32 might cause hard to learn attention.
"eval_batch_size":32,
"r": 5, // Number of frames to predict for step.
"r": 2, // Number of frames to predict for step.
"wd": 0.00001, // Weight decay weight.
"checkpoint": true, // If true, it saves checkpoints per "save_step"
"save_step": 5000, // Number of training steps expected to save traning stats and checkpoints.

1
test_cluster.py Normal file
View File

@ -0,0 +1 @@
print("Python is running!!")