Comments (3)
Sorry for this. I forgot to change self.decoder_inputs to self.y. Pull now.
from tacotron.
I am getting the same issue. I trained using
python train_multi_gpus.py
My hyperparmaters.py was modified slightly for 2 x GPUs and more epochs:
diff --git a/hyperparams.py b/hyperparams.py
index 5aaccab..8ac9032 100644
--- a/hyperparams.py
+++ b/hyperparams.py
@@ -35,13 +35,13 @@ class Hyperparams:
# training scheme
lr = 0.001 # Paper => Exponential decay
logdir = "logdir"
- batch_size = 32
- num_epochs = 200 # Paper => 2M global steps!
+ batch_size = 64
+ num_epochs = 2000 # Paper => 2M global steps!
loss_type = "l1" # Or you can test "l2"
num_samples = 32
# etc
- num_gpus = 1 # If you have multiple gpus, adjust this option, and increase the batch size
+ num_gpus = 2 # If you have multiple gpus, adjust this option, and increase the batch size
# and run `train_multiple_gpus.py` instead of `train.py`.
target_zeros_masking = False # If True, we mask zero padding on the target,
# so exclude them from the loss calculation.
from tacotron.
Fixed for me. Thanks!
from tacotron.
Related Issues (20)
- Can anyone guide me how to get Audio out from eval.py file for testing ?? HOT 1
- Bus error: 10 at training HOT 6
- How to synthesize long sentences?
- About the performance of synthesis
- speaker adaption : not to update the encoder parameters
- ref_db=20, max_db=100, Where did these values come from? statistics?
- Generated wave were empty HOT 8
- I've uploaded Donald Trump speeches and transcripts HOT 1
- error in utils,py
- How can we exploit forced alignments?
- Error in data_load.py---TypeError: a bytes-like object is required, not 'str'
- Segmentation fault on training HOT 1
- Get MelSpectogram for wavenet
- IOError: [Errno 2] No such file or directory: '/data/private/voice/LJSpeech-1.0/transcript.csv'
- IOError: [Errno 2] No such file or directory: '/data/private/voice/LJSpeech-1.0/transcript.csv' HOT 1
- Transcript.csv file? HOT 1
- Different result in train and eval and synthesize mode
- how much it takes to train and on what hardware?
- Tensorflow error
- [CONTRIBUTION] Speech Dataset Generator
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tacotron.