Comments (5)
environment: cuda-9.0 + cudnn-7.3.1 + python-3.6.7 + torch-0.4.0
from pytorch-dc-tts.
@Joee1995 It is working under Linux/Anaconda/Cuda10/PyTorch1. Maybe it is a windows problem?
I made a Colab notebook: https://colab.research.google.com/drive/1aG_2uDK-sCWkHIReRqm8WW3y8XsI3Ltm
You can follow the commands in the above notebook to replicate an environment which can successfully train DC-TTS.
from pytorch-dc-tts.
Really a windows problem.
When running in Linux, it works well at first, but there is another error at epoch 18:
epoch 18 with lr=1.22e-03
50%|██████████▌ | 1728/3456 [00:27<00:26, 66.45audios/s, l1=0.18589, att=0.00016]Traceback (most recent call last):
File "train-text2mel.py", line 157, in
train_epoch_loss = train(epoch, phase='train')
File "train-text2mel.py", line 140, in train
{'mels-true': S[0, :, :], 'mels-pred': Y[0, :, :], 'attention': A[0, :, :]})
File "/home/yy/TTS/pytorch-dc-tts/logger.py", line 29, in log_step
self.writer.add_image('%s/%s' % (self.model_name, key), image_dict[key], step)
File "/home/yy/anaconda3/envs/ptPy36/lib/python3.6/site-packages/tensorboardX/writer.py", line 427, in add_image
image(tag, img_tensor, dataformats=dataformats), global_step, walltime)
File "/home/yy/anaconda3/envs/ptPy36/lib/python3.6/site-packages/tensorboardX/summary.py", line 211, in image
tensor = convert_to_HWC(tensor, dataformats)
File "/home/yy/anaconda3/envs/ptPy36/lib/python3.6/site-packages/tensorboardX/utils.py", line 98, in convert_to_HWC
assert(len(tensor.shape) == len(input_format)), "size of input tensor and input format are different"
AssertionError: size of input tensor and input format are different
Thx!
from pytorch-dc-tts.
Latest TensorboardX version behaves differently. Should be now fixed with 653fd14
from pytorch-dc-tts.
@Joee1995 were you able to get it to run in windows later? would be great if anynone can get it to work in windows
from pytorch-dc-tts.
Related Issues (20)
- Text2Mel input to WaveGlow outputs noisy audio file without any speech HOT 33
- colab demo RuntimeError HOT 1
- transfer learning ljspeech HOT 2
- Transfer learning from already trained models HOT 1
- Custom dataset HOT 3
- Custom dataset HOT 1
- Empty speech output (some sentences synthesize and others don't) HOT 1
- h params module not found and 'indices' to have scalar type Long; but got torch.IntTensor instead (while checking arguments for embedding) HOT 1
- Problem about the checkpoints HOT 1
- Solved issue
- Empty audios HOT 6
- how to use HOT 2
- Transfer Learning
- bible_book_file_path
- How to train a Tibetan-TTS model HOT 1
- Speed Up Inference HOT 1
- how to train language require tokenization HOT 36
- Licence HOT 1
- decode速度很慢,请问怎么并行化。 HOT 1
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 pytorch-dc-tts.