Comments (4)
@Mao-JianGuo your solution can fix the error occured in training step
But, when the model is trained out, excuting synthesize.py would report the error below:
Traceback (most recent call last):
File "synthesize.py", line 99, in
synthesize(model, waveglow, melgan, text, sentence, prefix='step_{}'.format(args.step))
File "synthesize.py", line 47, in synthesize
mel, mel_postnet, log_duration_output, f0_output, energy_output, _, _, mel_len = model(text, src_len)
File "/home/op/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/op/.local/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 153, in forward
return self.module(*inputs[0], **kwargs[0])
File "/home/op/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/op/repo/github.com/ming024/FastSpeech2/fastspeech2.py", line 39, in forward
encoder_output, src_mask, mel_mask, d_target, p_target, e_target, max_mel_len)
File "/home/op/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/op/repo/github.com/ming024/FastSpeech2/modules.py", line 51, in forward
pitch_embedding = self.pitch_embedding(torch.bucketize(nn.Parameter(pitch_prediction), nn.Parameter(self.pitch_bins)))
RuntimeError: isDifferentiableType(variable.scalar_type()) INTERNAL ASSERT FAILED at "/pytorch/torch/csrc/autograd/functions/utils.h":59, please report a bug to PyTorch.
from fastspeech2.
In modules.py change
pitch_embedding = self.pitch_embedding(torch.bucketize(pitch_prediction, self.pitch_bins))
energy_embedding = self.energy_embedding(torch.bucketize(energy_prediction, self.energy_bins))
to
pitch_embedding = self.pitch_embedding(torch.bucketize(torch.tensor(pitch_prediction.data), self.pitch_bins))
energy_embedding = self.energy_embedding(torch.bucketize(torch.tensor(energy_prediction.data), self.energy_bins))
from fastspeech2.
It worked!!! Thank you very much.
Now, I know the reason of this reported err.
The torch version author used is "torch==1.6.0.dev20200428".
from fastspeech2.
Thank you all, closed #14
from fastspeech2.
Related Issues (20)
- fine-tuning issue HOT 1
- Inconvergence in pitch and energy loss
- 求救!!在VarianceAdaptor中 进行pith_embeding的时候显示编码器输出张量x和音素嵌入张量形状不同无法相加
- The numbers of the audio samples and speakers mismatch of LibriTTS dataset
- Duration of synthesis output is very short
- how to slove indexSelectSmallIndex: block: [1,0,0], thread: [32,0,0] Assertion `srcIndex < srcSelectDimSize` failed when training ASILLE3 HOT 1
- Minor bug in loading vocoders
- not found modules
- ran out of input
- [CONTRIBUTION] Speech Dataset Generator
- MFA version HOT 4
- Discrepancy in the Number of Decoder Layers
- How to train with Indian Accent HOT 2
- data
- FileNotFoundError: [Errno 2] No such file or directory: '/root/FastSpeech2-master/preprocessed_data/LJSpeech/mel/LJSpeech-mel-LJ016-0364.npy'
- preprocess.py
- train/py
- train.yaml
- CUDA out of memory
- amazing work,can it support that generate the phoneme delayed time sequence?
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 fastspeech2.