Comments (9)
Please make sure that you are on the specific git commit noted in the table https://github.com/r9y9/deepvoice3_pytorch#pretrained-models.
from deepvoice3_pytorch.
Ok thank you!
from deepvoice3_pytorch.
Unfortunately the problem still persists. I replaced master branch installation with 0421749 commit and still receive the same error.
from deepvoice3_pytorch.
Could you provide what command and model you are using? I want to reproduce it locally.
from deepvoice3_pytorch.
From 0421749 commit I run the following script:
python3 synthesis.py ./models/20171222_deepvoice3_vctk108_checkpoint_step000300000 ./models/text_list.txt ./models/
Here is the complete output:
Command line args:
{'--checkpoint-postnet': None,
'--checkpoint-seq2seq': None,
'--file-name-suffix': '',
'--help': False,
'--hparams': '',
'--max-decoder-steps': '500',
'--output-html': False,
'--replace_pronunciation_prob': '0.0',
'--speaker_id': None,
'': './models/20171222_deepvoice3_vctk108_checkpoint_step000300000',
'<dst_dir>': './models/',
'<text_list_file>': './models/text_list.txt'}
Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 482, in load_state_dict
own_state[name].copy_(param)
RuntimeError: invalid argument 2: sizes do not match at /pytorch/torch/lib/THC/generic/THCTensorCopy.c:101
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "synthesis.py", line 125, in
model.load_state_dict(checkpoint["state_dict"])
File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 487, in load_state_dict
.format(name, own_state[name].size(), param.size()))
RuntimeError: While copying the parameter named seq2seq.encoder.embed_tokens.weight, whose dimensions in the model are torch.Size([149, 128]) and whose dimensions in the checkpoint are torch.Size([149, 256]).
from deepvoice3_pytorch.
Okay, the problem is that you didn't specify proper hyper parameters. Try adding the additional command line args: --hparams="builder=deepvoice3_vctk,preset=deepvoice3_vctk"
. Also, you have to specify speaker_id as well for multi-speaker model. Try adding --speaker_id=0
.
from deepvoice3_pytorch.
Thanks for the hparams, totally missed that. I followed your recommendations, except, I set builder to deepvoice3_multispeaker and I was able to produce wav files.
from deepvoice3_pytorch.
python synthesis.py --hparams="builder=deepvoice3_vctk,preset=deepvoice3_vctk" ./20171222_deepvoice3_vctk108_checkpoint_step000300000.pth ./sentences.txt ./temp
Command line args:
{'--checkpoint-postnet': None,
'--checkpoint-seq2seq': None,
'--file-name-suffix': '',
'--help': False,
'--hparams': 'builder=deepvoice3_vctk,preset=deepvoice3_vctk',
'--max-decoder-steps': '500',
'--output-html': False,
'--replace_pronunciation_prob': '0.0',
'--speaker_id': None,
'<checkpoint>': './20171222_deepvoice3_vctk108_checkpoint_step000300000.pth',
'<dst_dir>': './temp',
'<text_list_file>': './sentences.txt'}
Override hyper parameters with preset "deepvoice3_vctk": {
"n_speakers": 108,
"speaker_embed_dim": 16,
"downsample_step": 4,
"outputs_per_step": 1,
"embedding_weight_std": 0.1,
"speaker_embedding_weight_std": 0.05,
"dropout": 0.050000000000000044,
"kernel_size": 3,
"text_embed_dim": 256,
"encoder_channels": 512,
"decoder_channels": 256,
"converter_channels": 256,
"use_guided_attention": true,
"guided_attention_sigma": 0.4,
"binary_divergence_weight": 0.1,
"use_decoder_state_for_postnet_input": true,
"max_positions": 1024,
"query_position_rate": 2.0,
"key_position_rate": 7.6,
"key_projection": true,
"value_projection": true,
"clip_thresh": 0.1,
"initial_learning_rate": 0.0005
}
Traceback (most recent call last):
File "synthesis.py", line 115, in <module>
model = build_model()
File "/Users/my_user/external_projects/text-to-speech/deepvoice3_pytorch-multi-speaker/train.py", line 766, in build_model
model = getattr(builder, hparams.builder)(
AttributeError: module 'deepvoice3_pytorch.builder' has no attribute 'deepvoice3_vctk'
Related:
#151
from deepvoice3_pytorch.
@r9y9
i put the same command but i got this error
from deepvoice3_pytorch.
Related Issues (20)
- How to use other Vocoder to synthesis waveform?
- Key for all speaker_id's
- Slow down speaking rate?
- Samples cutting out early
- Using deprecated Tensorflow 1. HOT 1
- About audio parameters settings
- pre trained model works but goes crazy on some sentences which are a bit long
- DeepVoice3 multi-speaker TTS en demo.ipynb fixes HOT 2
- Problem with lws package HOT 2
- Error while loading the model HOT 1
- Deep voice multi-speaker on Colab has pip install torch==0.3.1 error
- Deep voice 3 multi speaker on Colab - failed building wheel for lws HOT 1
- Unknown hyperparameter type for use_preset HOT 2
- Dataset not available at link
- voice tone
- n_vocab AttributeError
- Installation nightmare
- train.py problem HOT 2
- 'SinusoidalEncoding' object has no attribute '_backend' HOT 1
- Both Sample Colab Notebooks No Longer Work HOT 2
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 deepvoice3_pytorch.