Comments (10)
Ok, I will do it!
from nnsvs.
Thank You! It works correctly on Colab! I close this issue and I start to work on Streamlit app like in the issue!
from nnsvs.
I think that another fix is to correctly install pysinsy by update submodule before install
! cd pysinsy && git submodule update --recursive --init && export SINSY_INSTALL_PREFIX=/usr/ && pip install -q .
from nnsvs.
Now I have the problem at Time-lag model
---------------------------------------------------------------------------
ConfigAttributeError Traceback (most recent call last)
[<ipython-input-16-1af2a256b7d5>](https://localhost:8080/#) in <module>()
1 timelag_config = OmegaConf.load(join(model_dir, "timelag", "model.yaml"))
----> 2 timelag_model = hydra.utils.instantiate(timelag_config.netG).to(device)
3 checkpoint = torch.load(join(model_dir, "timelag", "latest.pth"), map_location=lambda storage, loc: storage)
4 timelag_model.load_state_dict(checkpoint["state_dict"])
5 timelag_in_scaler = joblib.load(join(model_dir, "in_timelag_scaler.joblib"))
6 frames
[/usr/local/lib/python3.7/dist-packages/omegaconf/dictconfig.py](https://localhost:8080/#) in _get_node(self, key, validate_access, throw_on_missing_value, throw_on_missing_key)
468 if value is None:
469 if throw_on_missing_key:
--> 470 raise ConfigKeyError(f"Missing key {key}")
471 elif throw_on_missing_value and value._is_missing():
472 raise MissingMandatoryValue("Missing mandatory value: $KEY")
ConfigAttributeError: Missing key to
full_key: netG.to
object_type=dict
from nnsvs.
Also hts_engine do not install correctly, I try to do the following commands:
! cd hts_engine_API/src && mkdir -p build && cd build && cmake .. && cmake --build . --config Release
And also sinsy fail the install
! cd sinsy && git submodule update --recursive --init && cd src && mkdir -p build && cd build && cmake -DCMAKE_BUILD_TYPE=Release -DBUILD_SHARED_LIBS=ON .. && make -j && sudo make install
from nnsvs.
In that modified notebook seams that the installation of the libraries works correctly Neural_network_based_singing_voice_synthesis_demo_using_kiritan_singing_database_(Japanese).zip .
Sometimes the import box should be run two times (that can be a first smell).
After I arrive to the Time-lag model box and I reach:
---------------------------------------------------------------------------
ConfigAttributeError Traceback (most recent call last)
[<ipython-input-16-1af2a256b7d5>](https://localhost:8080/#) in <module>()
1 timelag_config = OmegaConf.load(join(model_dir, "timelag", "model.yaml"))
----> 2 timelag_model = hydra.utils.instantiate(timelag_config.netG).to(device)
3 checkpoint = torch.load(join(model_dir, "timelag", "latest.pth"), map_location=lambda storage, loc: storage)
4 timelag_model.load_state_dict(checkpoint["state_dict"])
5 timelag_in_scaler = joblib.load(join(model_dir, "in_timelag_scaler.joblib"))
6 frames
[/usr/local/lib/python3.7/dist-packages/omegaconf/dictconfig.py](https://localhost:8080/#) in _get_node(self, key, validate_access, throw_on_missing_value, throw_on_missing_key)
468 if value is None:
469 if throw_on_missing_key:
--> 470 raise ConfigKeyError(f"Missing key {key}")
471 elif throw_on_missing_value and value._is_missing():
472 raise MissingMandatoryValue("Missing mandatory value: $KEY")
ConfigAttributeError: Missing key to
full_key: netG.to
object_type=dict
@r9y9 Any idea about that problem? Seams that it cannot be loaded into GPU, without the .to(device), it seams to work and break in the next instruction.
from nnsvs.
Sorry for the inconvenience. I am currently working on a huge refactoring. After finishing it, I will update the notebook.
from nnsvs.
Thank you! Can I help in some way?
from nnsvs.
Sure. I'd appreciate it if you can help to test once the huge refactoring settled down.
from nnsvs.
Hi @nicolalandro, I've merged the #81 and made a new demo notebook. I think the installation process now became much more simpler.
- Colab link: https://colab.research.google.com/github/r9y9/nnsvs/blob/master/notebooks/Demos.ipynb
- Github link: https://github.com/r9y9/nnsvs/tree/master/notebooks
Could you check if it works for you? Also, I'd appreciate it if you make a streamlet app version of the demo! Any feedbacks or PRs are welcomed.
Side note: The notebook above focuses on Japanese singing voice synthesis. It shouldn't be difficult to make a demo for other languages. However, I have no experience using nnsvs for non-Japanese languages and not sure what's the best idea.
from nnsvs.
Related Issues (20)
- Incorporate the uSFGAN training step into recipes
- Improvements related to NNSVS paper
- train_acoustic entry point missing from setup.py HOT 2
- Add DiffSinger configurations and recipes to reproduce experiments reported in NNSVS documentation HOT 6
- Diffusion-based acoustic models HOT 2
- from nnsvs.train_util import NpyFileSource HOT 1
- The combination of NPSSMDNMultistreamParametricModel and BiLSTMResF0NonAttentiveDecoder with use_mdn=True results in training failure HOT 4
- [suggeston] Add an warning for acoustic model config not matching feature generation
- Converting Enunu to NNSVS HOT 3
- A Question HOT 1
- Refactor svs.py to be more modular and extensible for ENUNU
- Remove the trainable post-filter functionality to make code simple
- A separate training script for F0 prediction model HOT 1
- Can nnsvs be run on AMD GPUs via ROCm? HOT 2
- Using Enunu english model on NNSVS HOT 3
- AttributeError: module 'matplotlib' has no attribute 'axes'
- Is it unnecessary to resample the audio which is not 48k to 48k? HOT 2
- !pip install nnsvs HOT 6
- Cannot install nnsvs HOT 2
- (suggestion) Ability to preface Gaussian Diffusion with a user-selectable acoustic model
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 nnsvs.