Comments (6)
After all stream size 6 was good I was able to learn for the time being Can I fix the poor timing model estimation?There are many error estimates such as long vowels😂
from nnsvs.
Please check the error message.
from nnsvs.
stream_sizes: [180, 3, 1, 15]
has_dynamic_features: [True, True, False, True]
Error
stream_sizes: [180, 3, 1, 3]
Error
I don't know which parameter is correct because the stream size is unknown
I did it with the default value, but I get an error
from nnsvs.
I'm sorry
Did not add vibrato to StreamSize
I checked the operation
from nnsvs.
I see. I'll share you my config for vibrato modeling. Please hold on.
from nnsvs.
This is an example of conf/train/acoustic/model/acoustic_conv.yaml
for testing vibrato modeling with #73
# @package _group_
# (mgc, lf0, vuv, bap, vib)
stream_sizes: [180, 3, 1, 15, 6]
has_dynamic_features: [true, true, false, true, true]
num_windows: 3
# If None, automatically set based on stream sizes
stream_weights:
netG:
_target_: nnsvs.model.Conv1dResnet
in_dim: 348
out_dim: 205
hidden_dim: 128
num_layers: 6
dropout: 0.1
NOTE: in_dim
may differ depending on what hed file you use.
from nnsvs.
Related Issues (20)
- 想制作中文数据库 HOT 1
- assert exists(wav_path) AssertionError HOT 1
- Configs for 44.1 kHz
- 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
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.