Comments (8)
A huge thank you for sharing the results. The main reason of using iSTFT here was its fast synthesis speed that it showed from its original VITS variant. As so, I would say the result is far beyond my expectations. Magnificent.
from mb-istft-vits2.
@FENRlR do you know by chance the optimal configs for different sampling rates? I need 16kHz, 24kHz and 48kHz.
from mb-istft-vits2.
Currently, no. It seems there were some issues with 16kHz sampling rate in the original iSTFT repo. I've never seen the other two, however.
from mb-istft-vits2.
@FENRlR hi, can you add me on discord and ping me? (id -> p0p4k)'
thanks.
from mb-istft-vits2.
Super neat! Was this on an A100? Looks like it took ~3 days?
from mb-istft-vits2.
I downloaded the model from the web disk you provided, and reported this error when reasoning, do you know how to solve it?
RuntimeError: Error(s) in loading state_dict for SynthesizerTrn:
size mismatch for enc_p.emb.weight: copying a param with shape torch.Size([155, 192]) from checkpoint, the shape in current model is torch.Size([205, 192]).
from mb-istft-vits2.
I downloaded the model from the web disk you provided, and reported this error when reasoning, do you know how to solve it? RuntimeError: Error(s) in loading state_dict for SynthesizerTrn: size mismatch for enc_p.emb.weight: copying a param with shape torch.Size([155, 192]) from checkpoint, the shape in current model is torch.Size([205, 192]).
Hey, it's possible that the repository have changed and some weight sizes don't match defaults anymore. The easiest way to run it is to go back to the commit that dates back to the time of the post, clone it, plug in the weights and launch it from there.
from mb-istft-vits2.
@Insensiblee Before reverting back to that commit, have you tried changing symbols?
The length of symbols he used for Russian is exactly 155, while 205 is the length of the default symbol. So I'm 90% sure that
you've forgot to modify it.
from mb-istft-vits2.
Related Issues (16)
- Training more Chinese speaking person error: ValueError: too many values to unpack (expected 3) HOT 2
- Multispeaker training issue HOT 3
- Boolean value subbands in istft_vits2_base.json? HOT 2
- rank error HOT 2
- Would it be possible to train and initialize training with previous checkpoint? HOT 8
- AttributeError: 'ResidualCouplingTransformersLayer2' object has no attribute 'remove_weight_norm' HOT 1
- My experience and pronunciation problems HOT 1
- How to go ahead by adding emotion as a trainable parameter? HOT 2
- ONNX format HOT 3
- KSS dataset for 490 epochs but the quality is not as good as I expected HOT 6
- Does batch size make a difference to end quality? HOT 2
- New feature: Deleting the previous .pth files when training
- The model for Chinese speech doesn't work after training for 1700 epochs HOT 3
- “ZeroDivisionError: integer division or modulo by zero” in Google Colab HOT 2
- ValueError: too many values to unpack (expected 2) 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 mb-istft-vits2.