Comments (3)
Hi -- yes, you can. Typically when I train StyleTTS2 to synthesise another language, I keep a bit of English in the dataset, just to make sure I retain the English speaking capability.
The other thing is that the reference you use often matters. If you are using a reference from a (for example) Spanish speaker and try to synthesise English, then you might run into an issue where you get a Spanish accent.
If none of this works, you can try to use this multilingual PL-BERT model on Huggingface - I just open-sourced it. https://huggingface.co/papercup-ai/multilingual-pl-bert
from styletts2.
You can maybe use RVC (or any voice conversion model) to convert an english reference to the target speaker you are trying to synthesise, and then use the RVC output as the reference for styletts2
from styletts2.
Got it, thanks for your reply! I was imagining that mixing the languages might be a solution.
I didn't pay attention to the reference, though. I have this problem that I don't have the reference in English, so maybe I'll think how can I get to work in this case. Do you have any ideas?
Also, good work with the PL Bert. It will definitely help me and others!
from styletts2.
Related Issues (20)
- Stage 2 Training Fails with NaN Loss on Single GPU Due to Inconsistent Checkpoint Keys
- Getting CUDA Out of memory error in Stage2 training HOT 13
- Multi-lingual training HOT 18
- In training Stage1 after 49th epoch getting RuntimeError: you can only change requires_grad flags of leaf variables, g_loss.requires_grad = True
- First stage training after 49th epoch (i.e., when epoch >= TMA_epoch)
- Getting error in d_loss.backward() of first_stage training
- Can the model learn accents not supported by espeak-ng?
- Joint training is failing with Assertion error
- In 2nd stage training AttributeError: 'AudioDiffusionConditional' object has no attribute 'module'
- Questions about Differentiable Duration Modeling HOT 1
- weird chinese pronunciation HOT 3
- Training PL-BERT on styletts2-community/multilingual-pl-bert
- Can anyone please share checkpoints that we get after we complete both stages of training HOT 3
- Model Size of fine tuned Model
- Can StyleTTS2 use phonemization from different languages to finetune or train?
- StyleTTS Python API doesn't detect devanagari script
- After training 1 epoch, train_first.py crashes: RuntimeError: Expected 2D (unbatched) or 3D (batched) input to conv1d, but got input of size: [1, 1, 1, 800] HOT 1
- Do we need lr scheduler?
- ImportError: A module that was compiled using NumPy 1.x cannot be run in NumPy 2.0.1 HOT 1
- Wav File not being read
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 styletts2.