Comments (7)
I'm gonna pin this in case someone else has similar problems. I don't know how to deal with this because I can't reproduce this problem with the oldest GPU I have access now (GTX 1080 Ti).
from styletts2.
The same problem happens to me, my GPU is A100. And using the CPU to infer cannot help for me, the noise is still there by using the CPU.
from styletts2.
@ruby11dog could you please share the details to reproduce this problem? It seems itβs not related to the version of GPUs then?
from styletts2.
@ruby11dog could you please share the details to reproduce this problem? It seems itβs not related to the version of GPUs then?
The noise will appear when inferencing with your pretrained model "epoch_2nd_00100.pth". But the noise seems to fade away with model i trained myself along with epoch increase in second stage.
Here is my related python package version: torch:2.1.0
from styletts2.
So weird, I tried in Colab (T4, V100 and A100) without specifying any version of the libraries it works perfectly fine: https://colab.research.google.com/drive/1k5OqSp8a-x-27xlaWr2kZh_9F9aBh39K
I'm really wondering what is the reason behind this problem. It doesn't seem like it's just the GPU version though.
from styletts2.
I have just ran into the same problem after training the model on the cloud using 4xA40 GPU's. I did inference both locally (RTX 3060 + CPU) and via the cloud computer (4xA40 + CPU). Doing inference on the cloud works fine without any background pitches. However, running it locally produces the background pitches (also when running the models on CPU, both on the cloud and locally).
After doing some investigation, it seems that the sampler is the culprit. Since it produces random output and my test is running either on the cloud or locally, it's not possible to set a seed producing similar outputs within the sampler.
A quick solution for testing the bug was to obtain the output of the sampler in the cloud and copy this output to my local pc. This output is then used at the local pc for further inference. Hereafter, the background pitch was gone and the sound was exactly produced as it should.
s_pred = sampler(noise,
embedding=bert_dur[0].unsqueeze(0), num_steps=diffusion_steps,
embedding_scale=embedding_scale).squeeze(0)
# Save torch tensor on the cloud
# torch.save(s_pred, 'sampled_tensor.pt')
# Obtain the tensor via rsync and load it locally
# s_pred = torch.load('sampled_tensor.pt')
At the moment, I don't have time to look into the sampler, but I think closer inspection of the sampler could lead to fixing this bug.
from styletts2.
After more investigation, I have solved the problem for myself. The problem for me was the sigma_data
in the config. In the default config, it is set to 0.2. During training, this variable changes and is written to a new config file, which is stored in your Models
folder. Doing inference with the default config file, I obtained the high pitch. Using the config file which is obtained during training, the pitch was gone and the sound was good. So this is the solution that works for me.
Btw, @yl4579 Thanks you for your great work, it's really awesome that you produced this and made your code open source!
from styletts2.
Related Issues (20)
- Strange Loss Behavior During Stage Two Training - Not Decreasing after Diff Epoch HOT 2
- Finetune on ljspeech or libritts? HOT 1
- Better LJSpeech or LibriTTS for finetuning a single speaker voice? Or training from scratch with not so much data? HOT 3
- SLM Adversarial Training did not start when finetuning HOT 11
- Second stage training with smaller window size HOT 1
- Possible Bug in Style Diffusion Inference Code
- Issue with impropper pauses and random bursts of noise
- Cannot Convert float NaN to integer HOT 1
- HELP WANTED!!!!!!!!!!! HOT 3
- asr negative loss
- Resuming finetuning uses second to last epoch
- Help Wanted For Stage-1 HOT 2
- Inference with multilingual PL-BERT Model HOT 4
- During training, the graphics memory has been continuously increasing
- May be a bug? input parameters for model.predictor_encoder and model.style_encoder in train_finetune.py
- S_loss = 0 ... why? HOT 2
- Inference Error: context_features exists but no features provided HOT 1
- Speech conditioning like tortoise TTS HOT 1
- FP8 Fine Tuning Crashes HOT 1
- Error Message After Using a fine tuned ASR Model
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from styletts2.