Comments (5)
Weird, not sure why the tensorboard didn't push to the hub. I have pushed it by hand now https://huggingface.co/teticio/audio-diffusion-ddim-256/tensorboard. Regarding your question, I would need to know what you mean by data - the images are expected to be in the range 0, 255 and are normalized accordingly.
from audio-diffusion.
I am training this model on dry vocal. Considering the accuracy, I changed the image data storage to float. My mel original value range is 1~-11 (hop size of 240). I normalized it before inputting it into the model. , normalize the value range to 0~1.The following is my loss curve, as well as image and audio.
from audio-diffusion.
Could you share the tensorboard of "teticio/audio-diffusion-ddim-256"? I am training the ddim model on dry vocal.
from audio-diffusion.
Thank you! This tensorboard is very helpful for me.
I have a batch of mostly dry singing data. I use the bigvgan scheme to extract its audio features as input data. The audio feature range is around [-10,1]. At present, I am training the ddpm model, and there is audible sound at 10epoch, but the same configuration (except num_train_steps=50) ddim is difficult to converge, even at 10epoch, it is still meaningless noise.
from audio-diffusion.
I think you need to train with more steps - I used 1000 if I remember right. You can do inference with much fewer steps (like 50).
from audio-diffusion.
Related Issues (20)
- How to run this scripts in linux? HOT 2
- Starting Point for Dataset HOT 4
- train_vae.py report error 'gpu' is not a valid DistributedType HOT 5
- Ask for the losses of vae HOT 1
- Recommended training hyperparameters for 44.1Khz & 48Khz Samplerate HOT 2
- diffusers v-0.12.0 causes import issues HOT 1
- Diffusers v0.12 removed the `ema_model.averaged_model` attribute HOT 1
- Increasing input size HOT 4
- how does the audio_to_images.py file work? HOT 3
- Whether the longer music sample is the repetition of a shorted sample? HOT 1
- NameError: name 'transformers' is not defined upon running model via Gradio HOT 2
- Dataset constriants HOT 16
- High fidelity training? HOT 3
- Training own music samples? HOT 1
- Can I input audio file then generate image HOT 2
- Numpy Error HOT 1
- AttributeError: 'AutoencoderKL' object has no attribute 'sample_size' HOT 3
- teticio/audio-diffusion-256 is really good HOT 1
- multi-gpu training 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 audio-diffusion.