---
datasets:
- flexthink/audiomnist
pipeline_tag: text-to-speech
---

This is a basic audio diffusion model using Unet. I've uploaded the weights and training code. 
The sample method of the model is used to generate whatever spoken digit you want.
I used the awesome code provided by HuggingFace audio diffusers to generate Mel-spectrograms which were then used to train the model.
For the model code I used the denoising-diffusion-pytorch repo found at https://github.com/lucidrains/denoising-diffusion-pytorch
![alt text](sample24_4_6.jpg "Title") ![alt text]( sample24_5_5.jpg
 "Title") ![alt text]( sample24_6_3.jpg
 "Title") ![alt text]( sample24_7_2.jpg
 "Title") 


The images found in the files are sample{epoch}_{sample#}_{digit}.jpg. They also have corresponding audio files.
The audio is VERY quiet, so turn up the speakers to hear better. (Just don't forget to turn it down after!)