|
--- |
|
license: openrail |
|
--- |
|
# Al-Nay (ุงููุงู) Unconditional Diffusion |
|
|
|
Al-Nay is one of the oldest instruments used to this date. |
|
With its roots in ancient Egypt nearly 5,000 years ago, it has become a staple in Arabic and Persian music. |
|
While the number of Nayzens โ the name associated with skilled players of the instrument โ has diminished over time, our Unconditional Diffusion model ensures that number is never zero. |
|
This project could not have been done without [the following audio diffusion tools.](https://github.com/teticio/audio-diffusion) |
|
|
|
## Usage |
|
|
|
Usage of this model is no different from any other audio diffusion model from HuggingFace. |
|
|
|
```python |
|
import torch |
|
from diffusers import DiffusionPipeline |
|
|
|
# Setup device and create generator |
|
device = "cuda" if torch.cuda.is_available() else "cpu" |
|
generator = torch.Generator(device=device) |
|
|
|
# Instantiate model |
|
model_id = "mijwiz-laboratories/al_nay_diffusion_unconditional_256" |
|
audio_diffusion = DiffusionPipeline.from_pretrained(model_id).to(device) |
|
|
|
# Set seed for generator |
|
seed = generator.seed() |
|
generator.manual_seed(seed) |
|
|
|
# Run inference |
|
output = audio_diffusion(generator=generator) |
|
image = output.images[0] # Mel spectrogram generated |
|
audio = output.audios[0, 0] # Playable audio file |
|
``` |
|
|
|
## Limitations of Model |
|
The dataset used was very small, so the diversity of snippets that can be generated is rather limited. Furthermore, with high intensity segments (think a human playing the instrument with high intensity,) |
|
the realism/naturalness of the generated flute degrades. |