The Oud is one of the most foundational instruments to all of Arab music. It can be heard in nearly every song, whether the subgenre is rooted in pop or classical music.
Its distinguishing sound can be picked out of a crowd of string instruments with little to no training.
Our Unconditional Diffusion model ensures that we show respect to the sound and culture it has created.
This project could not have been done without
the following audio diffusion tools.Usage of this model is no different from any other audio diffusion model from HuggingFace.
1import torch
2from diffusers import DiffusionPipeline
3
4# Setup device and create generator
5device = "cuda" if torch.cuda.is_available() else "cpu"
6generator = torch.Generator(device=device)
7
8# Instantiate model
9model_id = "mijwiz-laboratories/oud_diffusion_unconditional_256"
10audio_diffusion = DiffusionPipeline.from_pretrained(model_id).to(device)
11
12# Set seed for generator
13seed = generator.seed()
14generator.manual_seed(seed)
15
16# Run inference
17output = audio_diffusion(generator=generator)
18image = output.images[0] # Mel spectrogram generated
19audio = output.audios[0, 0] # Playable audio file
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 oud samples degrades.
