Diffusers documentation

Audio Diffusion

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v0.27.2).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Audio Diffusion

Audio Diffusion is by Robert Dargavel Smith, and it leverages the recent advances in image generation from diffusion models by converting audio samples to and from Mel spectrogram images.

Make sure to check out the Schedulers guide to learn how to explore the tradeoff between scheduler speed and quality, and see the reuse components across pipelines section to learn how to efficiently load the same components into multiple pipelines.

AudioDiffusionPipeline

class diffusers.AudioDiffusionPipeline

< >

( vqvae: AutoencoderKL unet: UNet2DConditionModel mel: Mel scheduler: typing.Union[diffusers.schedulers.scheduling_ddim.DDIMScheduler, diffusers.schedulers.scheduling_ddpm.DDPMScheduler] )

Parameters

  • vqae (AutoencoderKL) — Variational Auto-Encoder (VAE) model to encode and decode images to and from latent representations.
  • unet (UNet2DConditionModel) — A UNet2DConditionModel to denoise the encoded image latents.
  • mel (Mel) — Transform audio into a spectrogram.
  • scheduler (DDIMScheduler or DDPMScheduler) — A scheduler to be used in combination with unet to denoise the encoded image latents. Can be one of DDIMScheduler or DDPMScheduler.

Pipeline for audio diffusion.

This model inherits from DiffusionPipeline. Check the superclass documentation for the generic methods implemented for all pipelines (downloading, saving, running on a particular device, etc.).

__call__

< >

( batch_size: int = 1 audio_file: str = None raw_audio: ndarray = None slice: int = 0 start_step: int = 0 steps: int = None generator: Generator = None mask_start_secs: float = 0 mask_end_secs: float = 0 step_generator: Generator = None eta: float = 0 noise: Tensor = None encoding: Tensor = None return_dict = True ) → List[PIL Image]

Parameters

  • batch_size (int) — Number of samples to generate.
  • audio_file (str) — An audio file that must be on disk due to Librosa limitation.
  • raw_audio (np.ndarray) — The raw audio file as a NumPy array.
  • slice (int) — Slice number of audio to convert.
  • start_step (int) — Step to start diffusion from.
  • steps (int) — Number of denoising steps (defaults to 50 for DDIM and 1000 for DDPM).
  • generator (torch.Generator) — A torch.Generator to make generation deterministic.
  • mask_start_secs (float) — Number of seconds of audio to mask (not generate) at start.
  • mask_end_secs (float) — Number of seconds of audio to mask (not generate) at end.
  • step_generator (torch.Generator) — A torch.Generator used to denoise. None
  • eta (float) — Corresponds to parameter eta (η) from the DDIM paper. Only applies to the DDIMScheduler, and is ignored in other schedulers.
  • noise (torch.Tensor) — A noise tensor of shape (batch_size, 1, height, width) or None.
  • encoding (torch.Tensor) — A tensor for UNet2DConditionModel of shape (batch_size, seq_length, cross_attention_dim).
  • return_dict (bool) — Whether or not to return a AudioPipelineOutput, ImagePipelineOutput or a plain tuple.

Returns

List[PIL Image]

A list of Mel spectrograms (float, List[np.ndarray]) with the sample rate and raw audio.

The call function to the pipeline for generation.

Examples:

For audio diffusion:

import torch
from IPython.display import Audio
from diffusers import DiffusionPipeline

device = "cuda" if torch.cuda.is_available() else "cpu"
pipe = DiffusionPipeline.from_pretrained("teticio/audio-diffusion-256").to(device)

output = pipe()
display(output.images[0])
display(Audio(output.audios[0], rate=mel.get_sample_rate()))

For latent audio diffusion:

import torch
from IPython.display import Audio
from diffusers import DiffusionPipeline

device = "cuda" if torch.cuda.is_available() else "cpu"
pipe = DiffusionPipeline.from_pretrained("teticio/latent-audio-diffusion-256").to(device)

output = pipe()
display(output.images[0])
display(Audio(output.audios[0], rate=pipe.mel.get_sample_rate()))

For other tasks like variation, inpainting, outpainting, etc:

output = pipe(
    raw_audio=output.audios[0, 0],
    start_step=int(pipe.get_default_steps() / 2),
    mask_start_secs=1,
    mask_end_secs=1,
)
display(output.images[0])
display(Audio(output.audios[0], rate=pipe.mel.get_sample_rate()))

encode

< >

( images: typing.List[PIL.Image.Image] steps: int = 50 ) → np.ndarray

Parameters

  • images (List[PIL Image]) — List of images to encode.
  • steps (int) — Number of encoding steps to perform (defaults to 50).

Returns

np.ndarray

A noise tensor of shape (batch_size, 1, height, width).

Reverse the denoising step process to recover a noisy image from the generated image.

get_default_steps

< >

( ) → int

Returns

int

The number of steps.

Returns default number of steps recommended for inference.

slerp

< >

( x0: Tensor x1: Tensor alpha: float ) → torch.Tensor

Parameters

  • x0 (torch.Tensor) — The first tensor to interpolate between.
  • x1 (torch.Tensor) — Second tensor to interpolate between.
  • alpha (float) — Interpolation between 0 and 1

Returns

torch.Tensor

The interpolated tensor.

Spherical Linear intERPolation.

AudioPipelineOutput

class diffusers.AudioPipelineOutput

< >

( audios: ndarray )

Parameters

  • audios (np.ndarray) — List of denoised audio samples of a NumPy array of shape (batch_size, num_channels, sample_rate).

Output class for audio pipelines.

ImagePipelineOutput

class diffusers.ImagePipelineOutput

< >

( images: typing.Union[typing.List[PIL.Image.Image], numpy.ndarray] )

Parameters

  • images (List[PIL.Image.Image] or np.ndarray) — List of denoised PIL images of length batch_size or NumPy array of shape (batch_size, height, width, num_channels).

Output class for image pipelines.

Mel

class diffusers.Mel

< >

( x_res: int = 256 y_res: int = 256 sample_rate: int = 22050 n_fft: int = 2048 hop_length: int = 512 top_db: int = 80 n_iter: int = 32 )

Parameters

  • x_res (int) — x resolution of spectrogram (time).
  • y_res (int) — y resolution of spectrogram (frequency bins).
  • sample_rate (int) — Sample rate of audio.
  • n_fft (int) — Number of Fast Fourier Transforms.
  • hop_length (int) — Hop length (a higher number is recommended if y_res < 256).
  • top_db (int) — Loudest decibel value.
  • n_iter (int) — Number of iterations for Griffin-Lim Mel inversion.

audio_slice_to_image

< >

( slice: int ) → PIL Image

Parameters

  • slice (int) — Slice number of audio to convert (out of get_number_of_slices()).

Returns

PIL Image

A grayscale image of x_res x y_res.

Convert slice of audio to spectrogram.

get_audio_slice

< >

( slice: int = 0 ) → np.ndarray

Parameters

  • slice (int) — Slice number of audio (out of get_number_of_slices()).

Returns

np.ndarray

The audio slice as a NumPy array.

Get slice of audio.

get_number_of_slices

< >

( ) → int

Returns

int

Number of spectograms audio can be sliced into.

Get number of slices in audio.

get_sample_rate

< >

( ) → int

Returns

int

Sample rate of audio.

Get sample rate.

image_to_audio

< >

( image: Image ) → audio (np.ndarray)

Parameters

  • image (PIL Image) — An grayscale image of x_res x y_res.

Returns

audio (np.ndarray)

The audio as a NumPy array.

Converts spectrogram to audio.

load_audio

< >

( audio_file: str = None raw_audio: ndarray = None )

Parameters

  • audio_file (str) — An audio file that must be on disk due to Librosa limitation.
  • raw_audio (np.ndarray) — The raw audio file as a NumPy array.

Load audio.

set_resolution

< >

( x_res: int y_res: int )

Parameters

  • x_res (int) — x resolution of spectrogram (time).
  • y_res (int) — y resolution of spectrogram (frequency bins).

Set resolution.