Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch.
They are basically using text-conditioned AudioLM, but surprisingly with the embeddings from a text-audio contrastive learned model named MuLan. MuLan is what will be built out in this repository, with AudioLM modified from the other repository to support the music generation needs here.
$ pip install musiclm-pytorch
MuLaN
first needs to be trained
import torch
from musiclm_pytorch import MuLaN, AudioSpectrogramTransformer, TextTransformer
audio_transformer = AudioSpectrogramTransformer(
dim = 512,
depth = 6,
heads = 8,
dim_head = 64,
spec_n_fft = 128,
spec_win_length = 24,
spec_aug_stretch_factor = 0.8
)
text_transformer = TextTransformer(
dim = 512,
depth = 6,
heads = 8,
dim_head = 64
)
mulan = MuLaN(
audio_transformer = audio_transformer,
text_transformer = text_transformer
)
# get a ton of <sound, text> pairs and train
wavs = torch.randn(2, 1024)
texts = torch.randint(0, 20000, (2, 256))
loss = mulan(wavs, texts)
loss.backward()
# after much training, you can embed sounds and text into a joint embedding space
# for conditioning the audio LM
embeds = mulan.get_audio_latents(wavs) # during training
embeds = mulan.get_text_latents(texts) # during inference
[x] mulan seems to be using decoupled contrastive learning, offer that as an option
[ ] wrap mulan with mulan wrapper and quantize the output, project to audiolm dimensions
[ ] modify audiolm to accept conditioning embeddings, optionally take care of different dimensions through a separate projection
[ ] audiolm and mulan goes into musiclm and generate, filter with mulan
[ ] add a version of mulan to open clip
[ ] set all the proper spectrogram hyperparameters
[ ] email some contrastive learning experts and figure out why some papers are sharing the projection from embeddings to latent space
[ ] improvise a bit and give the audio transformer a position generating module before each attention layer
@inproceedings{Agostinelli2023MusicLMGM,
title = {MusicLM: Generating Music From Text},
author = {Andrea Agostinelli and Timo I. Denk and Zal{\'a}n Borsos and Jesse Engel and Mauro Verzetti and Antoine Caillon and Qingqing Huang and Aren Jansen and Adam Roberts and Marco Tagliasacchi and Matthew Sharifi and Neil Zeghidour and C. Frank},
year = {2023}
}
@article{Huang2022MuLanAJ,
title = {MuLan: A Joint Embedding of Music Audio and Natural Language},
author = {Qingqing Huang and Aren Jansen and Joonseok Lee and Ravi Ganti and Judith Yue Li and Daniel P. W. Ellis},
journal = {ArXiv},
year = {2022},
volume = {abs/2208.12415}
}
The only truth is music. - Jack Kerouac