Commit 9158bb65 authored by Phil Wang's avatar Phil Wang
Browse files

only possible because of stability

parent 7cf2ad4a

README.md

+4 −0
Original line number Diff line number Diff line
@@ -6,6 +6,10 @@ Implementation of <a href="https://google-research.github.io/seanet/musiclm/exam 


They are basically using text-conditioned <a href="https://github.com/lucidrains/audiolm-pytorch">AudioLM</a>, but surprisingly with the embeddings from a text-audio contrastive learned model named <a href="https://arxiv.org/abs/2208.12415">MuLan</a>. MuLan is what will be built out in this repository, with AudioLM modified from the other repository to support the music generation needs here.



## Appreciation



- <a href="https://stability.ai/">Stability.ai</a> for the generous sponsorship to work and open source cutting edge artificial intelligence research



## Citations



```bibtex

musiclm_pytorch/musiclm_pytorch.py

+1 −5
Original line number Diff line number Diff line
@@ -53,11 +53,7 @@ class Attention(nn.Module): 
    def forward(

        self,

        x,

        context = None,

        mask = None,

        attn_bias = None,

        prefix_context = None,

        prefix_context_mask = None

        mask = None

    ):

        b, n, _, device = *x.shape, x.device