How to just train condition audio-diffusion without text-condition? about audio-diffusion-pytorch HOT 3 CLOSED

from audio_diffusion_pytorch import DiffusionModel, UNetV0, VDiffusion, VSampler

model = DiffusionModel(
    net_t=UNetV0, # The model type used for diffusion 
    in_channels=2, # U-Net: number of input/output (audio) channels 
    channels=[8, 32, 64, 128, 256, 512, 512, 1024, 1024], # U-Net: channels at each layer
    factors=[1, 4, 4, 4, 2, 2, 2, 2, 2], # U-Net: downsampling and upsampling factors at each layer 
    items=[1, 2, 2, 2, 2, 2, 2, 4, 4], # U-Net: number of repeating items at each layer
    attentions=[0, 0, 0, 0, 0, 1, 1, 1, 1], # U-Net: attention enabled/disabled at each layer 
    attention_heads=8, # U-Net: number of attention heads per attention block
    attention_features=64, # U-Net: number of attention features per attention block,
    diffusion_t=VDiffusion, # The diffusion method used 
    sampler_t=VSampler, # The diffusion sampler used 
    embedding_features=768, # U-Net: embedding features
    cross_attentions=[0, 0, 0, 1, 1, 1, 1, 1, 1], # U-Net: cross-attention enabled/disabled at each layer 
)

# Train model with audio
audio_wave = torch.randn(1, 2, 2**18) # [batch, in_channels, length]
embedding = torch.randn(1, 1, 768) # [batch, num_embeddings, embedding_features] 
loss = model(audio_wave, embedding=embedding) 
loss.backward()

noise = torch.randn(1, 2, 2**18)
sample = model.sample(noise, embedding=embedding, num_steps=2)