models/config.json

{
    "_class_name": "Transformer2DModel",
    "_diffusers_version": "0.27.2",
    "in_channels": 8,
    "num_layers": 24,
    "inner_dim": 2560,
    "attention_head_dim": 128,
    "num_attention_heads": 20,
    "mlp_ratio": 2.5,
    "out_channels": 8,
    "max_position": 32768,
    "rope_theta": 1000000.0,
    "speaker_embedding_dim": 512,
    "text_embedding_dim": 768,
    "ssl_encoder_depths": [8, 8],
    "ssl_names": ["mert", "m-hubert"],
    "ssl_latent_dims": [1024, 768],
    "patch_size": [16, 1],
    "max_height": 16,
    "max_width": 32768,
    "lyric_encoder_vocab_size": 6693,
    "lyric_hidden_size": 1024
}