clap_config:
  method: microsoft-clap
  audio_embed_dim: 1024
  config_root: ./ms_clap/src/configs
  model_name: 'clapcap'
  checkpoint: ./clapcap_weights_2023.pth
  window_length: 7.0
  window_overlap: 5.25
  max_num_window: 16
  max_num_fewshot: 4

model_config:
  cache_dir: None
  lang_encoder_path: facebook/opt-iml-max-1.3b
  tokenizer_path: facebook/opt-iml-max-1.3b
  cross_attn_every_n_layers: 1
  audio_transformer_kwargs: {
    n_head: 8,
    n_layers: 3,
    d_inner: 2048,
    max_num_media: 128,
    max_window_per_audio: 16,
  }