{
  "architectures": [
    "Mapperatorinator"
  ],
  "backbone_config": {
    "_name_or_path": "openai/whisper-small",
    "architectures": [
      "WhisperForConditionalGeneration"
    ],
    "begin_suppress_tokens": null,
    "bos_token_id": 1,
    "d_model": 768,
    "decoder_attention_heads": 12,
    "decoder_ffn_dim": 3072,
    "decoder_layers": 12,
    "decoder_start_token_id": 1,
    "encoder_attention_heads": 12,
    "encoder_ffn_dim": 3072,
    "encoder_layers": 12,
    "eos_token_id": 2,
    "forced_decoder_ids": null,
    "max_length": 448,
    "max_source_positions": 2048,
    "max_target_positions": 5120,
    "model_type": "whisper",
    "num_hidden_layers": 12,
    "num_mel_bins": 464,
    "pad_token_id": 0,
    "tie_word_embeddings": false,
    "torch_dtype": "float32",
    "use_cache": false,
    "vocab_size": 4607
  },
  "backbone_model_name": "openai/whisper-small",
  "bos_token_id": 1,
  "cond_dim": 128,
  "cond_embeds": 3,
  "decoder_start_token_id": 1,
  "disable_compile": true,
  "do_sample": true,
  "do_style_embed": false,
  "embed_decoder_input": true,
  "eos_token_id": 2,
  "hidden_size": 768,
  "hop_length": 128,
  "init_std": 0.02,
  "input_features": true,
  "is_encoder_decoder": true,
  "max_length": null,
  "max_source_positions": 2048,
  "max_target_positions": 5120,
  "model_type": "mapperatorinator",
  "n_fft": 1024,
  "n_mels": 80,
  "num_attention_heads": 12,
  "num_classes": 80742,
  "num_hidden_layers": 12,
  "num_mappers": 3731,
  "pad_token_id": 0,
  "rhythm_token_end": 3280,
  "rhythm_token_start": 3,
  "rhythm_weight": 1.0,
  "sample_rate": 16000,
  "top_k": 0,
  "torch_dtype": "float32",
  "transformers_version": "4.47.0",
  "vocab_size": 4607,
  "vocab_size_in": 8339
}