{
  "_commit_hash": null,
  "architectures": [
    "BarkModel"
  ],
  "coarse_acoustics_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": [
      "BarkCoarseAcousticsModule"
    ],
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bias": false,
    "block_size": 1024,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dropout": 0.0,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "input_vocab_size": 12096,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "coarse_acoustics",
    "n_codes_given": 1,
    "n_codes_total": 8,
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_heads": 12,
    "num_layers": 12,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "output_vocab_size": 12096,
    "pad_token_id": null,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "float32",
    "torchscript": false,
    "transformers_version": "4.31.0.dev0",
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true
  },
  "coarse_infer_token": 12050,
  "coarse_rate_hz": 75,
  "coarse_semantic_pad_token": 12048,
  "codebook_size": 1024,
  "context_window_size": 1024,
  "fine_acoustics_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": [
      "BarkFineAcousticsModule"
    ],
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bias": false,
    "block_size": 1024,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dropout": 0.0,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "input_vocab_size": 1056,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "fine_acoustics",
    "n_codes_given": 1,
    "n_codes_total": 8,
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_heads": 12,
    "num_layers": 12,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "output_vocab_size": 1056,
    "pad_token_id": null,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "float32",
    "torchscript": false,
    "transformers_version": "4.31.0.dev0",
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true
  },
  "model_type": "bark",
  "n_coarse_codebooks": 2,
  "n_fine_codebooks": 8,
  "pretrained_encodec_name_or_path": "facebook/encodec_24khz",
  "sample_rate": 24000,
  "semantic_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": [
      "BarkSemanticModule"
    ],
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bias": false,
    "block_size": 1024,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dropout": 0.0,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "input_vocab_size": 129600,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "semantic",
    "n_codes_given": 1,
    "n_codes_total": 8,
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_heads": 12,
    "num_layers": 12,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "output_vocab_size": 10048,
    "pad_token_id": null,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "float32",
    "torchscript": false,
    "transformers_version": "4.31.0.dev0",
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true
  },
  "semantic_infer_token": 129599,
  "semantic_pad_token": 10000,
  "semantic_rate_hz": 49.9,
  "semantic_vocab_size": 10000,
  "text_encoding_offset": 10048,
  "text_pad_token": 129595,
  "torch_dtype": "float32",
  "transformers_version": null
}