{
  "_bert_config_dict": {
    "_name_or_path": "./ckpts/chinese-roberta-wwm-ext-large",
    "add_cross_attention": false,
    "architectures": [
      "BertForMaskedLM"
    ],
    "attention_probs_dropout_prob": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "classifier_dropout": null,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "directionality": "bidi",
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-12,
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 512,
    "min_length": 0,
    "model_type": "bert",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 24,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_past": true,
    "output_scores": false,
    "pad_token_id": 0,
    "pooler_fc_size": 768,
    "pooler_num_attention_heads": 12,
    "pooler_num_fc_layers": 3,
    "pooler_size_per_head": 128,
    "pooler_type": "first_token_transform",
    "position_embedding_type": "absolute",
    "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": "float16",
    "torchscript": false,
    "transformers_version": "4.30.2",
    "type_vocab_size": 2,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 21128
  },
  "_gpt_config_dict": {
    "data": {
      "max_eval_sample": 8,
      "max_sec": 54,
      "num_workers": 4,
      "pad_val": 1024
    },
    "inference": {
      "top_k": 5
    },
    "model": {
      "EOS": 1024,
      "dropout": 0,
      "embedding_dim": 512,
      "head": 16,
      "hidden_dim": 512,
      "linear_units": 2048,
      "n_layer": 24,
      "phoneme_vocab_size": 512,
      "random_bert": 0,
      "vocab_size": 1025
    },
    "optimizer": {
      "decay_steps": 40000,
      "lr": 0.01,
      "lr_end": 0.0001,
      "lr_init": 1e-05,
      "warmup_steps": 2000
    },
    "output_dir": "logs/Lumi_294_dpo/logs_s1",
    "pretrained_s1": "GPT_SoVITS/pretrained_models/s1bert25hz-2kh-longer-epoch=68e-step=50232.ckpt",
    "train": {
      "batch_size": 1,
      "epochs": 15,
      "exp_name": "Lumi_294_dpo",
      "gradient_clip": 1.0,
      "half_weights_save_dir": "GPT_weights",
      "if_dpo": true,
      "if_save_every_weights": true,
      "if_save_latest": true,
      "precision": "16-mixed",
      "save_every_n_epoch": 5,
      "seed": 1234
    },
    "train_phoneme_path": "logs/Lumi_294_dpo/2-name2text.txt",
    "train_semantic_path": "logs/Lumi_294_dpo/6-name2semantic.tsv"
  },
  "_hps_dict": {
    "content_module": "cnhubert",
    "data": {
      "add_blank": true,
      "cleaned_text": true,
      "exp_dir": "logs/Lumi_294_dpo",
      "filter_length": 2048,
      "hop_length": 640,
      "max_wav_value": 32768.0,
      "mel_fmax": null,
      "mel_fmin": 0.0,
      "n_mel_channels": 128,
      "n_speakers": 300,
      "sampling_rate": 32000,
      "win_length": 2048
    },
    "model": {
      "filter_channels": 768,
      "freeze_quantizer": true,
      "gin_channels": 512,
      "hidden_channels": 192,
      "inter_channels": 192,
      "kernel_size": 3,
      "n_heads": 2,
      "n_layers": 6,
      "n_layers_q": 3,
      "p_dropout": 0.1,
      "resblock": "1",
      "resblock_dilation_sizes": [
        [
          1,
          3,
          5
        ],
        [
          1,
          3,
          5
        ],
        [
          1,
          3,
          5
        ]
      ],
      "resblock_kernel_sizes": [
        3,
        7,
        11
      ],
      "semantic_frame_rate": "25hz",
      "upsample_initial_channel": 512,
      "upsample_kernel_sizes": [
        16,
        16,
        8,
        2,
        2
      ],
      "upsample_rates": [
        10,
        8,
        2,
        2,
        2
      ],
      "use_spectral_norm": false
    },
    "name": "Lumi_294_dpo",
    "pretrain": null,
    "resume_step": null,
    "s2_ckpt_dir": "logs/Lumi_294_dpo",
    "save_weight_dir": "SoVITS_weights",
    "train": {
      "batch_size": 5,
      "betas": [
        0.8,
        0.99
      ],
      "c_kl": 1.0,
      "c_mel": 45,
      "epochs": 16,
      "eps": 1e-09,
      "eval_interval": 500,
      "fp16_run": true,
      "gpu_numbers": "0",
      "if_save_every_weights": true,
      "if_save_latest": true,
      "init_lr_ratio": 1,
      "learning_rate": 0.0001,
      "log_interval": 100,
      "lr_decay": 0.999875,
      "pretrained_s2D": "GPT_SoVITS/pretrained_models/s2D488k.pth",
      "pretrained_s2G": "GPT_SoVITS/pretrained_models/s2G488k.pth",
      "save_every_epoch": 4,
      "seed": 1234,
      "segment_size": 20480,
      "text_low_lr_rate": 0.4,
      "warmup_epochs": 0
    }
  },
  "_hubert_config_dict": {
    "_name_or_path": "./ckpts/chinese-hubert-base",
    "activation_dropout": 0.1,
    "add_cross_attention": false,
    "apply_spec_augment": true,
    "architectures": [
      "HubertModel"
    ],
    "attention_dropout": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 1,
    "chunk_size_feed_forward": 0,
    "classifier_proj_size": 256,
    "conv_bias": false,
    "conv_dim": [
      512,
      512,
      512,
      512,
      512,
      512,
      512
    ],
    "conv_kernel": [
      10,
      3,
      3,
      3,
      3,
      2,
      2
    ],
    "conv_stride": [
      5,
      2,
      2,
      2,
      2,
      2,
      2
    ],
    "cross_attention_hidden_size": null,
    "ctc_loss_reduction": "sum",
    "ctc_zero_infinity": false,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "do_stable_layer_norm": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "exponential_decay_length_penalty": null,
    "feat_extract_activation": "gelu",
    "feat_extract_norm": "group",
    "feat_proj_dropout": 0.0,
    "feat_proj_layer_norm": true,
    "final_dropout": 0.1,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "gelu",
    "hidden_dropout": 0.1,
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "layerdrop": 0.1,
    "length_penalty": 1.0,
    "mask_feature_length": 10,
    "mask_feature_min_masks": 0,
    "mask_feature_prob": 0.0,
    "mask_time_length": 10,
    "mask_time_min_masks": 2,
    "mask_time_prob": 0.05,
    "max_length": 20,
    "min_length": 0,
    "model_type": "hubert",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 12,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_conv_pos_embedding_groups": 16,
    "num_conv_pos_embeddings": 128,
    "num_feat_extract_layers": 7,
    "num_hidden_layers": 12,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 0,
    "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": "float16",
    "torchscript": false,
    "transformers_version": "4.30.2",
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_weighted_layer_sum": false,
    "vocab_size": 32
  },
  "_hubert_extractor_config_dict": {
    "_processor_class": null,
    "do_normalize": true,
    "feature_extractor_type": "Wav2Vec2FeatureExtractor",
    "feature_size": 1,
    "padding_side": "right",
    "padding_value": 0,
    "return_attention_mask": false,
    "sampling_rate": 16000
  },
  "architectures": [
    "GPTSoVITSModel"
  ],
  "auto_map": {
    "AutoConfig": "configuration_yags.GPTSoVITSConfig",
    "AutoModel": "modeling_yags.GPTSoVITSModel"
  },
  "model_type": "gpt_sovits",
  "prompt_language": "zh",
  "torch_dtype": "float32",
  "transformers_version": "4.30.2"
}