config.json

{
  "_name_or_path": "./hf/ellie",
  "activation_dropout": 0.1,
  "architectures": [
    "BertVits2Model"
  ],
  "attention_dropout": 0.1,
  "bert_configs": [
    {
      "_name_or_path": "",
      "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": null,
      "torchscript": false,
      "transformers_version": "4.38.2",
      "type_vocab_size": 2,
      "typical_p": 1.0,
      "use_bfloat16": false,
      "use_cache": true,
      "vocab_size": 21128
    }
  ],
  "cond_layer_index": 2,
  "conditioning_layer_index": 2,
  "depth_separable_channels": 2,
  "depth_separable_num_layers": 3,
  "duration_predictor_dropout": 0.1,
  "duration_predictor_filter_channels": 256,
  "duration_predictor_flow_bins": 10,
  "duration_predictor_kernel_size": 3,
  "duration_predictor_num_flows": 4,
  "duration_predictor_tail_bound": 5.0,
  "ffn_dim": 768,
  "ffn_kernel_size": 3,
  "flow_size": 192,
  "hidden_act": "relu",
  "hidden_dropout": 0.1,
  "hidden_size": 192,
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.1,
  "leaky_relu_slope": 0.1,
  "model_type": "bert_vits2",
  "noise_scale": 0.667,
  "noise_scale_duration": 0.8,
  "num_attention_heads": 2,
  "num_hidden_layers": 6,
  "num_languages": 3,
  "num_speakers": 256,
  "num_tones": 11,
  "posterior_encoder_num_wavenet_layers": 16,
  "prior_encoder_num_flows": 4,
  "prior_encoder_num_flows_layers": 6,
  "prior_encoder_num_wavenet_layers": 4,
  "resblock_dilation_sizes": [
    [
      1,
      3,
      5
    ],
    [
      1,
      3,
      5
    ],
    [
      1,
      3,
      5
    ]
  ],
  "resblock_kernel_sizes": [
    3,
    7,
    11
  ],
  "sampling_rate": 44100,
  "speaker_embedding_size": 256,
  "speaking_rate": 1.0,
  "spectrogram_bins": 1025,
  "stochastic_duration_prediction_ratio": 0.0,
  "torch_dtype": "float32",
  "transformers_version": "4.38.2",
  "upsample_initial_channel": 512,
  "upsample_kernel_sizes": [
    16,
    16,
    8,
    2,
    2
  ],
  "upsample_rates": [
    8,
    8,
    2,
    2,
    2
  ],
  "use_bias": true,
  "use_transformer_flow": true,
  "vocab_size": 112,
  "wavenet_dilation_rate": 1,
  "wavenet_dropout": 0.0,
  "wavenet_kernel_size": 5,
  "window_size": 4
}