config.json

{
  "model_type": "multispeaker_vits",
  "base_model": "facebook/mms-tts-hau",
  "n_speakers": 10,
  "model_class": "MultiSpeakerVITS",
  "architectures": [
    "MultiSpeakerVITS"
  ],
  "torch_dtype": "float32",
  "base_config": {
    "vocab_size": 34,
    "hidden_size": 192,
    "num_hidden_layers": 6,
    "num_attention_heads": 2,
    "window_size": 4,
    "use_bias": true,
    "ffn_dim": 768,
    "layerdrop": 0.1,
    "ffn_kernel_size": 3,
    "flow_size": 192,
    "spectrogram_bins": 513,
    "hidden_act": "relu",
    "hidden_dropout": 0.1,
    "attention_dropout": 0.1,
    "activation_dropout": 0.1,
    "initializer_range": 0.02,
    "layer_norm_eps": 1e-05,
    "use_stochastic_duration_prediction": true,
    "num_speakers": 10,
    "speaker_embedding_size": 192,
    "upsample_initial_channel": 512,
    "upsample_rates": [
      8,
      8,
      2,
      2
    ],
    "upsample_kernel_sizes": [
      16,
      16,
      4,
      4
    ],
    "resblock_kernel_sizes": [
      3,
      7,
      11
    ],
    "resblock_dilation_sizes": [
      [
        1,
        3,
        5
      ],
      [
        1,
        3,
        5
      ],
      [
        1,
        3,
        5
      ]
    ],
    "leaky_relu_slope": 0.1,
    "depth_separable_channels": 2,
    "depth_separable_num_layers": 3,
    "duration_predictor_flow_bins": 10,
    "duration_predictor_tail_bound": 5.0,
    "duration_predictor_kernel_size": 3,
    "duration_predictor_dropout": 0.5,
    "duration_predictor_num_flows": 4,
    "duration_predictor_filter_channels": 256,
    "prior_encoder_num_flows": 4,
    "prior_encoder_num_wavenet_layers": 4,
    "posterior_encoder_num_wavenet_layers": 16,
    "wavenet_kernel_size": 5,
    "wavenet_dilation_rate": 1,
    "wavenet_dropout": 0.0,
    "speaking_rate": 1.0,
    "noise_scale": 0.667,
    "noise_scale_duration": 0.8,
    "sampling_rate": 16000,
    "return_dict": true,
    "output_hidden_states": false,
    "output_attentions": false,
    "torchscript": false,
    "torch_dtype": "float32",
    "use_bfloat16": false,
    "tf_legacy_loss": false,
    "pruned_heads": {},
    "tie_word_embeddings": true,
    "chunk_size_feed_forward": 0,
    "is_encoder_decoder": false,
    "is_decoder": false,
    "cross_attention_hidden_size": null,
    "add_cross_attention": false,
    "tie_encoder_decoder": false,
    "max_length": 20,
    "min_length": 0,
    "do_sample": false,
    "early_stopping": false,
    "num_beams": 1,
    "num_beam_groups": 1,
    "diversity_penalty": 0.0,
    "temperature": 1.0,
    "top_k": 50,
    "top_p": 1.0,
    "typical_p": 1.0,
    "repetition_penalty": 1.0,
    "length_penalty": 1.0,
    "no_repeat_ngram_size": 0,
    "encoder_no_repeat_ngram_size": 0,
    "bad_words_ids": null,
    "num_return_sequences": 1,
    "output_scores": false,
    "return_dict_in_generate": false,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "remove_invalid_values": false,
    "exponential_decay_length_penalty": null,
    "suppress_tokens": null,
    "begin_suppress_tokens": null,
    "architectures": [
      "VitsModel"
    ],
    "finetuning_task": null,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "tokenizer_class": null,
    "prefix": null,
    "bos_token_id": null,
    "pad_token_id": null,
    "eos_token_id": null,
    "sep_token_id": null,
    "decoder_start_token_id": null,
    "task_specific_params": null,
    "problem_type": null,
    "_name_or_path": "facebook/mms-tts-hau",
    "_attn_implementation_autoset": true,
    "transformers_version": "4.51.3",
    "model_type": "vits"
  },
  "hidden_size": 192,
  "num_speakers": 10,
  "speaker_embedding_size": 192
}