{ "_name_or_path": "facebook/mms-tts-tur", "activation_dropout": 0.1, "adapter_attn_dim": null, "adapter_kernel_size": 3, "adapter_stride": 2, "add_adapter": false, "apply_spec_augment": true, "architectures": [ "Wav2Vec2ForCTC" ], "attention_dropout": 0.0, "bos_token_id": 1, "classifier_proj_size": 256, "codevector_dim": 256, "contrastive_logits_temperature": 0.1, "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 ], "ctc_loss_reduction": "mean", "ctc_zero_infinity": false, "depth_separable_channels": 2, "depth_separable_num_layers": 3, "diversity_loss_weight": 0.1, "do_stable_layer_norm": false, "duration_predictor_dropout": 0.5, "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, "eos_token_id": 2, "feat_extract_activation": "gelu", "feat_extract_norm": "group", "feat_proj_dropout": 0.0, "feat_quantizer_dropout": 0.0, "ffn_dim": 768, "ffn_kernel_size": 3, "final_dropout": 0.1, "flow_size": 192, "hidden_act": "relu", "hidden_dropout": 0.0, "hidden_size": 192, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-05, "layerdrop": 0.0, "leaky_relu_slope": 0.1, "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, "model_type": "wav2vec2", "noise_scale": 0.667, "noise_scale_duration": 0.8, "num_adapter_layers": 3, "num_attention_heads": 2, "num_codevector_groups": 2, "num_codevectors_per_group": 320, "num_conv_pos_embedding_groups": 16, "num_conv_pos_embeddings": 128, "num_feat_extract_layers": 7, "num_hidden_layers": 6, "num_negatives": 100, "num_speakers": 1, "output_hidden_size": 192, "pad_token_id": 39, "posterior_encoder_num_wavenet_layers": 16, "prior_encoder_num_flows": 4, "prior_encoder_num_wavenet_layers": 4, "proj_codevector_dim": 256, "resblock_dilation_sizes": [ [ 1, 3, 5 ], [ 1, 3, 5 ], [ 1, 3, 5 ] ], "resblock_kernel_sizes": [ 3, 7, 11 ], "sampling_rate": 16000, "speaker_embedding_size": 0, "speaking_rate": 1.0, "spectrogram_bins": 513, "tdnn_dilation": [ 1, 2, 3, 1, 1 ], "tdnn_dim": [ 512, 512, 512, 512, 1500 ], "tdnn_kernel": [ 5, 3, 3, 1, 1 ], "torch_dtype": "float32", "transformers_version": "4.33.0", "upsample_initial_channel": 512, "upsample_kernel_sizes": [ 16, 16, 4, 4 ], "upsample_rates": [ 8, 8, 2, 2 ], "use_bias": true, "use_stochastic_duration_prediction": true, "use_weighted_layer_sum": false, "vocab_size": 42, "wavenet_dilation_rate": 1, "wavenet_dropout": 0.0, "wavenet_kernel_size": 5, "window_size": 4, "xvector_output_dim": 512 }