{ "architectures": [ "EmoSpherePPForConditionalGeneration" ], "auto_map": { "AutoConfig": "configuration_emosphere_pp.EmoSpherePPConfig", "AutoModel": "modeling_emosphere_pp.EmoSpherePPForConditionalGeneration" }, "dtype": "float16", "duration_predictor_filter_channels": 256, "emotion_embedding_size": 768, "estimator_act_fn": "snakebeta", "estimator_channels": [ 256, 256 ], "estimator_dropout": 0.05, "estimator_ffn_mult": 4, "estimator_group_norm_groups": 8, "estimator_head_dim": 64, "estimator_num_blocks": 1, "estimator_num_heads": 2, "estimator_num_mid_blocks": 2, "initializer_range": 0.02, "layer_norm_eps": 0.0001, "model_type": "emosphere_pp", "num_mel_bins": 80, "orthogonality_loss_weight": 0.02, "prenet_dropout": 0.5, "prenet_kernel_size": 5, "prenet_num_layers": 3, "sampling_rate": 16000, "segment_size": 64, "sigma_min": 0.0001, "speaker_embedding_size": 512, "style_embedding_size": 64, "style_hidden_size": 1024, "text_dropout": 0.1, "text_ffn_dim": 768, "text_hidden_size": 192, "text_kernel_size": 3, "text_num_attention_heads": 2, "text_num_hidden_layers": 6, "text_window_size": 4, "transformers_version": "5.19.0", "vocab_size": 75, "vocoder_dtype": "float16", "vocoder_repo_id": "RetentionLabs/BigVGAN-16kHz-80band", "vocoder_revision": null }