Efficient-Large-Model/LTX-2.3-Diffusers

1{2  "_class_name": "LTX2VocoderWithBWE",3  "_diffusers_version": "0.37.0.dev0",4  "act_fn": "snakebeta",5  "antialias": true,6  "antialias_kernel_size": 12,7  "antialias_ratio": 2,8  "bwe_act_fn": "snakebeta",9  "bwe_antialias": true,10  "bwe_antialias_kernel_size": 12,11  "bwe_antialias_ratio": 2,12  "bwe_final_act_fn": null,13  "bwe_final_bias": false,14  "bwe_hidden_channels": 512,15  "bwe_in_channels": 128,16  "bwe_leaky_relu_negative_slope": 0.1,17  "bwe_out_channels": 2,18  "bwe_resnet_dilations": [19    [20      1,21      3,22      523    ],24    [25      1,26      3,27      528    ],29    [30      1,31      3,32      533    ]34  ],35  "bwe_resnet_kernel_sizes": [36    3,37    7,38    1139  ],40  "bwe_upsample_factors": [41    6,42    5,43    2,44    2,45    246  ],47  "bwe_upsample_kernel_sizes": [48    12,49    11,50    4,51    4,52    453  ],54  "filter_length": 512,55  "final_act_fn": null,56  "final_bias": false,57  "hidden_channels": 1536,58  "hop_length": 80,59  "in_channels": 128,60  "input_sampling_rate": 16000,61  "leaky_relu_negative_slope": 0.1,62  "num_mel_channels": 64,63  "out_channels": 2,64  "output_sampling_rate": 48000,65  "resnet_dilations": [66    [67      1,68      3,69      570    ],71    [72      1,73      3,74      575    ],76    [77      1,78      3,79      580    ]81  ],82  "resnet_kernel_sizes": [83    3,84    7,85    1186  ],87  "upsample_factors": [88    5,89    2,90    2,91    2,92    2,93    294  ],95  "upsample_kernel_sizes": [96    11,97    4,98    4,99    4,100    4,101    4102  ],103  "window_length": 512104}105