File size: 1,478 Bytes
87b4df2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 | {
"_class_name": "LTX2VocoderWithBWE",
"_diffusers_version": "0.37.0.dev0",
"act_fn": "snakebeta",
"antialias": true,
"antialias_kernel_size": 12,
"antialias_ratio": 2,
"bwe_act_fn": "snakebeta",
"bwe_antialias": true,
"bwe_antialias_kernel_size": 12,
"bwe_antialias_ratio": 2,
"bwe_final_act_fn": null,
"bwe_final_bias": false,
"bwe_hidden_channels": 512,
"bwe_in_channels": 128,
"bwe_leaky_relu_negative_slope": 0.1,
"bwe_out_channels": 2,
"bwe_resnet_dilations": [
[
1,
3,
5
],
[
1,
3,
5
],
[
1,
3,
5
]
],
"bwe_resnet_kernel_sizes": [
3,
7,
11
],
"bwe_upsample_factors": [
6,
5,
2,
2,
2
],
"bwe_upsample_kernel_sizes": [
12,
11,
4,
4,
4
],
"filter_length": 512,
"final_act_fn": null,
"final_bias": false,
"hidden_channels": 1536,
"hop_length": 80,
"in_channels": 128,
"input_sampling_rate": 16000,
"leaky_relu_negative_slope": 0.1,
"num_mel_channels": 64,
"out_channels": 2,
"output_sampling_rate": 48000,
"resnet_dilations": [
[
1,
3,
5
],
[
1,
3,
5
],
[
1,
3,
5
]
],
"resnet_kernel_sizes": [
3,
7,
11
],
"upsample_factors": [
5,
2,
2,
2,
2,
2
],
"upsample_kernel_sizes": [
11,
4,
4,
4,
4,
4
],
"window_length": 512
}
|