Trimux commited on
Commit
f553ecc
1 Parent(s): be84a70

Upload model

Browse files
Files changed (2) hide show
  1. config.json +107 -0
  2. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "architectures": [
4
+ "VitsModelForPreTraining"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "depth_separable_channels": 2,
8
+ "depth_separable_num_layers": 3,
9
+ "discriminator_kernel_size": 5,
10
+ "discriminator_period_channels": [
11
+ 1,
12
+ 32,
13
+ 128,
14
+ 512,
15
+ 1024
16
+ ],
17
+ "discriminator_periods": [
18
+ 2,
19
+ 3,
20
+ 5,
21
+ 7,
22
+ 11
23
+ ],
24
+ "discriminator_scale_channels": [
25
+ 1,
26
+ 16,
27
+ 64,
28
+ 256,
29
+ 1024
30
+ ],
31
+ "discriminator_stride": 3,
32
+ "duration_predictor_dropout": 0.5,
33
+ "duration_predictor_filter_channels": 256,
34
+ "duration_predictor_flow_bins": 10,
35
+ "duration_predictor_kernel_size": 3,
36
+ "duration_predictor_num_flows": 4,
37
+ "duration_predictor_tail_bound": 5.0,
38
+ "ffn_dim": 768,
39
+ "ffn_kernel_size": 3,
40
+ "flow_size": 192,
41
+ "hidden_act": "relu",
42
+ "hidden_dropout": 0.1,
43
+ "hidden_size": 192,
44
+ "hop_length": 256,
45
+ "initializer_range": 0.02,
46
+ "layer_norm_eps": 1e-05,
47
+ "layerdrop": 0.1,
48
+ "leaky_relu_slope": 0.1,
49
+ "model_type": "vits",
50
+ "noise_scale": 0.667,
51
+ "noise_scale_duration": 0.8,
52
+ "num_attention_heads": 2,
53
+ "num_hidden_layers": 6,
54
+ "num_speakers": 1,
55
+ "posterior_encoder_num_wavenet_layers": 16,
56
+ "prior_encoder_num_flows": 4,
57
+ "prior_encoder_num_wavenet_layers": 4,
58
+ "resblock_dilation_sizes": [
59
+ [
60
+ 1,
61
+ 3,
62
+ 5
63
+ ],
64
+ [
65
+ 1,
66
+ 3,
67
+ 5
68
+ ],
69
+ [
70
+ 1,
71
+ 3,
72
+ 5
73
+ ]
74
+ ],
75
+ "resblock_kernel_sizes": [
76
+ 3,
77
+ 7,
78
+ 11
79
+ ],
80
+ "sampling_rate": 16000,
81
+ "segment_size": 8192,
82
+ "speaker_embedding_size": 0,
83
+ "speaking_rate": 1.0,
84
+ "spectrogram_bins": 513,
85
+ "torch_dtype": "float32",
86
+ "transformers_version": "4.35.1",
87
+ "upsample_initial_channel": 512,
88
+ "upsample_kernel_sizes": [
89
+ 16,
90
+ 16,
91
+ 4,
92
+ 4
93
+ ],
94
+ "upsample_rates": [
95
+ 8,
96
+ 8,
97
+ 2,
98
+ 2
99
+ ],
100
+ "use_bias": true,
101
+ "use_stochastic_duration_prediction": true,
102
+ "vocab_size": 26,
103
+ "wavenet_dilation_rate": 1,
104
+ "wavenet_dropout": 0.0,
105
+ "wavenet_kernel_size": 5,
106
+ "window_size": 4
107
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3054e05a4d8e4adc4a30e04d40db359bcdb36a1ac860ec4b0041ca5a469dcfc9
3
+ size 332151496