Matthijs commited on
Commit
b0a3b3e
1 Parent(s): 4355803

Upload model

Browse files
Files changed (2) hide show
  1. config.json +70 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "architectures": [
4
+ "VitsModel"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "duration_predictor_dropout": 0.5,
8
+ "duration_predictor_filter_channels": 256,
9
+ "duration_predictor_kernel_size": 3,
10
+ "duration_predictor_num_flows": 4,
11
+ "encoder_attention_heads": 2,
12
+ "encoder_ffn_dim": 768,
13
+ "encoder_layerdrop": 0.1,
14
+ "encoder_layers": 6,
15
+ "ffn_kernel_size": 3,
16
+ "flow_size": 192,
17
+ "hidden_act": "relu",
18
+ "hidden_dropout": 0.1,
19
+ "hidden_size": 192,
20
+ "initializer_range": 0.02,
21
+ "layer_norm_eps": 1e-05,
22
+ "leaky_relu_slope": 0.1,
23
+ "model_type": "vits",
24
+ "num_speakers": 1,
25
+ "prior_encoder_num_flows": 4,
26
+ "resblock_dilation_sizes": [
27
+ [
28
+ 1,
29
+ 3,
30
+ 5
31
+ ],
32
+ [
33
+ 1,
34
+ 3,
35
+ 5
36
+ ],
37
+ [
38
+ 1,
39
+ 3,
40
+ 5
41
+ ]
42
+ ],
43
+ "resblock_kernel_sizes": [
44
+ 3,
45
+ 7,
46
+ 11
47
+ ],
48
+ "speaker_embedding_size": 0,
49
+ "spectrogram_bins": 513,
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.31.0.dev0",
52
+ "upsample_initial_channel": 512,
53
+ "upsample_kernel_sizes": [
54
+ 16,
55
+ 16,
56
+ 4,
57
+ 4
58
+ ],
59
+ "upsample_rates": [
60
+ 8,
61
+ 8,
62
+ 2,
63
+ 2
64
+ ],
65
+ "use_stochastic_duration_prediction": true,
66
+ "vocab_size": 33,
67
+ "wavenet_dilation_rate": 1,
68
+ "wavenet_dropout": 0.0,
69
+ "wavenet_kernel_size": 5
70
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b882d4c510890479bb4330716bbf2a1ba55f1ebaa535466a5a07085495194109
3
+ size 145384437