Matthijs commited on
Commit
de0f9a1
1 Parent(s): d9985f4

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_layers": 6,
14
+ "ffn_kernel_size": 3,
15
+ "flow_size": 192,
16
+ "hidden_act": "relu",
17
+ "hidden_dropout": 0.1,
18
+ "hidden_size": 192,
19
+ "initializer_range": 0.02,
20
+ "layer_norm_eps": 1e-05,
21
+ "leaky_relu_slope": 0.1,
22
+ "model_type": "vits",
23
+ "num_speakers": 1,
24
+ "prior_encoder_num_flows": 4,
25
+ "resblock_dilation_sizes": [
26
+ [
27
+ 1,
28
+ 3,
29
+ 5
30
+ ],
31
+ [
32
+ 1,
33
+ 3,
34
+ 5
35
+ ],
36
+ [
37
+ 1,
38
+ 3,
39
+ 5
40
+ ]
41
+ ],
42
+ "resblock_kernel_sizes": [
43
+ 3,
44
+ 7,
45
+ 11
46
+ ],
47
+ "speaker_embedding_size": 0,
48
+ "spectrogram_bins": 513,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.31.0.dev0",
51
+ "upsample_initial_channel": 512,
52
+ "upsample_kernel_sizes": [
53
+ 16,
54
+ 16,
55
+ 4,
56
+ 4
57
+ ],
58
+ "upsample_rates": [
59
+ 8,
60
+ 8,
61
+ 2,
62
+ 2
63
+ ],
64
+ "use_cache": false,
65
+ "use_stochastic_duration_prediction": true,
66
+ "vocab_size": 38,
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 sha256:3ed8d8b7a1cb4f36b7124612ad93cafc9285abf6b26a36c76bef3ea4b17b8eae
3
+ size 145387701