Hugging Face's logo

cheelam
/
mms-tts-purepixel-finetuned

Text-to-Audio
Transformers
Safetensors
vits
Inference Endpoints
Model card Files Community
1
cheelam commited on
Commit
71d6586
·
verified ·
1 Parent(s): 32a22b9

Upload model

Browse files
Files changed (2) hide show
  1. config.json +108 -108
  2. model.safetensors +1 -1
config.json CHANGED
@@ -1,108 +1,108 @@
1
- {
2
- "_name_or_path": "./tmp/ml/output",
3
- "activation_dropout": 0.1,
4
- "architectures": [
5
- "VitsModel"
6
- ],
7
- "attention_dropout": 0.1,
8
- "depth_separable_channels": 2,
9
- "depth_separable_num_layers": 3,
10
- "discriminator_kernel_size": 5,
11
- "discriminator_period_channels": [
12
- 1,
13
- 32,
14
- 128,
15
- 512,
16
- 1024
17
- ],
18
- "discriminator_periods": [
19
- 2,
20
- 3,
21
- 5,
22
- 7,
23
- 11
24
- ],
25
- "discriminator_scale_channels": [
26
- 1,
27
- 16,
28
- 64,
29
- 256,
30
- 1024
31
- ],
32
- "discriminator_stride": 3,
33
- "duration_predictor_dropout": 0.5,
34
- "duration_predictor_filter_channels": 256,
35
- "duration_predictor_flow_bins": 10,
36
- "duration_predictor_kernel_size": 3,
37
- "duration_predictor_num_flows": 4,
38
- "duration_predictor_tail_bound": 5.0,
39
- "ffn_dim": 768,
40
- "ffn_kernel_size": 3,
41
- "flow_size": 192,
42
- "hidden_act": "relu",
43
- "hidden_dropout": 0.1,
44
- "hidden_size": 192,
45
- "hop_length": 256,
46
- "initializer_range": 0.02,
47
- "layer_norm_eps": 1e-05,
48
- "layerdrop": 0.1,
49
- "leaky_relu_slope": 0.1,
50
- "model_type": "vits",
51
- "noise_scale": 0.667,
52
- "noise_scale_duration": 0.8,
53
- "num_attention_heads": 2,
54
- "num_hidden_layers": 6,
55
- "num_speakers": 1,
56
- "posterior_encoder_num_wavenet_layers": 16,
57
- "prior_encoder_num_flows": 4,
58
- "prior_encoder_num_wavenet_layers": 4,
59
- "resblock_dilation_sizes": [
60
- [
61
- 1,
62
- 3,
63
- 5
64
- ],
65
- [
66
- 1,
67
- 3,
68
- 5
69
- ],
70
- [
71
- 1,
72
- 3,
73
- 5
74
- ]
75
- ],
76
- "resblock_kernel_sizes": [
77
- 3,
78
- 7,
79
- 11
80
- ],
81
- "sampling_rate": 16000,
82
- "segment_size": 8192,
83
- "speaker_embedding_size": 0,
84
- "speaking_rate": 1.0,
85
- "spectrogram_bins": 513,
86
- "torch_dtype": "float32",
87
- "transformers_version": "4.44.1",
88
- "upsample_initial_channel": 512,
89
- "upsample_kernel_sizes": [
90
- 16,
91
- 16,
92
- 4,
93
- 4
94
- ],
95
- "upsample_rates": [
96
- 8,
97
- 8,
98
- 2,
99
- 2
100
- ],
101
- "use_bias": true,
102
- "use_stochastic_duration_prediction": true,
103
- "vocab_size": 34,
104
- "wavenet_dilation_rate": 1,
105
- "wavenet_dropout": 0.0,
106
- "wavenet_kernel_size": 5,
107
- "window_size": 4
108
- }
 
1
+ {
2
+ "_name_or_path": "/opt/ml/output",
3
+ "activation_dropout": 0.1,
4
+ "architectures": [
5
+ "VitsModel"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "depth_separable_channels": 2,
9
+ "depth_separable_num_layers": 3,
10
+ "discriminator_kernel_size": 5,
11
+ "discriminator_period_channels": [
12
+ 1,
13
+ 32,
14
+ 128,
15
+ 512,
16
+ 1024
17
+ ],
18
+ "discriminator_periods": [
19
+ 2,
20
+ 3,
21
+ 5,
22
+ 7,
23
+ 11
24
+ ],
25
+ "discriminator_scale_channels": [
26
+ 1,
27
+ 16,
28
+ 64,
29
+ 256,
30
+ 1024
31
+ ],
32
+ "discriminator_stride": 3,
33
+ "duration_predictor_dropout": 0.5,
34
+ "duration_predictor_filter_channels": 256,
35
+ "duration_predictor_flow_bins": 10,
36
+ "duration_predictor_kernel_size": 3,
37
+ "duration_predictor_num_flows": 4,
38
+ "duration_predictor_tail_bound": 5.0,
39
+ "ffn_dim": 768,
40
+ "ffn_kernel_size": 3,
41
+ "flow_size": 192,
42
+ "hidden_act": "relu",
43
+ "hidden_dropout": 0.1,
44
+ "hidden_size": 192,
45
+ "hop_length": 256,
46
+ "initializer_range": 0.02,
47
+ "layer_norm_eps": 1e-05,
48
+ "layerdrop": 0.1,
49
+ "leaky_relu_slope": 0.1,
50
+ "model_type": "vits",
51
+ "noise_scale": 0.667,
52
+ "noise_scale_duration": 0.8,
53
+ "num_attention_heads": 2,
54
+ "num_hidden_layers": 6,
55
+ "num_speakers": 1,
56
+ "posterior_encoder_num_wavenet_layers": 16,
57
+ "prior_encoder_num_flows": 4,
58
+ "prior_encoder_num_wavenet_layers": 4,
59
+ "resblock_dilation_sizes": [
60
+ [
61
+ 1,
62
+ 3,
63
+ 5
64
+ ],
65
+ [
66
+ 1,
67
+ 3,
68
+ 5
69
+ ],
70
+ [
71
+ 1,
72
+ 3,
73
+ 5
74
+ ]
75
+ ],
76
+ "resblock_kernel_sizes": [
77
+ 3,
78
+ 7,
79
+ 11
80
+ ],
81
+ "sampling_rate": 16000,
82
+ "segment_size": 8192,
83
+ "speaker_embedding_size": 0,
84
+ "speaking_rate": 1.0,
85
+ "spectrogram_bins": 513,
86
+ "torch_dtype": "float32",
87
+ "transformers_version": "4.44.2",
88
+ "upsample_initial_channel": 512,
89
+ "upsample_kernel_sizes": [
90
+ 16,
91
+ 16,
92
+ 4,
93
+ 4
94
+ ],
95
+ "upsample_rates": [
96
+ 8,
97
+ 8,
98
+ 2,
99
+ 2
100
+ ],
101
+ "use_bias": true,
102
+ "use_stochastic_duration_prediction": true,
103
+ "vocab_size": 34,
104
+ "wavenet_dilation_rate": 1,
105
+ "wavenet_dropout": 0.0,
106
+ "wavenet_kernel_size": 5,
107
+ "window_size": 4
108
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52aa7a0d97f15bf053b72485d869180b555abb5bf188e4316bea8972ab99ee4c
3
  size 145227640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60624bb0acb68d5fca7ad23c9ffe497d2b9299c5f7ba0571dfb5b24fceddacbf
3
  size 145227640