Hugging Face's logo

ZoniaChatbot
/
female

Safetensors
vits
Model card Files
xet
 Community
ZoniaChatbot commited on
Commit
8132805
·
verified ·
1 Parent(s): b2a1a8a

Upload 7 files

Browse files
Files changed (7) hide show
  1. added_tokens.json +3 -0
  2. config.json +107 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +11 -0
  5. special_tokens_map.json +16 -0
  6. tokenizer_config.json +32 -0
  7. vocab.json +47 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 45
3
+ }
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": "4.48.1",
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": 45,
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 sha256:169010ed20585b6f5be9dbcc323fca73f440de5be2e908c2522dcf1542230c22
3
+ size 332166088
preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor_type": "VitsFeatureExtractor",
3
+ "feature_size": 80,
4
+ "hop_length": 256,
5
+ "max_wav_value": 32768.0,
6
+ "n_fft": 1024,
7
+ "padding_side": "right",
8
+ "padding_value": 0.0,
9
+ "return_attention_mask": false,
10
+ "sampling_rate": 16000
11
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "7",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "unk_token": {
10
+ "content": "<unk>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_blank": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "7",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "45": {
13
+ "content": "<unk>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "clean_up_tokenization_spaces": true,
22
+ "extra_special_tokens": {},
23
+ "is_uroman": false,
24
+ "language": "spa",
25
+ "model_max_length": 1000000000000000019884624838656,
26
+ "normalize": true,
27
+ "pad_token": "7",
28
+ "phonemize": false,
29
+ "tokenizer_class": "VitsTokenizer",
30
+ "unk_token": "<unk>",
31
+ "verbose": false
32
+ }
vocab.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 27,
3
+ "0": 5,
4
+ "1": 24,
5
+ "2": 36,
6
+ "3": 32,
7
+ "4": 12,
8
+ "5": 6,
9
+ "6": 44,
10
+ "7": 0,
11
+ "8": 8,
12
+ "9": 23,
13
+ "_": 22,
14
+ "a": 1,
15
+ "b": 31,
16
+ "c": 3,
17
+ "d": 29,
18
+ "e": 39,
19
+ "f": 25,
20
+ "g": 34,
21
+ "h": 19,
22
+ "i": 37,
23
+ "j": 33,
24
+ "k": 15,
25
+ "l": 35,
26
+ "m": 13,
27
+ "n": 20,
28
+ "o": 41,
29
+ "p": 9,
30
+ "q": 18,
31
+ "r": 43,
32
+ "s": 16,
33
+ "t": 26,
34
+ "u": 38,
35
+ "v": 2,
36
+ "x": 28,
37
+ "y": 10,
38
+ "z": 11,
39
+ "á": 17,
40
+ "é": 21,
41
+ "í": 30,
42
+ "ñ": 42,
43
+ "ó": 7,
44
+ "ú": 40,
45
+ "ü": 14,
46
+ "—": 4
47
+ }