Hugging Face's logo

offiongbassey
/
mms-tts-yor-custom-base

Safetensors
vits
Model card Files
xet
 Community
offiongbassey commited on
Commit
8e49d49
·
verified ·
1 Parent(s): 0684642

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. added_tokens.json +3 -0
  2. config.json +83 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +11 -0
  5. special_tokens_map.json +16 -0
  6. tokenizer_config.json +30 -0
  7. vocab.json +83 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 43
3
+ }
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mms-tts-yor",
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
+ "duration_predictor_dropout": 0.5,
11
+ "duration_predictor_filter_channels": 256,
12
+ "duration_predictor_flow_bins": 10,
13
+ "duration_predictor_kernel_size": 3,
14
+ "duration_predictor_num_flows": 4,
15
+ "duration_predictor_tail_bound": 5.0,
16
+ "ffn_dim": 768,
17
+ "ffn_kernel_size": 3,
18
+ "flow_size": 192,
19
+ "hidden_act": "relu",
20
+ "hidden_dropout": 0.1,
21
+ "hidden_size": 192,
22
+ "initializer_range": 0.02,
23
+ "layer_norm_eps": 1e-05,
24
+ "layerdrop": 0.1,
25
+ "leaky_relu_slope": 0.1,
26
+ "model_type": "vits",
27
+ "noise_scale": 0.667,
28
+ "noise_scale_duration": 0.8,
29
+ "num_attention_heads": 2,
30
+ "num_hidden_layers": 6,
31
+ "num_speakers": 1,
32
+ "posterior_encoder_num_wavenet_layers": 16,
33
+ "prior_encoder_num_flows": 4,
34
+ "prior_encoder_num_wavenet_layers": 4,
35
+ "resblock_dilation_sizes": [
36
+ [
37
+ 1,
38
+ 3,
39
+ 5
40
+ ],
41
+ [
42
+ 1,
43
+ 3,
44
+ 5
45
+ ],
46
+ [
47
+ 1,
48
+ 3,
49
+ 5
50
+ ]
51
+ ],
52
+ "resblock_kernel_sizes": [
53
+ 3,
54
+ 7,
55
+ 11
56
+ ],
57
+ "sampling_rate": 16000,
58
+ "speaker_embedding_size": 0,
59
+ "speaking_rate": 1.0,
60
+ "spectrogram_bins": 513,
61
+ "torch_dtype": "float32",
62
+ "transformers_version": "4.35.1",
63
+ "upsample_initial_channel": 512,
64
+ "upsample_kernel_sizes": [
65
+ 16,
66
+ 16,
67
+ 4,
68
+ 4
69
+ ],
70
+ "upsample_rates": [
71
+ 8,
72
+ 8,
73
+ 2,
74
+ 2
75
+ ],
76
+ "use_bias": true,
77
+ "use_stochastic_duration_prediction": true,
78
+ "vocab_size": 81,
79
+ "wavenet_dilation_rate": 1,
80
+ "wavenet_dropout": 0.0,
81
+ "wavenet_kernel_size": 5,
82
+ "window_size": 4
83
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c07b5c97e4a0b72c01e6c32a5423a7cf9084a22241396b704c5035c175dde4b
3
+ size 145263736
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": "|",
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_blank": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "|",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "43": {
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
+ "is_uroman": false,
23
+ "language": "yor",
24
+ "model_max_length": 1000000000000000019884624838656,
25
+ "normalize": false,
26
+ "pad_token": "|",
27
+ "phonemize": false,
28
+ "tokenizer_class": "VitsTokenizer",
29
+ "unk_token": "<unk>"
30
+ }
vocab.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "!": 1,
3
+ "$": 2,
4
+ "&": 3,
5
+ "(": 4,
6
+ ")": 5,
7
+ ",": 6,
8
+ ".": 7,
9
+ "/": 8,
10
+ "0": 9,
11
+ "1": 10,
12
+ "2": 11,
13
+ "3": 12,
14
+ "4": 13,
15
+ "5": 14,
16
+ "6": 15,
17
+ "7": 16,
18
+ "8": 17,
19
+ "9": 18,
20
+ ":": 19,
21
+ ";": 20,
22
+ "<unk>": 80,
23
+ "?": 21,
24
+ "a": 22,
25
+ "b": 23,
26
+ "c": 24,
27
+ "d": 25,
28
+ "e": 26,
29
+ "f": 27,
30
+ "g": 28,
31
+ "h": 29,
32
+ "i": 30,
33
+ "j": 31,
34
+ "k": 32,
35
+ "l": 33,
36
+ "m": 34,
37
+ "n": 35,
38
+ "o": 36,
39
+ "p": 37,
40
+ "q": 38,
41
+ "r": 39,
42
+ "s": 40,
43
+ "t": 41,
44
+ "u": 42,
45
+ "v": 43,
46
+ "w": 44,
47
+ "x": 45,
48
+ "y": 46,
49
+ "z": 47,
50
+ "|": 0,
51
+ "À": 48,
52
+ "Á": 49,
53
+ "È": 50,
54
+ "É": 51,
55
+ "Ì": 52,
56
+ "Í": 53,
57
+ "Ò": 54,
58
+ "Ó": 55,
59
+ "Ù": 56,
60
+ "Ú": 57,
61
+ "ß": 58,
62
+ "ã": 59,
63
+ "æ": 60,
64
+ "ö": 61,
65
+ "ü": 62,
66
+ "ł": 63,
67
+ "Ń": 64,
68
+ "̣": 65,
69
+ "ḿ": 66,
70
+ "Ṣ": 67,
71
+ "ṣ": 68,
72
+ "Ẹ": 69,
73
+ "ẹ": 70,
74
+ "Ọ": 71,
75
+ "ọ": 72,
76
+ "–": 73,
77
+ "‘": 74,
78
+ "’": 75,
79
+ "“": 76,
80
+ "”": 77,
81
+ "▪": 78,
82
+ "●": 79
83
+ }