Spaces:
Sleeping
Sleeping
Delete models
Browse files
models/thpodcast/added_tokens.json
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"<unk>": 71
|
3 |
-
}
|
|
|
|
|
|
|
|
models/thpodcast/config.json
DELETED
@@ -1,108 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "./models",
|
3 |
-
"activation_dropout": 0.1,
|
4 |
-
"architectures": [
|
5 |
-
"VitsModelForPreTraining"
|
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": "4.47.1",
|
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": 71,
|
104 |
-
"wavenet_dilation_rate": 1,
|
105 |
-
"wavenet_dropout": 0.0,
|
106 |
-
"wavenet_kernel_size": 5,
|
107 |
-
"window_size": 4
|
108 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/thpodcast/preprocessor_config.json
DELETED
@@ -1,11 +0,0 @@
|
|
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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/thpodcast/special_tokens_map.json
DELETED
@@ -1,16 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"pad_token": {
|
3 |
-
"content": "า",
|
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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/thpodcast/tokenizer_config.json
DELETED
@@ -1,32 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_blank": true,
|
3 |
-
"added_tokens_decoder": {
|
4 |
-
"0": {
|
5 |
-
"content": "า",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": false,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false,
|
10 |
-
"special": true
|
11 |
-
},
|
12 |
-
"71": {
|
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": "tha",
|
25 |
-
"model_max_length": 1000000000000000019884624838656,
|
26 |
-
"normalize": true,
|
27 |
-
"pad_token": "า",
|
28 |
-
"phonemize": false,
|
29 |
-
"tokenizer_class": "VitsTokenizer",
|
30 |
-
"unk_token": "<unk>",
|
31 |
-
"verbose": false
|
32 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/thpodcast/vocab.json
DELETED
@@ -1,73 +0,0 @@
|
|
1 |
-
{
|
2 |
-
" ": 70,
|
3 |
-
"'": 59,
|
4 |
-
"-": 66,
|
5 |
-
"0": 60,
|
6 |
-
"1": 63,
|
7 |
-
"2": 65,
|
8 |
-
"4": 64,
|
9 |
-
"ก": 8,
|
10 |
-
"ข": 23,
|
11 |
-
"ค": 19,
|
12 |
-
"ฆ": 56,
|
13 |
-
"ง": 7,
|
14 |
-
"จ": 17,
|
15 |
-
"ฉ": 50,
|
16 |
-
"ช": 35,
|
17 |
-
"ซ": 43,
|
18 |
-
"ฌ": 69,
|
19 |
-
"ญ": 42,
|
20 |
-
"ฎ": 58,
|
21 |
-
"ฏ": 54,
|
22 |
-
"ฐ": 52,
|
23 |
-
"ฑ": 62,
|
24 |
-
"ฒ": 68,
|
25 |
-
"ณ": 46,
|
26 |
-
"ด": 21,
|
27 |
-
"ต": 20,
|
28 |
-
"ถ": 41,
|
29 |
-
"ท": 13,
|
30 |
-
"ธ": 44,
|
31 |
-
"น": 1,
|
32 |
-
"บ": 27,
|
33 |
-
"ป": 28,
|
34 |
-
"ผ": 40,
|
35 |
-
"ฝ": 51,
|
36 |
-
"พ": 14,
|
37 |
-
"ฟ": 48,
|
38 |
-
"ภ": 49,
|
39 |
-
"ม": 12,
|
40 |
-
"ย": 15,
|
41 |
-
"ร": 3,
|
42 |
-
"ฤ": 53,
|
43 |
-
"ล": 16,
|
44 |
-
"ว": 9,
|
45 |
-
"ศ": 45,
|
46 |
-
"ษ": 47,
|
47 |
-
"ส": 26,
|
48 |
-
"ห": 22,
|
49 |
-
"ฬ": 67,
|
50 |
-
"อ": 6,
|
51 |
-
"ฮ": 55,
|
52 |
-
"ะ": 10,
|
53 |
-
"ั": 11,
|
54 |
-
"า": 0,
|
55 |
-
"ิ": 24,
|
56 |
-
"ี": 18,
|
57 |
-
"ึ": 37,
|
58 |
-
"ื": 33,
|
59 |
-
"ุ": 36,
|
60 |
-
"ู": 30,
|
61 |
-
"เ": 4,
|
62 |
-
"แ": 25,
|
63 |
-
"โ": 39,
|
64 |
-
"ใ": 31,
|
65 |
-
"ไ": 29,
|
66 |
-
"็": 32,
|
67 |
-
"่": 2,
|
68 |
-
"้": 5,
|
69 |
-
"๊": 61,
|
70 |
-
"๋": 57,
|
71 |
-
"์": 34,
|
72 |
-
"ํ": 38
|
73 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|