Hugging Face's logo

vsisik
/
speecht5_tts_SK_v4

TensorBoard
Safetensors
speecht5
Model card Files Metrics Community
vsisik commited on
Commit
d1fa5cd
•
1 Parent(s): 663a409

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. added_tokens.json +20 -0
  2. config.json +92 -0
  3. model.safetensors +3 -0
  4. runs/Oct18_14-58-37_b748442ff429/events.out.tfevents.1729263566.b748442ff429.1225.0 +3 -0
  5. special_tokens_map.json +134 -0
  6. spm_char.model +3 -0
  7. tokenizer_config.json +218 -0
  8. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<ctc_blank>": 80,
3
+ "<mask>": 79,
4
+ "á": 81,
5
+ "ä": 82,
6
+ "í": 85,
7
+ "ó": 89,
8
+ "ô": 90,
9
+ "ú": 94,
10
+ "ý": 95,
11
+ "č": 83,
12
+ "ď": 84,
13
+ "ĺ": 86,
14
+ "ľ": 87,
15
+ "ň": 88,
16
+ "ŕ": 91,
17
+ "š": 92,
18
+ "ť": 93,
19
+ "ž": 96
20
+ }
config.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/speecht5_tts",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "SpeechT5ForTextToSpeech"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "conv_bias": false,
11
+ "conv_dim": [
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512
19
+ ],
20
+ "conv_kernel": [
21
+ 10,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 2,
27
+ 2
28
+ ],
29
+ "conv_stride": [
30
+ 5,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2
37
+ ],
38
+ "decoder_attention_heads": 12,
39
+ "decoder_ffn_dim": 3072,
40
+ "decoder_layerdrop": 0.1,
41
+ "decoder_layers": 6,
42
+ "decoder_start_token_id": 2,
43
+ "encoder_attention_heads": 12,
44
+ "encoder_ffn_dim": 3072,
45
+ "encoder_layerdrop": 0.1,
46
+ "encoder_layers": 12,
47
+ "encoder_max_relative_position": 160,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.0,
52
+ "guided_attention_loss_num_heads": 2,
53
+ "guided_attention_loss_scale": 10.0,
54
+ "guided_attention_loss_sigma": 0.4,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "initializer_range": 0.02,
59
+ "is_encoder_decoder": true,
60
+ "layer_norm_eps": 1e-05,
61
+ "mask_feature_length": 10,
62
+ "mask_feature_min_masks": 0,
63
+ "mask_feature_prob": 0.0,
64
+ "mask_time_length": 10,
65
+ "mask_time_min_masks": 2,
66
+ "mask_time_prob": 0.05,
67
+ "max_length": null,
68
+ "max_speech_positions": 1876,
69
+ "max_text_positions": 600,
70
+ "model_type": "speecht5",
71
+ "num_conv_pos_embedding_groups": 16,
72
+ "num_conv_pos_embeddings": 128,
73
+ "num_feat_extract_layers": 7,
74
+ "num_mel_bins": 80,
75
+ "pad_token_id": 1,
76
+ "positional_dropout": 0.1,
77
+ "reduction_factor": 2,
78
+ "scale_embedding": false,
79
+ "speaker_embedding_dim": 512,
80
+ "speech_decoder_postnet_dropout": 0.5,
81
+ "speech_decoder_postnet_kernel": 5,
82
+ "speech_decoder_postnet_layers": 5,
83
+ "speech_decoder_postnet_units": 256,
84
+ "speech_decoder_prenet_dropout": 0.5,
85
+ "speech_decoder_prenet_layers": 2,
86
+ "speech_decoder_prenet_units": 256,
87
+ "torch_dtype": "float32",
88
+ "transformers_version": "4.46.0.dev0",
89
+ "use_cache": false,
90
+ "use_guided_attention_loss": true,
91
+ "vocab_size": 97
92
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b38d67e6cdca78c3b212e76b45789f0ee164ce761bf17d4592e55e254d6f1ed4
3
+ size 577838472
runs/Oct18_14-58-37_b748442ff429/events.out.tfevents.1729263566.b748442ff429.1225.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1c4e6d61e1a91825ba0a543d79c1db4b1cf8ae3767c11600dc105272ee13487
3
+ size 11084
special_tokens_map.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "á",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "ä",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "č",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "ď",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "é",
33
+ "lstrip": false,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "í",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "ĺ",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "ľ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "ň",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "ó",
68
+ "lstrip": false,
69
+ "normalized": true,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "ô",
75
+ "lstrip": false,
76
+ "normalized": true,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "ŕ",
82
+ "lstrip": false,
83
+ "normalized": true,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "š",
89
+ "lstrip": false,
90
+ "normalized": true,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "ť",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "ú",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "ý",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "ž",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ }
122
+ ],
123
+ "bos_token": "<s>",
124
+ "eos_token": "</s>",
125
+ "mask_token": {
126
+ "content": "<mask>",
127
+ "lstrip": true,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false
131
+ },
132
+ "pad_token": "<pad>",
133
+ "unk_token": "<unk>"
134
+ }
spm_char.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
3
+ size 238473
tokenizer_config.json ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "73": {
36
+ "content": "é",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "79": {
44
+ "content": "<mask>",
45
+ "lstrip": true,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "80": {
52
+ "content": "<ctc_blank>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "81": {
60
+ "content": "á",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "82": {
68
+ "content": "ä",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "83": {
76
+ "content": "č",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "84": {
84
+ "content": "ď",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "85": {
92
+ "content": "í",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "86": {
100
+ "content": "ĺ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "87": {
108
+ "content": "ľ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "88": {
116
+ "content": "ň",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "89": {
124
+ "content": "ó",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "90": {
132
+ "content": "ô",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "91": {
140
+ "content": "ŕ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "92": {
148
+ "content": "š",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "93": {
156
+ "content": "ť",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "94": {
164
+ "content": "ú",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "95": {
172
+ "content": "ý",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "96": {
180
+ "content": "ž",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ }
187
+ },
188
+ "additional_special_tokens": [
189
+ "á",
190
+ "ä",
191
+ "č",
192
+ "ď",
193
+ "é",
194
+ "í",
195
+ "ĺ",
196
+ "ľ",
197
+ "ň",
198
+ "ó",
199
+ "ô",
200
+ "ŕ",
201
+ "š",
202
+ "ť",
203
+ "ú",
204
+ "ý",
205
+ "ž"
206
+ ],
207
+ "bos_token": "<s>",
208
+ "clean_up_tokenization_spaces": false,
209
+ "eos_token": "</s>",
210
+ "mask_token": "<mask>",
211
+ "model_max_length": 600,
212
+ "normalize": false,
213
+ "pad_token": "<pad>",
214
+ "processor_class": "SpeechT5Processor",
215
+ "sp_model_kwargs": {},
216
+ "tokenizer_class": "SpeechT5Tokenizer",
217
+ "unk_token": "<unk>"
218
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28524c07fb3ce1909df76f1ffbd7e653f7df08a96127467dbf427c20de592352
3
+ size 5432