mohammadh128
commited on
Commit
·
e383f73
1
Parent(s):
8311c7c
Upload folder using huggingface_hub
Browse files- config.json +46 -0
- generation_config.json +11 -0
- preprocessor_config.json +11 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +1 -0
- vocab.json +228 -0
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.1,
|
3 |
+
"activation_function": "relu",
|
4 |
+
"architectures": [
|
5 |
+
"Speech2TextForConditionalGeneration"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": 0.0,
|
10 |
+
"conv_channels": 1024,
|
11 |
+
"conv_kernel_sizes": [
|
12 |
+
5,
|
13 |
+
5
|
14 |
+
],
|
15 |
+
"d_model": 256,
|
16 |
+
"decoder_attention_heads": 4,
|
17 |
+
"decoder_ffn_dim": 2048,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 6,
|
20 |
+
"decoder_start_token_id": 2,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"early_stopping": true,
|
23 |
+
"encoder_attention_heads": 4,
|
24 |
+
"encoder_ffn_dim": 2048,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 12,
|
27 |
+
"eos_token_id": 2,
|
28 |
+
"gradient_checkpointing": false,
|
29 |
+
"init_std": 0.02,
|
30 |
+
"input_channels": 1,
|
31 |
+
"input_feat_per_channel": 80,
|
32 |
+
"is_encoder_decoder": true,
|
33 |
+
"max_length": 200,
|
34 |
+
"max_source_positions": 6000,
|
35 |
+
"max_target_positions": 1024,
|
36 |
+
"model_type": "speech_to_text",
|
37 |
+
"num_beams": 5,
|
38 |
+
"num_conv_layers": 2,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"pad_token_id": 1,
|
41 |
+
"scale_embedding": true,
|
42 |
+
"tie_word_embeddings": false,
|
43 |
+
"transformers_version": "4.4.0.dev0",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 226
|
46 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"early_stopping": true,
|
6 |
+
"eos_token_id": 2,
|
7 |
+
"max_length": 200,
|
8 |
+
"num_beams": 5,
|
9 |
+
"pad_token_id": 1,
|
10 |
+
"transformers_version": "4.27.0.dev0"
|
11 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_ceptral_normalize": true,
|
3 |
+
"feature_size": 80,
|
4 |
+
"normalize_means": true,
|
5 |
+
"normalize_vars": true,
|
6 |
+
"num_mel_bins": 80,
|
7 |
+
"padding_side": "right",
|
8 |
+
"padding_value": 0.0,
|
9 |
+
"return_attention_mask": true,
|
10 |
+
"sampling_rate": 48000
|
11 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cac7668055b6192f23161ad487765e11212897280956aa34aa22500af01a01ba
|
3 |
+
size 108490245
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25987ef895641543e2d555789dac1871bf90f9032916e4979aa44d93983dec32
|
3 |
+
size 240137
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f67ce0407c56f7ed959d7958cb547b9c580482a82263d17249d49d695a2c3b9
|
3 |
+
size 108783320
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "do_upper_case": false, "do_lower_case": false, "tgt_lang": null, "lang_codes": null, "tokenizer_file": null}
|
vocab.json
ADDED
@@ -0,0 +1,228 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<s>": 0,
|
3 |
+
"<pad>": 1,
|
4 |
+
"</s>": 2,
|
5 |
+
"<unk>": 3,
|
6 |
+
"\u2581": 4,
|
7 |
+
"\u0627": 5,
|
8 |
+
"\u06cc": 6,
|
9 |
+
"\u0631": 7,
|
10 |
+
"\u062f": 8,
|
11 |
+
"\u0646": 9,
|
12 |
+
"\u0648": 10,
|
13 |
+
"\u0647": 11,
|
14 |
+
"\u0645": 12,
|
15 |
+
"\u062a": 13,
|
16 |
+
"\u0628": 14,
|
17 |
+
"\u0633": 15,
|
18 |
+
"\u06a9": 16,
|
19 |
+
"\u0644": 17,
|
20 |
+
"\u0634": 18,
|
21 |
+
".": 19,
|
22 |
+
"\u0632": 20,
|
23 |
+
"\u06af": 21,
|
24 |
+
"\u0641": 22,
|
25 |
+
"\u062e": 23,
|
26 |
+
"\u0642": 24,
|
27 |
+
"\u062c": 25,
|
28 |
+
"\u0639": 26,
|
29 |
+
"\u067e": 27,
|
30 |
+
"\u0622": 28,
|
31 |
+
"\u060c": 29,
|
32 |
+
"\u062d": 30,
|
33 |
+
"\u0637": 31,
|
34 |
+
"\u0686": 32,
|
35 |
+
"\u0635": 33,
|
36 |
+
"e": 34,
|
37 |
+
"a": 35,
|
38 |
+
"\u063a": 36,
|
39 |
+
"\"": 37,
|
40 |
+
"r": 38,
|
41 |
+
"o": 39,
|
42 |
+
"i": 40,
|
43 |
+
"n": 41,
|
44 |
+
"\u0636": 42,
|
45 |
+
"\u0630": 43,
|
46 |
+
"\u0638": 44,
|
47 |
+
"l": 45,
|
48 |
+
"t": 46,
|
49 |
+
"s": 47,
|
50 |
+
"\u00ab": 48,
|
51 |
+
"\u00bb": 49,
|
52 |
+
"\u062b": 50,
|
53 |
+
"\u0626": 51,
|
54 |
+
"u": 52,
|
55 |
+
"\u0698": 53,
|
56 |
+
"h": 54,
|
57 |
+
"\u061f": 55,
|
58 |
+
"(": 56,
|
59 |
+
")": 57,
|
60 |
+
"d": 58,
|
61 |
+
"\u064b": 59,
|
62 |
+
"\u06d5": 60,
|
63 |
+
"c": 61,
|
64 |
+
"m": 62,
|
65 |
+
"g": 63,
|
66 |
+
"y": 64,
|
67 |
+
"S": 65,
|
68 |
+
"k": 66,
|
69 |
+
"-": 67,
|
70 |
+
"C": 68,
|
71 |
+
"p": 69,
|
72 |
+
":": 70,
|
73 |
+
"!": 71,
|
74 |
+
"B": 72,
|
75 |
+
"M": 73,
|
76 |
+
"b": 74,
|
77 |
+
"\u0643": 75,
|
78 |
+
"T": 76,
|
79 |
+
"A": 77,
|
80 |
+
"w": 78,
|
81 |
+
"P": 79,
|
82 |
+
"v": 80,
|
83 |
+
"\u0623": 81,
|
84 |
+
"\u0650": 82,
|
85 |
+
"R": 83,
|
86 |
+
"f": 84,
|
87 |
+
"\u064a": 85,
|
88 |
+
"D": 86,
|
89 |
+
"H": 87,
|
90 |
+
"G": 88,
|
91 |
+
"L": 89,
|
92 |
+
"W": 90,
|
93 |
+
"F": 91,
|
94 |
+
"E": 92,
|
95 |
+
"K": 93,
|
96 |
+
"N": 94,
|
97 |
+
"J": 95,
|
98 |
+
"O": 96,
|
99 |
+
"z": 97,
|
100 |
+
"\u06c0": 98,
|
101 |
+
"I": 99,
|
102 |
+
"\u201d": 100,
|
103 |
+
"\u201c": 101,
|
104 |
+
"\u0621": 102,
|
105 |
+
"V": 103,
|
106 |
+
"x": 104,
|
107 |
+
"<": 105,
|
108 |
+
">": 106,
|
109 |
+
"\u061b": 107,
|
110 |
+
"\u0624": 108,
|
111 |
+
"\u064f": 109,
|
112 |
+
"'": 110,
|
113 |
+
",": 111,
|
114 |
+
"\u0649": 112,
|
115 |
+
"U": 113,
|
116 |
+
"Y": 114,
|
117 |
+
"j": 115,
|
118 |
+
"\u064e": 116,
|
119 |
+
"q": 117,
|
120 |
+
"\u2013": 118,
|
121 |
+
"Z": 119,
|
122 |
+
"\u0640": 120,
|
123 |
+
"X": 121,
|
124 |
+
"Q": 122,
|
125 |
+
"\u0651": 123,
|
126 |
+
"[": 124,
|
127 |
+
"]": 125,
|
128 |
+
"/": 126,
|
129 |
+
"\u0654": 127,
|
130 |
+
"1": 128,
|
131 |
+
"_": 129,
|
132 |
+
"\u2019": 130,
|
133 |
+
"0": 131,
|
134 |
+
"5": 132,
|
135 |
+
"\u2014": 133,
|
136 |
+
"\u0629": 134,
|
137 |
+
"\u064c": 135,
|
138 |
+
"2": 136,
|
139 |
+
"9": 137,
|
140 |
+
"3": 138,
|
141 |
+
"6": 139,
|
142 |
+
"?": 140,
|
143 |
+
"\u06ce": 141,
|
144 |
+
"4": 142,
|
145 |
+
"&": 143,
|
146 |
+
"\u06f1": 144,
|
147 |
+
"\u06f2": 145,
|
148 |
+
"8": 146,
|
149 |
+
"7": 147,
|
150 |
+
"*": 148,
|
151 |
+
"\\": 149,
|
152 |
+
"\u00ad": 150,
|
153 |
+
"\u00f1": 151,
|
154 |
+
"\u00ac": 152,
|
155 |
+
"\u00e1": 153,
|
156 |
+
"\u2018": 154,
|
157 |
+
"\u00e9": 155,
|
158 |
+
"\u00f6": 156,
|
159 |
+
"\u0670": 157,
|
160 |
+
";": 158,
|
161 |
+
"\u00f3": 159,
|
162 |
+
"\u00e4": 160,
|
163 |
+
"\u014d": 161,
|
164 |
+
"\u06f0": 162,
|
165 |
+
"\u06f9": 163,
|
166 |
+
"\u0625": 164,
|
167 |
+
"\u06f5": 165,
|
168 |
+
"\u00fc": 166,
|
169 |
+
"\u0652": 167,
|
170 |
+
"\u00ed": 168,
|
171 |
+
"\u06f4": 169,
|
172 |
+
"=": 170,
|
173 |
+
"\u0101": 171,
|
174 |
+
"\u06b5": 172,
|
175 |
+
"\u06f6": 173,
|
176 |
+
"\u00d6": 174,
|
177 |
+
"\u00fa": 175,
|
178 |
+
"\u06f3": 176,
|
179 |
+
"\u06f8": 177,
|
180 |
+
"\u00c9": 178,
|
181 |
+
"\u00e3": 179,
|
182 |
+
"\u00e8": 180,
|
183 |
+
"\u00f0": 181,
|
184 |
+
"\u00f8": 182,
|
185 |
+
"\u0103": 183,
|
186 |
+
"\u0142": 184,
|
187 |
+
"\u03c0": 185,
|
188 |
+
"\u0438": 186,
|
189 |
+
"\u043a": 187,
|
190 |
+
"\u064d": 188,
|
191 |
+
"\u066c": 189,
|
192 |
+
"\u06a4": 190,
|
193 |
+
"%": 191,
|
194 |
+
"\u00c3": 192,
|
195 |
+
"\u00d3": 193,
|
196 |
+
"\u00e2": 194,
|
197 |
+
"\u00e6": 195,
|
198 |
+
"\u00f4": 196,
|
199 |
+
"\u00fe": 197,
|
200 |
+
"\u0107": 198,
|
201 |
+
"\u010c": 199,
|
202 |
+
"\u010d": 200,
|
203 |
+
"\u012b": 201,
|
204 |
+
"\u0153": 202,
|
205 |
+
"\u0160": 203,
|
206 |
+
"\u0161": 204,
|
207 |
+
"\u016b": 205,
|
208 |
+
"\u02bb": 206,
|
209 |
+
"\u0412": 207,
|
210 |
+
"\u0435": 208,
|
211 |
+
"\u0437": 209,
|
212 |
+
"\u0439": 210,
|
213 |
+
"\u043b": 211,
|
214 |
+
"\u043d": 212,
|
215 |
+
"\u044c": 213,
|
216 |
+
"\u044f": 214,
|
217 |
+
"\u0695": 215,
|
218 |
+
"\u0696": 216,
|
219 |
+
"\u06c6": 217,
|
220 |
+
"\u06f7": 218,
|
221 |
+
"\u1e43": 219,
|
222 |
+
"\u2261": 220,
|
223 |
+
"\u2500": 221,
|
224 |
+
"\u4eac": 222,
|
225 |
+
"\u5927": 223,
|
226 |
+
"\u90fd": 224,
|
227 |
+
"\u962a": 225
|
228 |
+
}
|