Upload 2 files
Browse files- config.json +172 -0
- preprocessor_config.json +14 -0
config.json
ADDED
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai/whisper-medium.en",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"apply_spec_augment": false,
|
6 |
+
"architectures": [
|
7 |
+
"WhisperForAudioClassification"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"begin_suppress_tokens": [
|
11 |
+
220,
|
12 |
+
50256
|
13 |
+
],
|
14 |
+
"bos_token_id": 50257,
|
15 |
+
"classifier_proj_size": 256,
|
16 |
+
"d_model": 1024,
|
17 |
+
"decoder_attention_heads": 16,
|
18 |
+
"decoder_ffn_dim": 4096,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 24,
|
21 |
+
"decoder_start_token_id": 50257,
|
22 |
+
"dropout": 0.0,
|
23 |
+
"encoder_attention_heads": 16,
|
24 |
+
"encoder_ffn_dim": 4096,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 24,
|
27 |
+
"eos_token_id": 50256,
|
28 |
+
"forced_decoder_ids": [
|
29 |
+
[
|
30 |
+
1,
|
31 |
+
50362
|
32 |
+
]
|
33 |
+
],
|
34 |
+
"id2label": {
|
35 |
+
"0": "blues",
|
36 |
+
"1": "classical",
|
37 |
+
"2": "country",
|
38 |
+
"3": "disco",
|
39 |
+
"4": "hiphop",
|
40 |
+
"5": "jazz",
|
41 |
+
"6": "metal",
|
42 |
+
"7": "pop",
|
43 |
+
"8": "reggae",
|
44 |
+
"9": "rock"
|
45 |
+
},
|
46 |
+
"init_std": 0.02,
|
47 |
+
"is_encoder_decoder": true,
|
48 |
+
"label2id": {
|
49 |
+
"blues": "0",
|
50 |
+
"classical": "1",
|
51 |
+
"country": "2",
|
52 |
+
"disco": "3",
|
53 |
+
"hiphop": "4",
|
54 |
+
"jazz": "5",
|
55 |
+
"metal": "6",
|
56 |
+
"pop": "7",
|
57 |
+
"reggae": "8",
|
58 |
+
"rock": "9"
|
59 |
+
},
|
60 |
+
"mask_feature_length": 10,
|
61 |
+
"mask_feature_min_masks": 0,
|
62 |
+
"mask_feature_prob": 0.0,
|
63 |
+
"mask_time_length": 10,
|
64 |
+
"mask_time_min_masks": 2,
|
65 |
+
"mask_time_prob": 0.05,
|
66 |
+
"max_length": 448,
|
67 |
+
"max_source_positions": 1500,
|
68 |
+
"max_target_positions": 448,
|
69 |
+
"median_filter_width": 7,
|
70 |
+
"model_type": "whisper",
|
71 |
+
"num_hidden_layers": 24,
|
72 |
+
"num_mel_bins": 80,
|
73 |
+
"pad_token_id": 50256,
|
74 |
+
"scale_embedding": false,
|
75 |
+
"suppress_tokens": [
|
76 |
+
1,
|
77 |
+
2,
|
78 |
+
7,
|
79 |
+
8,
|
80 |
+
9,
|
81 |
+
10,
|
82 |
+
14,
|
83 |
+
25,
|
84 |
+
26,
|
85 |
+
27,
|
86 |
+
28,
|
87 |
+
29,
|
88 |
+
31,
|
89 |
+
58,
|
90 |
+
59,
|
91 |
+
60,
|
92 |
+
61,
|
93 |
+
62,
|
94 |
+
63,
|
95 |
+
90,
|
96 |
+
91,
|
97 |
+
92,
|
98 |
+
93,
|
99 |
+
357,
|
100 |
+
366,
|
101 |
+
438,
|
102 |
+
532,
|
103 |
+
685,
|
104 |
+
705,
|
105 |
+
796,
|
106 |
+
930,
|
107 |
+
1058,
|
108 |
+
1220,
|
109 |
+
1267,
|
110 |
+
1279,
|
111 |
+
1303,
|
112 |
+
1343,
|
113 |
+
1377,
|
114 |
+
1391,
|
115 |
+
1635,
|
116 |
+
1782,
|
117 |
+
1875,
|
118 |
+
2162,
|
119 |
+
2361,
|
120 |
+
2488,
|
121 |
+
3467,
|
122 |
+
4008,
|
123 |
+
4211,
|
124 |
+
4600,
|
125 |
+
4808,
|
126 |
+
5299,
|
127 |
+
5855,
|
128 |
+
6329,
|
129 |
+
7203,
|
130 |
+
9609,
|
131 |
+
9959,
|
132 |
+
10563,
|
133 |
+
10786,
|
134 |
+
11420,
|
135 |
+
11709,
|
136 |
+
11907,
|
137 |
+
13163,
|
138 |
+
13697,
|
139 |
+
13700,
|
140 |
+
14808,
|
141 |
+
15306,
|
142 |
+
16410,
|
143 |
+
16791,
|
144 |
+
17992,
|
145 |
+
19203,
|
146 |
+
19510,
|
147 |
+
20724,
|
148 |
+
22305,
|
149 |
+
22935,
|
150 |
+
27007,
|
151 |
+
30109,
|
152 |
+
30420,
|
153 |
+
33409,
|
154 |
+
34949,
|
155 |
+
40283,
|
156 |
+
40493,
|
157 |
+
40549,
|
158 |
+
47282,
|
159 |
+
49146,
|
160 |
+
50257,
|
161 |
+
50357,
|
162 |
+
50358,
|
163 |
+
50359,
|
164 |
+
50360,
|
165 |
+
50361
|
166 |
+
],
|
167 |
+
"torch_dtype": "float32",
|
168 |
+
"transformers_version": "4.37.0.dev0",
|
169 |
+
"use_cache": true,
|
170 |
+
"use_weighted_layer_sum": false,
|
171 |
+
"vocab_size": 51864
|
172 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chunk_length": 30,
|
3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
4 |
+
"feature_size": 80,
|
5 |
+
"hop_length": 160,
|
6 |
+
"n_fft": 400,
|
7 |
+
"n_samples": 480000,
|
8 |
+
"nb_max_frames": 3000,
|
9 |
+
"padding_side": "right",
|
10 |
+
"padding_value": 0.0,
|
11 |
+
"processor_class": "WhisperProcessor",
|
12 |
+
"return_attention_mask": false,
|
13 |
+
"sampling_rate": 16000
|
14 |
+
}
|