mujadid-syahbana
commited on
Commit
•
ab97e17
1
Parent(s):
10eb4a5
Training in progress, epoch 1
Browse files
config.json
ADDED
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai/whisper-base",
|
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 |
+
50257
|
13 |
+
],
|
14 |
+
"bos_token_id": 50257,
|
15 |
+
"classifier_proj_size": 256,
|
16 |
+
"d_model": 512,
|
17 |
+
"decoder_attention_heads": 8,
|
18 |
+
"decoder_ffn_dim": 2048,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 6,
|
21 |
+
"decoder_start_token_id": 50258,
|
22 |
+
"dropout": 0.0,
|
23 |
+
"encoder_attention_heads": 8,
|
24 |
+
"encoder_ffn_dim": 2048,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 50257,
|
28 |
+
"finetuning_task": "audio-classification",
|
29 |
+
"forced_decoder_ids": [
|
30 |
+
[
|
31 |
+
1,
|
32 |
+
50259
|
33 |
+
],
|
34 |
+
[
|
35 |
+
2,
|
36 |
+
50359
|
37 |
+
],
|
38 |
+
[
|
39 |
+
3,
|
40 |
+
50363
|
41 |
+
]
|
42 |
+
],
|
43 |
+
"id2label": {
|
44 |
+
"0": "alif",
|
45 |
+
"1": "seen",
|
46 |
+
"10": "wao",
|
47 |
+
"11": "kaif",
|
48 |
+
"12": "duad",
|
49 |
+
"13": "faa",
|
50 |
+
"14": "tua",
|
51 |
+
"15": "suad",
|
52 |
+
"16": "ba",
|
53 |
+
"17": "noon",
|
54 |
+
"18": "yaa",
|
55 |
+
"19": "hha",
|
56 |
+
"2": "zua",
|
57 |
+
"20": "hamzah",
|
58 |
+
"21": "sheen",
|
59 |
+
"22": "meem",
|
60 |
+
"23": "quaf",
|
61 |
+
"24": "zhal",
|
62 |
+
"25": "sa",
|
63 |
+
"26": "jeem",
|
64 |
+
"27": "aain",
|
65 |
+
"28": "zaa",
|
66 |
+
"3": "ta",
|
67 |
+
"4": "kha",
|
68 |
+
"5": "dal",
|
69 |
+
"6": "haa",
|
70 |
+
"7": "laam",
|
71 |
+
"8": "raa",
|
72 |
+
"9": "ghain"
|
73 |
+
},
|
74 |
+
"init_std": 0.02,
|
75 |
+
"is_encoder_decoder": true,
|
76 |
+
"label2id": {
|
77 |
+
"aain": "27",
|
78 |
+
"alif": "0",
|
79 |
+
"ba": "16",
|
80 |
+
"dal": "5",
|
81 |
+
"duad": "12",
|
82 |
+
"faa": "13",
|
83 |
+
"ghain": "9",
|
84 |
+
"haa": "6",
|
85 |
+
"hamzah": "20",
|
86 |
+
"hha": "19",
|
87 |
+
"jeem": "26",
|
88 |
+
"kaif": "11",
|
89 |
+
"kha": "4",
|
90 |
+
"laam": "7",
|
91 |
+
"meem": "22",
|
92 |
+
"noon": "17",
|
93 |
+
"quaf": "23",
|
94 |
+
"raa": "8",
|
95 |
+
"sa": "25",
|
96 |
+
"seen": "1",
|
97 |
+
"sheen": "21",
|
98 |
+
"suad": "15",
|
99 |
+
"ta": "3",
|
100 |
+
"tua": "14",
|
101 |
+
"wao": "10",
|
102 |
+
"yaa": "18",
|
103 |
+
"zaa": "28",
|
104 |
+
"zhal": "24",
|
105 |
+
"zua": "2"
|
106 |
+
},
|
107 |
+
"mask_feature_length": 10,
|
108 |
+
"mask_feature_min_masks": 0,
|
109 |
+
"mask_feature_prob": 0.0,
|
110 |
+
"mask_time_length": 10,
|
111 |
+
"mask_time_min_masks": 2,
|
112 |
+
"mask_time_prob": 0.05,
|
113 |
+
"max_length": 448,
|
114 |
+
"max_source_positions": 1500,
|
115 |
+
"max_target_positions": 448,
|
116 |
+
"median_filter_width": 7,
|
117 |
+
"model_type": "whisper",
|
118 |
+
"num_hidden_layers": 6,
|
119 |
+
"num_mel_bins": 80,
|
120 |
+
"pad_token_id": 50257,
|
121 |
+
"scale_embedding": false,
|
122 |
+
"suppress_tokens": [
|
123 |
+
1,
|
124 |
+
2,
|
125 |
+
7,
|
126 |
+
8,
|
127 |
+
9,
|
128 |
+
10,
|
129 |
+
14,
|
130 |
+
25,
|
131 |
+
26,
|
132 |
+
27,
|
133 |
+
28,
|
134 |
+
29,
|
135 |
+
31,
|
136 |
+
58,
|
137 |
+
59,
|
138 |
+
60,
|
139 |
+
61,
|
140 |
+
62,
|
141 |
+
63,
|
142 |
+
90,
|
143 |
+
91,
|
144 |
+
92,
|
145 |
+
93,
|
146 |
+
359,
|
147 |
+
503,
|
148 |
+
522,
|
149 |
+
542,
|
150 |
+
873,
|
151 |
+
893,
|
152 |
+
902,
|
153 |
+
918,
|
154 |
+
922,
|
155 |
+
931,
|
156 |
+
1350,
|
157 |
+
1853,
|
158 |
+
1982,
|
159 |
+
2460,
|
160 |
+
2627,
|
161 |
+
3246,
|
162 |
+
3253,
|
163 |
+
3268,
|
164 |
+
3536,
|
165 |
+
3846,
|
166 |
+
3961,
|
167 |
+
4183,
|
168 |
+
4667,
|
169 |
+
6585,
|
170 |
+
6647,
|
171 |
+
7273,
|
172 |
+
9061,
|
173 |
+
9383,
|
174 |
+
10428,
|
175 |
+
10929,
|
176 |
+
11938,
|
177 |
+
12033,
|
178 |
+
12331,
|
179 |
+
12562,
|
180 |
+
13793,
|
181 |
+
14157,
|
182 |
+
14635,
|
183 |
+
15265,
|
184 |
+
15618,
|
185 |
+
16553,
|
186 |
+
16604,
|
187 |
+
18362,
|
188 |
+
18956,
|
189 |
+
20075,
|
190 |
+
21675,
|
191 |
+
22520,
|
192 |
+
26130,
|
193 |
+
26161,
|
194 |
+
26435,
|
195 |
+
28279,
|
196 |
+
29464,
|
197 |
+
31650,
|
198 |
+
32302,
|
199 |
+
32470,
|
200 |
+
36865,
|
201 |
+
42863,
|
202 |
+
47425,
|
203 |
+
49870,
|
204 |
+
50254,
|
205 |
+
50258,
|
206 |
+
50358,
|
207 |
+
50359,
|
208 |
+
50360,
|
209 |
+
50361,
|
210 |
+
50362
|
211 |
+
],
|
212 |
+
"torch_dtype": "float32",
|
213 |
+
"transformers_version": "4.36.0.dev0",
|
214 |
+
"use_cache": true,
|
215 |
+
"use_weighted_layer_sum": false,
|
216 |
+
"vocab_size": 51865
|
217 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08f9faf151992f9ce34d18552a0cc48813b37259570a51d0815363e69ba584a1
|
3 |
+
size 82928036
|
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 |
+
}
|
runs/Nov06_12-08-22_3bea23f1b63f/events.out.tfevents.1699272510.3bea23f1b63f.277.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bc67dbdf088000940978659a06cf42109972018da4e0b0f6d71887c62b730fc
|
3 |
+
size 7263
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa4c5d971f11c26f5d0bef58a5aa2f2f6bcd79c8122825e3f4971ebdf97343b8
|
3 |
+
size 4600
|