hyojin99 commited on
Commit
80365df
·
verified ·
1 Parent(s): b6ffc3e

End of training

Browse files
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ko
4
+ license: apache-2.0
5
+ base_model: openai/whisper-small
6
+ tags:
7
+ - hf-asr-leaderboard
8
+ - generated_from_trainer
9
+ datasets:
10
+ - hyojin99/EBRC
11
+ model-index:
12
+ - name: ft_model
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # ft_model
20
+
21
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the EBRC dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.2978
24
+ - Cer: 10.5708
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-05
44
+ - train_batch_size: 32
45
+ - eval_batch_size: 16
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 50
50
+ - training_steps: 6000
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
56
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
57
+ | 0.3829 | 1.0 | 1500 | 0.3817 | 15.4574 |
58
+ | 0.1779 | 2.0 | 3000 | 0.3238 | 13.5614 |
59
+ | 0.0732 | 3.0 | 4500 | 0.2954 | 11.2004 |
60
+ | 0.0228 | 4.0 | 6000 | 0.2978 | 10.5708 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.42.0.dev0
66
+ - Pytorch 2.3.0+cu121
67
+ - Datasets 2.19.1
68
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 9,
5
+ 19
6
+ ],
7
+ [
8
+ 11,
9
+ 2
10
+ ],
11
+ [
12
+ 11,
13
+ 4
14
+ ],
15
+ [
16
+ 11,
17
+ 17
18
+ ],
19
+ [
20
+ 22,
21
+ 7
22
+ ],
23
+ [
24
+ 22,
25
+ 11
26
+ ],
27
+ [
28
+ 22,
29
+ 17
30
+ ],
31
+ [
32
+ 23,
33
+ 2
34
+ ],
35
+ [
36
+ 23,
37
+ 15
38
+ ]
39
+ ],
40
+ "begin_suppress_tokens": [
41
+ 220,
42
+ 50257
43
+ ],
44
+ "bos_token_id": 50257,
45
+ "decoder_start_token_id": 50258,
46
+ "eos_token_id": 50257,
47
+ "forced_decoder_ids": [
48
+ [
49
+ 1,
50
+ 50264
51
+ ],
52
+ [
53
+ 2,
54
+ 50359
55
+ ],
56
+ [
57
+ 3,
58
+ 50363
59
+ ]
60
+ ],
61
+ "is_multilingual": true,
62
+ "lang_to_id": {
63
+ "<|af|>": 50327,
64
+ "<|am|>": 50334,
65
+ "<|ar|>": 50272,
66
+ "<|as|>": 50350,
67
+ "<|az|>": 50304,
68
+ "<|ba|>": 50355,
69
+ "<|be|>": 50330,
70
+ "<|bg|>": 50292,
71
+ "<|bn|>": 50302,
72
+ "<|bo|>": 50347,
73
+ "<|br|>": 50309,
74
+ "<|bs|>": 50315,
75
+ "<|ca|>": 50270,
76
+ "<|cs|>": 50283,
77
+ "<|cy|>": 50297,
78
+ "<|da|>": 50285,
79
+ "<|de|>": 50261,
80
+ "<|el|>": 50281,
81
+ "<|en|>": 50259,
82
+ "<|es|>": 50262,
83
+ "<|et|>": 50307,
84
+ "<|eu|>": 50310,
85
+ "<|fa|>": 50300,
86
+ "<|fi|>": 50277,
87
+ "<|fo|>": 50338,
88
+ "<|fr|>": 50265,
89
+ "<|gl|>": 50319,
90
+ "<|gu|>": 50333,
91
+ "<|haw|>": 50352,
92
+ "<|ha|>": 50354,
93
+ "<|he|>": 50279,
94
+ "<|hi|>": 50276,
95
+ "<|hr|>": 50291,
96
+ "<|ht|>": 50339,
97
+ "<|hu|>": 50286,
98
+ "<|hy|>": 50312,
99
+ "<|id|>": 50275,
100
+ "<|is|>": 50311,
101
+ "<|it|>": 50274,
102
+ "<|ja|>": 50266,
103
+ "<|jw|>": 50356,
104
+ "<|ka|>": 50329,
105
+ "<|kk|>": 50316,
106
+ "<|km|>": 50323,
107
+ "<|kn|>": 50306,
108
+ "<|ko|>": 50264,
109
+ "<|la|>": 50294,
110
+ "<|lb|>": 50345,
111
+ "<|ln|>": 50353,
112
+ "<|lo|>": 50336,
113
+ "<|lt|>": 50293,
114
+ "<|lv|>": 50301,
115
+ "<|mg|>": 50349,
116
+ "<|mi|>": 50295,
117
+ "<|mk|>": 50308,
118
+ "<|ml|>": 50296,
119
+ "<|mn|>": 50314,
120
+ "<|mr|>": 50320,
121
+ "<|ms|>": 50282,
122
+ "<|mt|>": 50343,
123
+ "<|my|>": 50346,
124
+ "<|ne|>": 50313,
125
+ "<|nl|>": 50271,
126
+ "<|nn|>": 50342,
127
+ "<|no|>": 50288,
128
+ "<|oc|>": 50328,
129
+ "<|pa|>": 50321,
130
+ "<|pl|>": 50269,
131
+ "<|ps|>": 50340,
132
+ "<|pt|>": 50267,
133
+ "<|ro|>": 50284,
134
+ "<|ru|>": 50263,
135
+ "<|sa|>": 50344,
136
+ "<|sd|>": 50332,
137
+ "<|si|>": 50322,
138
+ "<|sk|>": 50298,
139
+ "<|sl|>": 50305,
140
+ "<|sn|>": 50324,
141
+ "<|so|>": 50326,
142
+ "<|sq|>": 50317,
143
+ "<|sr|>": 50303,
144
+ "<|su|>": 50357,
145
+ "<|sv|>": 50273,
146
+ "<|sw|>": 50318,
147
+ "<|ta|>": 50287,
148
+ "<|te|>": 50299,
149
+ "<|tg|>": 50331,
150
+ "<|th|>": 50289,
151
+ "<|tk|>": 50341,
152
+ "<|tl|>": 50348,
153
+ "<|tr|>": 50268,
154
+ "<|tt|>": 50351,
155
+ "<|uk|>": 50280,
156
+ "<|ur|>": 50290,
157
+ "<|uz|>": 50337,
158
+ "<|vi|>": 50278,
159
+ "<|yi|>": 50335,
160
+ "<|yo|>": 50325,
161
+ "<|zh|>": 50260
162
+ },
163
+ "max_initial_timestamp_index": 50,
164
+ "max_length": 448,
165
+ "no_timestamps_token_id": 50363,
166
+ "pad_token_id": 50257,
167
+ "prev_sot_token_id": 50361,
168
+ "return_timestamps": false,
169
+ "suppress_tokens": [],
170
+ "task_to_id": {
171
+ "transcribe": 50359,
172
+ "translate": 50358
173
+ },
174
+ "transformers_version": "4.42.0.dev0"
175
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f40ed957a6b9c1d526a6d108f3d2871d4490caffc2c0b45566b2f0ffa1def2ce
3
+ size 4992706480
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95b998ef50407b7f0dd5515cfbe3ce17747f768012bb4f48f7b3cd22b00274f
3
+ size 1180663192
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/May23_02-51-48_1ef4f73b8e95/events.out.tfevents.1716432710.1ef4f73b8e95.2441.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1d92d973baa3896861586360eaed7c7eb041001256edce2e930f885c9200b65
3
- size 70285
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a0892c722b31e583b46ffce0f56aa5d4cae1cc5b08f9385908252d74f0ee093
3
+ size 70639