haseong8012 commited on
Commit
71ffe4a
1 Parent(s): cd60e72

End of training

Browse files
Files changed (5) hide show
  1. README.md +54 -0
  2. config.json +1 -1
  3. generation_config.json +162 -0
  4. pytorch_model.bin +1 -1
  5. tokenizer_config.json +1 -1
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ko
4
+ license: apache-2.0
5
+ base_model: openai/whisper-tiny
6
+ tags:
7
+ - hf-asr-leaderboard
8
+ - generated_from_trainer
9
+ datasets:
10
+ - haseong8012/child-50k
11
+ model-index:
12
+ - name: whisper-tiny_child-50k
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
+ # whisper-tiny_child-50k
20
+
21
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the haseong8012/child-50k dataset.
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 3.75e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 500
47
+ - training_steps: 5000
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.34.0
52
+ - Pytorch 2.1.0+cu121
53
+ - Datasets 2.14.5
54
+ - Tokenizers 0.14.1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "openai/whisper-tiny",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
1
  {
2
+ "_name_or_path": "whisper-tiny_child-50k",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
generation_config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 2
6
+ ],
7
+ [
8
+ 3,
9
+ 0
10
+ ],
11
+ [
12
+ 3,
13
+ 2
14
+ ],
15
+ [
16
+ 3,
17
+ 3
18
+ ],
19
+ [
20
+ 3,
21
+ 4
22
+ ],
23
+ [
24
+ 3,
25
+ 5
26
+ ]
27
+ ],
28
+ "begin_suppress_tokens": [
29
+ 220,
30
+ 50257
31
+ ],
32
+ "bos_token_id": 50257,
33
+ "decoder_start_token_id": 50258,
34
+ "eos_token_id": 50257,
35
+ "forced_decoder_ids": [
36
+ [
37
+ 1,
38
+ 50264
39
+ ],
40
+ [
41
+ 2,
42
+ 50359
43
+ ],
44
+ [
45
+ 3,
46
+ 50363
47
+ ]
48
+ ],
49
+ "is_multilingual": true,
50
+ "lang_to_id": {
51
+ "<|af|>": 50327,
52
+ "<|am|>": 50334,
53
+ "<|ar|>": 50272,
54
+ "<|as|>": 50350,
55
+ "<|az|>": 50304,
56
+ "<|ba|>": 50355,
57
+ "<|be|>": 50330,
58
+ "<|bg|>": 50292,
59
+ "<|bn|>": 50302,
60
+ "<|bo|>": 50347,
61
+ "<|br|>": 50309,
62
+ "<|bs|>": 50315,
63
+ "<|ca|>": 50270,
64
+ "<|cs|>": 50283,
65
+ "<|cy|>": 50297,
66
+ "<|da|>": 50285,
67
+ "<|de|>": 50261,
68
+ "<|el|>": 50281,
69
+ "<|en|>": 50259,
70
+ "<|es|>": 50262,
71
+ "<|et|>": 50307,
72
+ "<|eu|>": 50310,
73
+ "<|fa|>": 50300,
74
+ "<|fi|>": 50277,
75
+ "<|fo|>": 50338,
76
+ "<|fr|>": 50265,
77
+ "<|gl|>": 50319,
78
+ "<|gu|>": 50333,
79
+ "<|haw|>": 50352,
80
+ "<|ha|>": 50354,
81
+ "<|he|>": 50279,
82
+ "<|hi|>": 50276,
83
+ "<|hr|>": 50291,
84
+ "<|ht|>": 50339,
85
+ "<|hu|>": 50286,
86
+ "<|hy|>": 50312,
87
+ "<|id|>": 50275,
88
+ "<|is|>": 50311,
89
+ "<|it|>": 50274,
90
+ "<|ja|>": 50266,
91
+ "<|jw|>": 50356,
92
+ "<|ka|>": 50329,
93
+ "<|kk|>": 50316,
94
+ "<|km|>": 50323,
95
+ "<|kn|>": 50306,
96
+ "<|ko|>": 50264,
97
+ "<|la|>": 50294,
98
+ "<|lb|>": 50345,
99
+ "<|ln|>": 50353,
100
+ "<|lo|>": 50336,
101
+ "<|lt|>": 50293,
102
+ "<|lv|>": 50301,
103
+ "<|mg|>": 50349,
104
+ "<|mi|>": 50295,
105
+ "<|mk|>": 50308,
106
+ "<|ml|>": 50296,
107
+ "<|mn|>": 50314,
108
+ "<|mr|>": 50320,
109
+ "<|ms|>": 50282,
110
+ "<|mt|>": 50343,
111
+ "<|my|>": 50346,
112
+ "<|ne|>": 50313,
113
+ "<|nl|>": 50271,
114
+ "<|nn|>": 50342,
115
+ "<|no|>": 50288,
116
+ "<|oc|>": 50328,
117
+ "<|pa|>": 50321,
118
+ "<|pl|>": 50269,
119
+ "<|ps|>": 50340,
120
+ "<|pt|>": 50267,
121
+ "<|ro|>": 50284,
122
+ "<|ru|>": 50263,
123
+ "<|sa|>": 50344,
124
+ "<|sd|>": 50332,
125
+ "<|si|>": 50322,
126
+ "<|sk|>": 50298,
127
+ "<|sl|>": 50305,
128
+ "<|sn|>": 50324,
129
+ "<|so|>": 50326,
130
+ "<|sq|>": 50317,
131
+ "<|sr|>": 50303,
132
+ "<|su|>": 50357,
133
+ "<|sv|>": 50273,
134
+ "<|sw|>": 50318,
135
+ "<|ta|>": 50287,
136
+ "<|te|>": 50299,
137
+ "<|tg|>": 50331,
138
+ "<|th|>": 50289,
139
+ "<|tk|>": 50341,
140
+ "<|tl|>": 50348,
141
+ "<|tr|>": 50268,
142
+ "<|tt|>": 50351,
143
+ "<|uk|>": 50280,
144
+ "<|ur|>": 50290,
145
+ "<|uz|>": 50337,
146
+ "<|vi|>": 50278,
147
+ "<|yi|>": 50335,
148
+ "<|yo|>": 50325,
149
+ "<|zh|>": 50260
150
+ },
151
+ "max_initial_timestamp_index": 1,
152
+ "max_length": 448,
153
+ "no_timestamps_token_id": 50363,
154
+ "pad_token_id": 50257,
155
+ "return_timestamps": false,
156
+ "suppress_tokens": [],
157
+ "task_to_id": {
158
+ "transcribe": 50359,
159
+ "translate": 50358
160
+ },
161
+ "transformers_version": "4.34.0"
162
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f2ea7ea447703d5958b6251e9a118689995c508139dcb1c16d59b26a98508c3
3
  size 151099494
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3064acf83f71097bcefa4e236785e3220647b4e069bc316e303766bfd8cee76f
3
  size 151099494
tokenizer_config.json CHANGED
@@ -5,7 +5,7 @@
5
  "50257": {
6
  "content": "<|endoftext|>",
7
  "lstrip": false,
8
- "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
 
5
  "50257": {
6
  "content": "<|endoftext|>",
7
  "lstrip": false,
8
+ "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true