Hugging Face's logo

jlvdoorn
/
whisper-tiny.en-atcosim

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
jlvdoorn commited on
Commit
b7a3206
•
1 Parent(s): f12d60b

Model save

Browse files
Files changed (4) hide show
  1. README.md +72 -0
  2. generation_config.json +148 -0
  3. pytorch_model.bin +1 -1
  4. runs/Jan13_14-42-30_gpu013/events.out.tfevents.1705153351.gpu013 +2 -2
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: openai/whisper-tiny.en
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: whisper-tiny.en-atcosim
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # whisper-tiny.en-atcosim
17
+
18
+ This model is a fine-tuned version of [openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0737
21
+ - Wer: 2.7135
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: 1e-05
41
+ - train_batch_size: 128
42
+ - eval_batch_size: 128
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: 10
47
+ - num_epochs: 100
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 0.4068 | 8.33 | 500 | 0.0639 | 2.4958 |
54
+ | 0.0021 | 16.67 | 1000 | 0.0638 | 2.3245 |
55
+ | 0.0006 | 25.0 | 1500 | 0.0665 | 2.3338 |
56
+ | 0.0003 | 33.33 | 2000 | 0.0680 | 2.2736 |
57
+ | 0.0002 | 41.67 | 2500 | 0.0693 | 2.3893 |
58
+ | 0.0001 | 50.0 | 3000 | 0.0703 | 2.4634 |
59
+ | 0.0001 | 58.33 | 3500 | 0.0713 | 2.4449 |
60
+ | 0.0001 | 66.67 | 4000 | 0.0720 | 2.4542 |
61
+ | 0.0001 | 75.0 | 4500 | 0.0727 | 2.4588 |
62
+ | 0.0001 | 83.33 | 5000 | 0.0732 | 2.6394 |
63
+ | 0.0001 | 91.67 | 5500 | 0.0736 | 2.7783 |
64
+ | 0.0001 | 100.0 | 6000 | 0.0737 | 2.7135 |
65
+
66
+
67
+ ### Framework versions
68
+
69
+ - Transformers 4.36.2
70
+ - Pytorch 2.1.2
71
+ - Datasets 2.15.0
72
+ - Tokenizers 0.15.0
generation_config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 1,
5
+ 0
6
+ ],
7
+ [
8
+ 2,
9
+ 0
10
+ ],
11
+ [
12
+ 2,
13
+ 5
14
+ ],
15
+ [
16
+ 3,
17
+ 0
18
+ ],
19
+ [
20
+ 3,
21
+ 1
22
+ ],
23
+ [
24
+ 3,
25
+ 2
26
+ ],
27
+ [
28
+ 3,
29
+ 3
30
+ ],
31
+ [
32
+ 3,
33
+ 4
34
+ ]
35
+ ],
36
+ "begin_suppress_tokens": [
37
+ 220,
38
+ 50256
39
+ ],
40
+ "bos_token_id": 50257,
41
+ "decoder_start_token_id": 50257,
42
+ "eos_token_id": 50256,
43
+ "forced_decoder_ids": [
44
+ [
45
+ 1,
46
+ 50362
47
+ ]
48
+ ],
49
+ "is_multilingual": false,
50
+ "max_initial_timestamp_index": 1,
51
+ "max_length": 448,
52
+ "no_timestamps_token_id": 50362,
53
+ "pad_token_id": 50256,
54
+ "return_timestamps": false,
55
+ "suppress_tokens": [
56
+ 1,
57
+ 2,
58
+ 7,
59
+ 8,
60
+ 9,
61
+ 10,
62
+ 14,
63
+ 25,
64
+ 26,
65
+ 27,
66
+ 28,
67
+ 29,
68
+ 31,
69
+ 58,
70
+ 59,
71
+ 60,
72
+ 61,
73
+ 62,
74
+ 63,
75
+ 90,
76
+ 91,
77
+ 92,
78
+ 93,
79
+ 357,
80
+ 366,
81
+ 438,
82
+ 532,
83
+ 685,
84
+ 705,
85
+ 796,
86
+ 930,
87
+ 1058,
88
+ 1220,
89
+ 1267,
90
+ 1279,
91
+ 1303,
92
+ 1343,
93
+ 1377,
94
+ 1391,
95
+ 1635,
96
+ 1782,
97
+ 1875,
98
+ 2162,
99
+ 2361,
100
+ 2488,
101
+ 3467,
102
+ 4008,
103
+ 4211,
104
+ 4600,
105
+ 4808,
106
+ 5299,
107
+ 5855,
108
+ 6329,
109
+ 7203,
110
+ 9609,
111
+ 9959,
112
+ 10563,
113
+ 10786,
114
+ 11420,
115
+ 11709,
116
+ 11907,
117
+ 13163,
118
+ 13697,
119
+ 13700,
120
+ 14808,
121
+ 15306,
122
+ 16410,
123
+ 16791,
124
+ 17992,
125
+ 19203,
126
+ 19510,
127
+ 20724,
128
+ 22305,
129
+ 22935,
130
+ 27007,
131
+ 30109,
132
+ 30420,
133
+ 33409,
134
+ 34949,
135
+ 40283,
136
+ 40493,
137
+ 40549,
138
+ 47282,
139
+ 49146,
140
+ 50257,
141
+ 50357,
142
+ 50358,
143
+ 50359,
144
+ 50360,
145
+ 50361
146
+ ],
147
+ "transformers_version": "4.36.2"
148
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ba894e951224bd939467ba93de29230190101bb2d551210302b77b2f221aad8
3
  size 151097958
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:307b9a821ab5154b874a218cdc9e826bff5fe9e6e7f598a1eeb9a6f0c9d4e242
3
  size 151097958
runs/Jan13_14-42-30_gpu013/events.out.tfevents.1705153351.gpu013 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:880885a1b63fcc10b41a491b88aca54da371194b8233c8a6fb0e1b00f099e80d
3
- size 10536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94a2c19a1a3a4a552ae92ee43cc3d66f1222061805fe867bb03cddc228356ca2
3
+ size 11208