Hugging Face's logo

khaingsmon
/
whisper2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
khaingsmon commited on
Commit
70120f2
•
1 Parent(s): 8542237

Model save

Browse files
Files changed (2) hide show
  1. README.md +110 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: whisper2
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
+ # whisper2
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: 0.5233
21
+ - Wer: 31.1083
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: 64
42
+ - eval_batch_size: 8
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: 500
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:------:|:----:|:---------------:|:-------:|
53
+ | 3.9553 | 0.1408 | 10 | 3.9646 | 74.8741 |
54
+ | 3.9548 | 0.2817 | 20 | 3.8794 | 77.6763 |
55
+ | 3.8127 | 0.4225 | 30 | 3.7405 | 76.4169 |
56
+ | 3.6178 | 0.5634 | 40 | 3.5547 | 75.3149 |
57
+ | 3.3992 | 0.7042 | 50 | 3.3235 | 70.2771 |
58
+ | 3.1416 | 0.8451 | 60 | 3.0402 | 67.8526 |
59
+ | 2.8052 | 0.9859 | 70 | 2.6852 | 65.9635 |
60
+ | 2.3513 | 1.1268 | 80 | 2.2235 | 68.3249 |
61
+ | 1.893 | 1.2676 | 90 | 1.6708 | 63.8224 |
62
+ | 1.2871 | 1.4085 | 100 | 1.1645 | 63.2557 |
63
+ | 0.9146 | 1.5493 | 110 | 0.8785 | 56.8325 |
64
+ | 0.8044 | 1.6901 | 120 | 0.7907 | 46.9773 |
65
+ | 0.6634 | 1.8310 | 130 | 0.7425 | 47.4811 |
66
+ | 0.6722 | 1.9718 | 140 | 0.7100 | 45.9068 |
67
+ | 0.6823 | 2.1127 | 150 | 0.6854 | 42.4118 |
68
+ | 0.5802 | 2.2535 | 160 | 0.6659 | 40.4282 |
69
+ | 0.6084 | 2.3944 | 170 | 0.6503 | 40.8375 |
70
+ | 0.6038 | 2.5352 | 180 | 0.6346 | 41.4987 |
71
+ | 0.5095 | 2.6761 | 190 | 0.6247 | 42.0340 |
72
+ | 0.5251 | 2.8169 | 200 | 0.6155 | 39.3577 |
73
+ | 0.5699 | 2.9577 | 210 | 0.6046 | 38.3501 |
74
+ | 0.4839 | 3.0986 | 220 | 0.5945 | 37.2796 |
75
+ | 0.4843 | 3.2394 | 230 | 0.5861 | 48.3942 |
76
+ | 0.4538 | 3.3803 | 240 | 0.5794 | 34.6662 |
77
+ | 0.4741 | 3.5211 | 250 | 0.5737 | 33.8161 |
78
+ | 0.4542 | 3.6620 | 260 | 0.5663 | 41.9710 |
79
+ | 0.4163 | 3.8028 | 270 | 0.5623 | 46.0957 |
80
+ | 0.3496 | 3.9437 | 280 | 0.5605 | 42.2544 |
81
+ | 0.3835 | 4.0845 | 290 | 0.5557 | 41.6562 |
82
+ | 0.3462 | 4.2254 | 300 | 0.5507 | 36.3980 |
83
+ | 0.3133 | 4.3662 | 310 | 0.5452 | 42.5693 |
84
+ | 0.3638 | 4.5070 | 320 | 0.5435 | 35.9572 |
85
+ | 0.3826 | 4.6479 | 330 | 0.5396 | 31.9584 |
86
+ | 0.3581 | 4.7887 | 340 | 0.5361 | 33.7846 |
87
+ | 0.3127 | 4.9296 | 350 | 0.5339 | 37.3426 |
88
+ | 0.2988 | 5.0704 | 360 | 0.5348 | 38.7280 |
89
+ | 0.2807 | 5.2113 | 370 | 0.5344 | 35.5164 |
90
+ | 0.2612 | 5.3521 | 380 | 0.5305 | 34.6662 |
91
+ | 0.2762 | 5.4930 | 390 | 0.5306 | 32.2733 |
92
+ | 0.299 | 5.6338 | 400 | 0.5267 | 36.8703 |
93
+ | 0.2718 | 5.7746 | 410 | 0.5232 | 41.6877 |
94
+ | 0.2618 | 5.9155 | 420 | 0.5208 | 34.0995 |
95
+ | 0.2121 | 6.0563 | 430 | 0.5220 | 28.0542 |
96
+ | 0.1929 | 6.1972 | 440 | 0.5256 | 35.7997 |
97
+ | 0.2504 | 6.3380 | 450 | 0.5296 | 32.8715 |
98
+ | 0.2064 | 6.4789 | 460 | 0.5265 | 35.3904 |
99
+ | 0.2044 | 6.6197 | 470 | 0.5267 | 38.3186 |
100
+ | 0.1844 | 6.7606 | 480 | 0.5231 | 35.1071 |
101
+ | 0.1867 | 6.9014 | 490 | 0.5235 | 31.5806 |
102
+ | 0.1562 | 7.0423 | 500 | 0.5233 | 31.1083 |
103
+
104
+
105
+ ### Framework versions
106
+
107
+ - Transformers 4.40.1
108
+ - Pytorch 2.2.1+cu121
109
+ - Datasets 2.19.1.dev0
110
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:882f27ce9f0525fb3483ebff77d6c2f26784996e92aebdcd136a9b49b6edbdab
3
  size 151060136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f68d9018c77a05b7242228f0e7de1705a6ae31431b69faeea82ee2207feafd0f
3
  size 151060136