Hugging Face's logo

khaingsmon
/
whisper4

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
khaingsmon commited on
Commit
fee0113
•
1 Parent(s): 8a758c6

Model save

Browse files
Files changed (2) hide show
  1. README.md +90 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: whisper4
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
+ # whisper4
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: 0.5409
21
+ - Wer: 28.2719
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: 0.0001
41
+ - train_batch_size: 128
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: 300
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:------:|:----:|:---------------:|:-------:|
53
+ | 3.8231 | 0.2778 | 10 | 3.7088 | 76.9377 |
54
+ | 3.1925 | 0.5556 | 20 | 2.9439 | 65.5654 |
55
+ | 2.1383 | 0.8333 | 30 | 1.7221 | 61.5311 |
56
+ | 1.0671 | 1.1111 | 40 | 0.8320 | 50.6989 |
57
+ | 0.6947 | 1.3889 | 50 | 0.6587 | 41.0102 |
58
+ | 0.6263 | 1.6667 | 60 | 0.5874 | 29.7967 |
59
+ | 0.5827 | 1.9444 | 70 | 0.5402 | 27.3825 |
60
+ | 0.4222 | 2.2222 | 80 | 0.5154 | 32.0521 |
61
+ | 0.4065 | 2.5 | 90 | 0.4997 | 25.6989 |
62
+ | 0.3959 | 2.7778 | 100 | 0.4804 | 23.8247 |
63
+ | 0.3081 | 3.0556 | 110 | 0.4670 | 24.8412 |
64
+ | 0.2497 | 3.3333 | 120 | 0.4687 | 23.2846 |
65
+ | 0.2535 | 3.6111 | 130 | 0.4594 | 23.0940 |
66
+ | 0.2428 | 3.8889 | 140 | 0.4545 | 23.5070 |
67
+ | 0.1627 | 4.1667 | 150 | 0.4651 | 24.4917 |
68
+ | 0.1224 | 4.4444 | 160 | 0.4686 | 23.6976 |
69
+ | 0.1326 | 4.7222 | 170 | 0.4653 | 23.6976 |
70
+ | 0.1334 | 5.0 | 180 | 0.4741 | 24.7459 |
71
+ | 0.0659 | 5.2778 | 190 | 0.4792 | 24.6823 |
72
+ | 0.0639 | 5.5556 | 200 | 0.4760 | 33.3863 |
73
+ | 0.0667 | 5.8333 | 210 | 0.4820 | 25.4765 |
74
+ | 0.042 | 6.1111 | 220 | 0.4933 | 29.4155 |
75
+ | 0.0325 | 6.3889 | 230 | 0.5066 | 29.9873 |
76
+ | 0.0333 | 6.6667 | 240 | 0.5126 | 26.0801 |
77
+ | 0.0333 | 6.9444 | 250 | 0.5073 | 24.6188 |
78
+ | 0.0187 | 7.2222 | 260 | 0.5129 | 27.3507 |
79
+ | 0.0214 | 7.5 | 270 | 0.5209 | 28.2084 |
80
+ | 0.0187 | 7.7778 | 280 | 0.5213 | 29.3202 |
81
+ | 0.0312 | 8.0556 | 290 | 0.5274 | 34.6569 |
82
+ | 0.0172 | 8.3333 | 300 | 0.5409 | 28.2719 |
83
+
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 4.40.1
88
+ - Pytorch 2.2.1+cu121
89
+ - Datasets 2.19.1.dev0
90
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8be1658abaf8e08ce37a6c740f392d9bd847bc6128227416a69a87d44c78f2ae
3
  size 151060136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d170fefd0ce30ca4f0cd0324c7a7849c7fc1dc71ceab4124d25d79185832b4
3
  size 151060136