Hugging Face's logo

jlvdoorn
/
whisper-large-v2-atco2-asr

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
Jan van Doorn commited on
Commit
899903d
•
1 Parent(s): 1604ea9

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +88 -0
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: whisper-large-v2-atco2-asr
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # whisper-large-v2-atco2-asr
16
+
17
+ This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.7915
20
+ - Wer: 18.7722
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 1e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 100
47
+ - training_steps: 2800
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
53
+ | 0.1333 | 3.57 | 100 | 0.5298 | 21.8861 |
54
+ | 0.0338 | 7.14 | 200 | 0.5430 | 18.8167 |
55
+ | 0.0132 | 10.71 | 300 | 0.5830 | 17.9270 |
56
+ | 0.0067 | 14.29 | 400 | 0.6011 | 17.6157 |
57
+ | 0.0009 | 17.86 | 500 | 0.6582 | 18.8167 |
58
+ | 0.0004 | 21.43 | 600 | 0.6743 | 18.7722 |
59
+ | 0.0003 | 25.0 | 700 | 0.6919 | 18.4609 |
60
+ | 0.0004 | 28.57 | 800 | 0.6943 | 26.6459 |
61
+ | 0.0004 | 32.14 | 900 | 0.7090 | 18.5053 |
62
+ | 0.0002 | 35.71 | 1000 | 0.7212 | 18.8167 |
63
+ | 0.0001 | 39.29 | 1100 | 0.7305 | 18.8612 |
64
+ | 0.0001 | 42.86 | 1200 | 0.7383 | 18.6388 |
65
+ | 0.0001 | 46.43 | 1300 | 0.7451 | 18.5498 |
66
+ | 0.0001 | 50.0 | 1400 | 0.7515 | 18.5498 |
67
+ | 0.0001 | 53.57 | 1500 | 0.7573 | 18.5498 |
68
+ | 0.0001 | 57.14 | 1600 | 0.7622 | 18.5943 |
69
+ | 0.0001 | 60.71 | 1700 | 0.7666 | 18.5943 |
70
+ | 0.0001 | 64.29 | 1800 | 0.7705 | 18.5498 |
71
+ | 0.0001 | 67.86 | 1900 | 0.7744 | 18.6833 |
72
+ | 0.0001 | 71.43 | 2000 | 0.7778 | 18.6833 |
73
+ | 0.0001 | 75.0 | 2100 | 0.7808 | 18.7278 |
74
+ | 0.0001 | 78.57 | 2200 | 0.7837 | 18.6833 |
75
+ | 0.0001 | 82.14 | 2300 | 0.7856 | 18.6388 |
76
+ | 0.0001 | 85.71 | 2400 | 0.7881 | 18.6833 |
77
+ | 0.0001 | 89.29 | 2500 | 0.7896 | 18.6388 |
78
+ | 0.0001 | 92.86 | 2600 | 0.7905 | 18.7278 |
79
+ | 0.0001 | 96.43 | 2700 | 0.7915 | 18.8167 |
80
+ | 0.0001 | 100.0 | 2800 | 0.7915 | 18.7722 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.30.0.dev0
86
+ - Pytorch 2.0.1+cu117
87
+ - Datasets 2.12.0
88
+ - Tokenizers 0.13.3