Hugging Face's logo

drmeeseeks
/
whisper-medium-v2-amet

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
whisper-event
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
drmeeseeks commited on
Commit
745dd79
•
1 Parent(s): 15b3f5f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +105 -0
README.md ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - fleurs
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: whisper-medium-v2-amet
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: fleurs
17
+ type: fleurs
18
+ config: am_et
19
+ split: validation
20
+ args: am_et
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 154.41176470588235
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # whisper-medium-v2-amet
31
+
32
+ This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the fleurs dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 7.8670
35
+ - Wer: 154.4118
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 1e-05
55
+ - train_batch_size: 32
56
+ - eval_batch_size: 16
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - lr_scheduler_warmup_steps: 500
61
+ - training_steps: 3000
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
67
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
68
+ | 0.0194 | 100.0 | 100 | 3.8540 | 147.9947 |
69
+ | 0.0001 | 200.0 | 200 | 4.1479 | 148.1283 |
70
+ | 0.0001 | 300.0 | 300 | 4.1840 | 150.5348 |
71
+ | 0.0001 | 400.0 | 400 | 4.3339 | 177.9412 |
72
+ | 0.0 | 500.0 | 500 | 4.5831 | 151.0695 |
73
+ | 0.0 | 600.0 | 600 | 4.9317 | 164.0374 |
74
+ | 0.0 | 700.0 | 700 | 5.3031 | 141.0428 |
75
+ | 0.0 | 800.0 | 800 | 5.6584 | 122.3262 |
76
+ | 0.0 | 900.0 | 900 | 5.9711 | 157.4866 |
77
+ | 0.0 | 1000.0 | 1000 | 6.2465 | 141.1765 |
78
+ | 0.0 | 1100.0 | 1100 | 6.4832 | 169.6524 |
79
+ | 0.0 | 1200.0 | 1200 | 6.6890 | 155.0802 |
80
+ | 0.0 | 1300.0 | 1300 | 6.8679 | 159.7594 |
81
+ | 0.0 | 1400.0 | 1400 | 7.0250 | 155.0802 |
82
+ | 0.0 | 1500.0 | 1500 | 7.1615 | 146.2567 |
83
+ | 0.0 | 1600.0 | 1600 | 7.2877 | 143.0481 |
84
+ | 0.0 | 1700.0 | 1700 | 7.3987 | 148.5294 |
85
+ | 0.0 | 1800.0 | 1800 | 7.5010 | 142.5134 |
86
+ | 0.0 | 1900.0 | 1900 | 7.5849 | 136.7647 |
87
+ | 0.0 | 2000.0 | 2000 | 7.6689 | 148.2620 |
88
+ | 0.0 | 2100.0 | 2100 | 7.6955 | 165.3743 |
89
+ | 0.0 | 2200.0 | 2200 | 7.7247 | 162.9679 |
90
+ | 0.0 | 2300.0 | 2300 | 7.7557 | 161.6310 |
91
+ | 0.0 | 2400.0 | 2400 | 7.7842 | 162.2995 |
92
+ | 0.0 | 2500.0 | 2500 | 7.8074 | 150.9358 |
93
+ | 0.0 | 2600.0 | 2600 | 7.8287 | 154.8128 |
94
+ | 0.0 | 2700.0 | 2700 | 7.8434 | 155.4813 |
95
+ | 0.0 | 2800.0 | 2800 | 7.8567 | 154.4118 |
96
+ | 0.0 | 2900.0 | 2900 | 7.8635 | 154.4118 |
97
+ | 0.0 | 3000.0 | 3000 | 7.8670 | 154.4118 |
98
+
99
+
100
+ ### Framework versions
101
+
102
+ - Transformers 4.26.0.dev0
103
+ - Pytorch 1.13.1+cu117
104
+ - Datasets 2.8.1.dev0
105
+ - Tokenizers 0.13.2