zeynepgulhan commited on
Commit
b7f2665
1 Parent(s): 9c7037e

update model card README.md

Browse files
Files changed (2) hide show
  1. README.md +65 -0
  2. training.log +32 -0
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: openai/whisper-medium
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
+ # openai/whisper-medium
16
+
17
+ This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.1711
20
+ - Wer: 10.1446
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-06
40
+ - train_batch_size: 32
41
+ - eval_batch_size: 16
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 200
46
+ - training_steps: 5000
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
53
+ | 0.111 | 0.2 | 1000 | 0.1786 | 11.0063 |
54
+ | 0.0961 | 1.16 | 2000 | 0.1719 | 10.5906 |
55
+ | 0.0732 | 2.12 | 3000 | 0.1743 | 10.3268 |
56
+ | 0.0742 | 3.08 | 4000 | 0.1715 | 10.2262 |
57
+ | 0.0692 | 4.03 | 5000 | 0.1711 | 10.1446 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.26.0.dev0
63
+ - Pytorch 1.13.0+cu117
64
+ - Datasets 2.7.1.dev0
65
+ - Tokenizers 0.13.2
training.log CHANGED
@@ -33391,3 +33391,35 @@ Training completed. Do not forget to share your model on huggingface.co/models =
33391
  [INFO|configuration_utils.py:447] 2022-12-13 05:26:41,273 >> Configuration saved in ./config.json
33392
  [INFO|modeling_utils.py:1671] 2022-12-13 05:26:44,710 >> Model weights saved in ./pytorch_model.bin
33393
  [INFO|feature_extraction_utils.py:368] 2022-12-13 05:26:44,727 >> Feature extractor saved in ./preprocessor_config.json
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33391
  [INFO|configuration_utils.py:447] 2022-12-13 05:26:41,273 >> Configuration saved in ./config.json
33392
  [INFO|modeling_utils.py:1671] 2022-12-13 05:26:44,710 >> Model weights saved in ./pytorch_model.bin
33393
  [INFO|feature_extraction_utils.py:368] 2022-12-13 05:26:44,727 >> Feature extractor saved in ./preprocessor_config.json
33394
+ Several commits (2) will be pushed upstream.
33395
+ {'loss': 0.1087, 'learning_rate': 4.2500000000000003e-08, 'epoch': 3.24}
33396
+ {'loss': 0.0933, 'learning_rate': 3.7291666666666665e-08, 'epoch': 3.24}
33397
+ {'loss': 0.0561, 'learning_rate': 3.208333333333333e-08, 'epoch': 4.0}
33398
+ {'loss': 0.0479, 'learning_rate': 2.6874999999999997e-08, 'epoch': 4.01}
33399
+ {'loss': 0.0686, 'learning_rate': 2.1666666666666665e-08, 'epoch': 4.01}
33400
+ {'loss': 0.0595, 'learning_rate': 1.645833333333333e-08, 'epoch': 4.02}
33401
+ {'loss': 0.0784, 'learning_rate': 1.125e-08, 'epoch': 4.02}
33402
+ {'loss': 0.0767, 'learning_rate': 6.041666666666666e-09, 'epoch': 4.03}
33403
+ {'loss': 0.0692, 'learning_rate': 8.333333333333334e-10, 'epoch': 4.03}
33404
+ {'eval_loss': 0.17108416557312012, 'eval_wer': 10.144624962040693, 'eval_runtime': 5757.3768, 'eval_samples_per_second': 1.762, 'eval_steps_per_second': 0.11, 'epoch': 4.03}
33405
+ {'train_runtime': 57069.8569, 'train_samples_per_second': 2.804, 'train_steps_per_second': 0.088, 'train_loss': 0.12449393980503082, 'epoch': 4.03}
33406
+ 12/13/2022 05:27:04 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.
33407
+ The progress bars may be unreliable.
33408
+ 12/13/2022 05:27:04 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
33409
+
33410
+
33411
+ remote: LFS file scan complete.
33412
+ To https://huggingface.co/zeynepgulhan/whisper-mediaspeech-cv-tr-v2
33413
+ dea3da7..9c7037e main -> main
33414
+
33415
+ 12/13/2022 05:29:17 - WARNING - huggingface_hub.repository - remote: Scanning LFS files for validity, may be slow...
33416
+ remote: LFS file scan complete.
33417
+ To https://huggingface.co/zeynepgulhan/whisper-mediaspeech-cv-tr-v2
33418
+ dea3da7..9c7037e main -> main
33419
+
33420
+
33421
+
33422
+
33423
+
33424
+ [INFO|modelcard.py:449] 2022-12-13 05:29:21,255 >> Dropping the following result as it does not have all the necessary fields:
33425
+ {'task': {'name': 'Automatic Speech Recognition', 'type': 'automatic-speech-recognition'}, 'metrics': [{'name': 'Wer', 'type': 'wer', 'value': 10.144624962040693}]}