nefasto commited on
Commit
5c5cbe7
1 Parent(s): 950168c

update model card README.md

Browse files
Files changed (2) hide show
  1. README.md +81 -0
  2. log +17 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice_11_0
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: openai/whisper-small
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: common_voice_11_0
17
+ type: common_voice_11_0
18
+ config: it
19
+ split: test
20
+ args: it
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 12.502657877950243
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
+ # openai/whisper-small
31
+
32
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_11_0 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.2698
35
+ - Wer: 12.5027
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: 8e-06
55
+ - train_batch_size: 64
56
+ - eval_batch_size: 32
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: 6000
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
67
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
68
+ | 0.2737 | 2.01 | 1000 | 0.2728 | 13.4097 |
69
+ | 0.1536 | 4.02 | 2000 | 0.2611 | 12.9897 |
70
+ | 0.0905 | 6.03 | 3000 | 0.2686 | 12.9273 |
71
+ | 0.1301 | 8.04 | 4000 | 0.2534 | 12.3040 |
72
+ | 0.096 | 10.05 | 5000 | 0.2727 | 12.6130 |
73
+ | 0.0604 | 12.06 | 6000 | 0.2698 | 12.5027 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.26.0.dev0
79
+ - Pytorch 1.13.0+cu117
80
+ - Datasets 2.7.1.dev0
81
+ - Tokenizers 0.13.2
log CHANGED
@@ -33745,3 +33745,20 @@ Training completed. Do not forget to share your model on huggingface.co/models =
33745
  [INFO|configuration_utils.py:447] 2022-12-15 17:20:48,112 >> Configuration saved in ./config.json
33746
  [INFO|modeling_utils.py:1680] 2022-12-15 17:20:49,374 >> Model weights saved in ./pytorch_model.bin
33747
  [INFO|feature_extraction_utils.py:368] 2022-12-15 17:20:49,390 >> Feature extractor saved in ./preprocessor_config.json
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33745
  [INFO|configuration_utils.py:447] 2022-12-15 17:20:48,112 >> Configuration saved in ./config.json
33746
  [INFO|modeling_utils.py:1680] 2022-12-15 17:20:49,374 >> Model weights saved in ./pytorch_model.bin
33747
  [INFO|feature_extraction_utils.py:368] 2022-12-15 17:20:49,390 >> Feature extractor saved in ./preprocessor_config.json
33748
+ Several commits (2) will be pushed upstream.
33749
+ {'eval_loss': 0.26977524161338806, 'eval_wer': 12.502657877950243, 'eval_runtime': 5061.9846, 'eval_samples_per_second': 2.964, 'eval_steps_per_second': 0.093, 'epoch': 12.06}
33750
+ {'train_runtime': 84190.0984, 'train_samples_per_second': 4.561, 'train_steps_per_second': 0.071, 'train_loss': 0.1507516227165858, 'epoch': 12.06}
33751
+ 12/15/2022 17:21:21 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.
33752
+ The progress bars may be unreliable.
33753
+ 12/15/2022 17:21:21 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
33754
+
33755
+ remote: LFS file scan complete.
33756
+ To https://huggingface.co/nefasto/whisper-small-it
33757
+ 1875cbe..950168c main -> main
33758
+
33759
+ 12/15/2022 17:21:26 - WARNING - huggingface_hub.repository - remote: Scanning LFS files for validity, may be slow...
33760
+ remote: LFS file scan complete.
33761
+ To https://huggingface.co/nefasto/whisper-small-it
33762
+ 1875cbe..950168c main -> main
33763
+
33764
+