emilios commited on
Commit
7f6c586
1 Parent(s): 8e1480f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -13
README.md CHANGED
@@ -3,30 +3,39 @@ language:
3
  - el
4
  license: apache-2.0
5
  tags:
6
- - hf-asr-leaderboard, whisper-medium, mozilla-foundation/common_voice_11_0, greek,
7
- whisper-event
8
  - generated_from_trainer
9
  datasets:
10
  - mozilla-foundation/common_voice_11_0
 
 
11
  model-index:
12
- - name: Whisper Medium El Greco Greek
13
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # Whisper Medium El Greco Greek
20
 
21
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 11.0 dataset.
22
  It achieves the following results on the evaluation set:
23
- - epoch : 12.44
24
- - eval_loss : 0.3801
25
- - eval_runtime : 0:18:30.86
26
- - eval_samples_per_second : 1.527
27
- - eval_steps_per_second : 0.095
28
- - eval_wer : 11.1999
29
- - step: 5000
30
 
31
  ## Model description
32
 
@@ -52,9 +61,22 @@ The following hyperparameters were used during training:
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
  - lr_scheduler_warmup_steps: 500
55
- - training_steps: 5000
56
  - mixed_precision_training: Native AMP
57
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  ### Framework versions
59
 
60
  - Transformers 4.26.0.dev0
 
3
  - el
4
  license: apache-2.0
5
  tags:
6
+ - hf-asr-leaderboard
 
7
  - generated_from_trainer
8
  datasets:
9
  - mozilla-foundation/common_voice_11_0
10
+ metrics:
11
+ - wer
12
  model-index:
13
+ - name: Whisper Medium El Greco
14
+ results:
15
+ - task:
16
+ name: Automatic Speech Recognition
17
+ type: automatic-speech-recognition
18
+ dataset:
19
+ name: Common Voice 11.0
20
+ type: mozilla-foundation/common_voice_11_0
21
+ config: el
22
+ split: test
23
+ args: el
24
+ metrics:
25
+ - name: Wer
26
+ type: wer
27
+ value: 10.74479940564636
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
  should probably proofread and complete it, then remove this comment. -->
32
 
33
+ # Whisper Medium El Greco
34
 
35
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 11.0 dataset.
36
  It achieves the following results on the evaluation set:
37
+ - Loss: 0.4245
38
+ - Wer: 10.7448
 
 
 
 
 
39
 
40
  ## Model description
41
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
+ - training_steps: 7000
65
  - mixed_precision_training: Native AMP
66
 
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
70
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
71
+ | 0.0039 | 2.49 | 1000 | 0.3787 | 12.4443 |
72
+ | 0.0017 | 4.98 | 2000 | 0.4010 | 12.2864 |
73
+ | 0.0006 | 7.46 | 3000 | 0.4108 | 11.6921 |
74
+ | 0.0004 | 9.95 | 4000 | 0.4221 | 11.5806 |
75
+ | 0.0005 | 12.44 | 5000 | 0.4222 | 11.4134 |
76
+ | 0.0006 | 4.03 | 6000 | 0.4230 | 10.9212 |
77
+ | 0.0006 | 9.03 | 7000 | 0.4245 | 10.7448 |
78
+
79
+
80
  ### Framework versions
81
 
82
  - Transformers 4.26.0.dev0