Hugging Face's logo

drmeeseeks
/
whisper-small-amet

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
whisper-event
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
drmeeseeks commited on
Commit
f4a81be
·
1 Parent(s): 6d172a2

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -30
README.md CHANGED
@@ -1,39 +1,38 @@
1
  ---
2
  license: apache-2.0
3
  tags:
4
- - whisper-event
5
  - generated_from_trainer
6
  datasets:
7
- - google/fleurs
8
  metrics:
9
  - wer
10
  model-index:
11
- - name: Whisper Small Amharic FLEURS
12
  results:
13
  - task:
14
  name: Automatic Speech Recognition
15
  type: automatic-speech-recognition
16
  dataset:
17
- name: google/fleurs am_et
18
- type: google/fleurs
19
  config: am_et
20
  split: validation
21
  args: am_et
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 100.0
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
  should probably proofread and complete it, then remove this comment. -->
30
 
31
- # Whisper Small Amharic FLEURS
32
 
33
- This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the google/fleurs am_et dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 6.8012
36
- - Wer: 100.0
37
 
38
  ## Model description
39
 
@@ -66,26 +65,26 @@ The following hyperparameters were used during training:
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Wer |
68
  |:-------------:|:------:|:----:|:---------------:|:--------:|
69
- | 0.9013 | 100.0 | 100 | 2.7051 | 276.0 |
70
- | 0.0002 | 200.0 | 200 | 3.7415 | 334.6667 |
71
- | 0.0001 | 300.0 | 300 | 3.8402 | 117.3333 |
72
- | 0.0001 | 400.0 | 400 | 3.8931 | 340.0 |
73
- | 0.0001 | 500.0 | 500 | 4.0671 | 397.3333 |
74
- | 0.0001 | 600.0 | 600 | 4.2844 | 137.3333 |
75
- | 0.0 | 700.0 | 700 | 4.4697 | 289.3333 |
76
- | 0.0 | 800.0 | 800 | 4.6278 | 449.3333 |
77
- | 0.0 | 900.0 | 900 | 4.7794 | 678.6667 |
78
- | 0.0405 | 1000.0 | 1000 | 4.6769 | 261.3333 |
79
- | 0.0002 | 1100.0 | 1100 | 5.4995 | 100.0 |
80
- | 0.0002 | 1200.0 | 1200 | 6.0033 | 100.0 |
81
- | 0.0002 | 1300.0 | 1300 | 6.2884 | 100.0 |
82
- | 0.0002 | 1400.0 | 1400 | 6.4744 | 100.0 |
83
- | 0.0002 | 1500.0 | 1500 | 6.5964 | 100.0 |
84
- | 0.0001 | 1600.0 | 1600 | 6.6792 | 100.0 |
85
- | 0.0001 | 1700.0 | 1700 | 6.7370 | 100.0 |
86
- | 0.0001 | 1800.0 | 1800 | 6.7735 | 100.0 |
87
- | 0.0001 | 1900.0 | 1900 | 6.7958 | 100.0 |
88
- | 0.0001 | 2000.0 | 2000 | 6.8012 | 100.0 |
89
 
90
 
91
  ### Framework versions
 
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-small-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: 103.08219178082192
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-small-amet
31
 
32
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the fleurs dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 6.8839
35
+ - Wer: 103.0822
36
 
37
  ## Model description
38
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:------:|:----:|:---------------:|:--------:|
68
+ | 0.9013 | 100.0 | 100 | 2.7090 | 171.5753 |
69
+ | 0.0002 | 200.0 | 200 | 3.7303 | 298.6301 |
70
+ | 0.0001 | 300.0 | 300 | 3.8287 | 239.3836 |
71
+ | 0.0001 | 400.0 | 400 | 3.8877 | 234.9315 |
72
+ | 0.0001 | 500.0 | 500 | 4.0561 | 316.4384 |
73
+ | 0.0001 | 600.0 | 600 | 4.2706 | 189.0411 |
74
+ | 0.0 | 700.0 | 700 | 4.4524 | 229.4521 |
75
+ | 0.0 | 800.0 | 800 | 4.6250 | 308.5616 |
76
+ | 0.0 | 900.0 | 900 | 4.7844 | 429.4521 |
77
+ | 0.0405 | 1000.0 | 1000 | 4.6182 | 206.8493 |
78
+ | 0.0002 | 1100.0 | 1100 | 5.5423 | 159.9315 |
79
+ | 0.0002 | 1200.0 | 1200 | 6.0517 | 151.7123 |
80
+ | 0.0002 | 1300.0 | 1300 | 6.3493 | 154.7945 |
81
+ | 0.0002 | 1400.0 | 1400 | 6.5431 | 138.6986 |
82
+ | 0.0002 | 1500.0 | 1500 | 6.6699 | 158.5616 |
83
+ | 0.0001 | 1600.0 | 1600 | 6.7591 | 160.2740 |
84
+ | 0.0001 | 1700.0 | 1700 | 6.8209 | 103.0822 |
85
+ | 0.0001 | 1800.0 | 1800 | 6.8562 | 103.0822 |
86
+ | 0.0001 | 1900.0 | 1900 | 6.8758 | 103.0822 |
87
+ | 0.0001 | 2000.0 | 2000 | 6.8839 | 103.0822 |
88
 
89
 
90
  ### Framework versions