Hugging Face's logo

ymoslem
/
whisper-small-ga2en-v1.5-r

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Irish
English
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ymoslem commited on
Commit
87ab808
•
1 Parent(s): ca02cdb

End of training

Browse files
Files changed (2) hide show
  1. README.md +69 -4
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,19 +1,48 @@
1
  ---
 
 
 
2
  license: apache-2.0
3
  base_model: openai/whisper-small
4
  tags:
5
  - generated_from_trainer
 
 
 
 
 
 
 
 
6
  model-index:
7
- - name: whisper-small-ga2en-v1.5-r
8
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
- # whisper-small-ga2en-v1.5-r
15
 
16
- This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
 
 
 
 
 
17
 
18
  ## Model description
19
 
@@ -41,6 +70,42 @@ The following hyperparameters were used during training:
41
  - training_steps: 3000
42
  - mixed_precision_training: Native AMP
43
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
  ### Framework versions
45
 
46
  - Transformers 4.41.1
 
1
  ---
2
+ language:
3
+ - ga
4
+ - en
5
  license: apache-2.0
6
  base_model: openai/whisper-small
7
  tags:
8
  - generated_from_trainer
9
+ datasets:
10
+ - ymoslem/IWSLT2023-GA-EN
11
+ - ymoslem/FLEURS-GA-EN
12
+ - ymoslem/BitesizeIrish-GA-EN
13
+ - ymoslem/SpokenWords-GA-EN-MTed
14
+ metrics:
15
+ - bleu
16
+ - wer
17
  model-index:
18
+ - name: Whisper Small GA-EN Speech Translation + VAD
19
+ results:
20
+ - task:
21
+ name: Automatic Speech Recognition
22
+ type: automatic-speech-recognition
23
+ dataset:
24
+ name: IWSLT-2023, FLEURS, BiteSize, and SpokenWords
25
+ type: ymoslem/IWSLT2023-GA-EN
26
+ metrics:
27
+ - name: Bleu
28
+ type: bleu
29
+ value: 28.22
30
+ - name: Wer
31
+ type: wer
32
+ value: 68.52769022962629
33
  ---
34
 
35
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
36
  should probably proofread and complete it, then remove this comment. -->
37
 
38
+ # Whisper Small GA-EN Speech Translation + VAD
39
 
40
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the IWSLT-2023, FLEURS, BiteSize, and SpokenWords dataset.
41
+ It achieves the following results on the evaluation set:
42
+ - Loss: 1.7352
43
+ - Bleu: 28.22
44
+ - Chrf: 44.19
45
+ - Wer: 68.5277
46
 
47
  ## Model description
48
 
 
70
  - training_steps: 3000
71
  - mixed_precision_training: Native AMP
72
 
73
+ ### Training results
74
+
75
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf | Wer |
76
+ |:-------------:|:------:|:----:|:---------------:|:-----:|:-----:|:--------:|
77
+ | 1.9529 | 0.2188 | 100 | 1.7388 | 12.76 | 29.03 | 97.1184 |
78
+ | 1.5762 | 0.4376 | 200 | 1.5362 | 15.3 | 33.31 | 98.4241 |
79
+ | 1.2624 | 0.6565 | 300 | 1.4346 | 17.94 | 37.2 | 101.4408 |
80
+ | 1.0367 | 0.8753 | 400 | 1.4502 | 21.52 | 39.13 | 85.4120 |
81
+ | 0.4677 | 1.0941 | 500 | 1.4693 | 23.26 | 40.49 | 78.4331 |
82
+ | 0.4284 | 1.3129 | 600 | 1.5163 | 21.31 | 41.41 | 86.0873 |
83
+ | 0.4026 | 1.5317 | 700 | 1.4999 | 24.11 | 40.59 | 79.3787 |
84
+ | 0.4132 | 1.7505 | 800 | 1.5134 | 27.77 | 43.01 | 70.1936 |
85
+ | 0.3701 | 1.9694 | 900 | 1.5368 | 27.74 | 42.61 | 66.0964 |
86
+ | 0.1337 | 2.1882 | 1000 | 1.5692 | 27.96 | 43.77 | 64.9257 |
87
+ | 0.143 | 2.4070 | 1100 | 1.5516 | 26.06 | 42.12 | 71.3192 |
88
+ | 0.144 | 2.6258 | 1200 | 1.5839 | 27.55 | 43.19 | 69.7434 |
89
+ | 0.1372 | 2.8446 | 1300 | 1.5510 | 27.93 | 43.07 | 66.1414 |
90
+ | 0.0573 | 3.0635 | 1400 | 1.6567 | 26.34 | 41.69 | 72.3998 |
91
+ | 0.0554 | 3.2823 | 1500 | 1.6511 | 27.98 | 42.66 | 68.5277 |
92
+ | 0.0534 | 3.5011 | 1600 | 1.6732 | 28.29 | 43.2 | 67.1319 |
93
+ | 0.0588 | 3.7199 | 1700 | 1.6687 | 27.0 | 43.31 | 70.7789 |
94
+ | 0.0486 | 3.9387 | 1800 | 1.6759 | 28.02 | 43.97 | 66.3665 |
95
+ | 0.0224 | 4.1575 | 1900 | 1.7597 | 26.86 | 41.81 | 70.5538 |
96
+ | 0.0264 | 4.3764 | 2000 | 1.7113 | 27.58 | 43.38 | 70.4638 |
97
+ | 0.0233 | 4.5952 | 2100 | 1.7013 | 27.83 | 42.87 | 68.2575 |
98
+ | 0.0192 | 4.8140 | 2200 | 1.7351 | 25.39 | 42.09 | 78.0279 |
99
+ | 0.0149 | 5.0328 | 2300 | 1.7350 | 27.62 | 43.99 | 70.5538 |
100
+ | 0.0086 | 5.2516 | 2400 | 1.7331 | 29.37 | 45.08 | 68.5277 |
101
+ | 0.006 | 5.4705 | 2500 | 1.7145 | 29.04 | 44.19 | 66.9968 |
102
+ | 0.0064 | 5.6893 | 2600 | 1.7322 | 28.27 | 43.6 | 70.2386 |
103
+ | 0.0053 | 5.9081 | 2700 | 1.7239 | 27.86 | 43.78 | 69.6083 |
104
+ | 0.0021 | 6.1269 | 2800 | 1.7288 | 28.14 | 44.12 | 68.5727 |
105
+ | 0.0016 | 6.3457 | 2900 | 1.7375 | 28.26 | 44.14 | 68.7078 |
106
+ | 0.0023 | 6.5646 | 3000 | 1.7352 | 28.22 | 44.19 | 68.5277 |
107
+
108
+
109
  ### Framework versions
110
 
111
  - Transformers 4.41.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f31b3d9b7b8ef61bff576cb6b1e4400c28bff95c0eaf99e22c56f1675cbed16
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:922cf40a008d7aa2bf13e82b0eecfa561712b7f2470aff0d3d0b054cc499518b
3
  size 966995080