Hugging Face's logo

ymoslem
/
whisper-small-ga2en-v1.2

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
fe010a1
•
1 Parent(s): 619c617

End of training

Browse files
Files changed (2) hide show
  1. README.md +79 -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-v1.2
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-v1.2
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
 
@@ -42,6 +71,52 @@ The following hyperparameters were used during training:
42
  - training_steps: 4000
43
  - mixed_precision_training: Native AMP
44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  ### Framework versions
46
 
47
  - Transformers 4.39.3
 
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
19
+ results:
20
+ - task:
21
+ name: Automatic Speech Recognition
22
+ type: automatic-speech-recognition
23
+ dataset:
24
+ name: IWSLT-2023, FLEURS, BiteSize, SpokenWords
25
+ type: ymoslem/IWSLT2023-GA-EN
26
+ metrics:
27
+ - name: Bleu
28
+ type: bleu
29
+ value: 26.85
30
+ - name: Wer
31
+ type: wer
32
+ value: 73.52543899144528
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
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, SpokenWords dataset.
41
+ It achieves the following results on the evaluation set:
42
+ - Loss: 1.6195
43
+ - Bleu: 26.85
44
+ - Chrf: 44.41
45
+ - Wer: 73.5254
46
 
47
  ## Model description
48
 
 
71
  - training_steps: 4000
72
  - mixed_precision_training: Native AMP
73
 
74
+ ### Training results
75
+
76
+ | Training Loss | Epoch | Step | Bleu | Chrf | Validation Loss | Wer |
77
+ |:-------------:|:-----:|:----:|:-----:|:-----:|:---------------:|:--------:|
78
+ | 2.4954 | 0.11 | 100 | 3.7 | 18.03 | 2.1286 | 179.7839 |
79
+ | 2.045 | 0.22 | 200 | 12.65 | 25.53 | 1.8146 | 100.9005 |
80
+ | 1.7928 | 0.32 | 300 | 13.78 | 30.2 | 1.7253 | 101.9811 |
81
+ | 1.6615 | 0.43 | 400 | 15.8 | 31.88 | 1.6834 | 92.5259 |
82
+ | 1.4491 | 0.54 | 500 | 15.61 | 36.27 | 1.5971 | 107.3841 |
83
+ | 1.2074 | 0.65 | 600 | 19.92 | 36.31 | 1.5939 | 84.3314 |
84
+ | 1.2308 | 0.76 | 700 | 20.37 | 38.72 | 1.5234 | 84.8267 |
85
+ | 1.107 | 0.86 | 800 | 21.35 | 37.87 | 1.5460 | 82.8906 |
86
+ | 0.9491 | 0.97 | 900 | 21.06 | 40.74 | 1.5161 | 82.5754 |
87
+ | 0.384 | 1.08 | 1000 | 23.24 | 41.98 | 1.4927 | 82.2152 |
88
+ | 0.362 | 1.19 | 1100 | 23.19 | 42.24 | 1.5567 | 80.2792 |
89
+ | 0.3756 | 1.29 | 1200 | 27.83 | 43.8 | 1.5265 | 69.2481 |
90
+ | 0.3401 | 1.4 | 1300 | 21.79 | 41.66 | 1.5522 | 92.3908 |
91
+ | 0.3346 | 1.51 | 1400 | 24.61 | 42.15 | 1.5085 | 75.4615 |
92
+ | 0.3101 | 1.62 | 1500 | 26.67 | 43.41 | 1.4933 | 70.7789 |
93
+ | 0.3231 | 1.73 | 1600 | 27.95 | 42.82 | 1.4979 | 68.3026 |
94
+ | 0.2665 | 1.83 | 1700 | 28.5 | 43.76 | 1.4977 | 68.1225 |
95
+ | 0.2704 | 1.94 | 1800 | 28.15 | 43.87 | 1.5063 | 68.8429 |
96
+ | 0.0769 | 2.05 | 1900 | 25.76 | 43.22 | 1.5162 | 77.6227 |
97
+ | 0.0597 | 2.16 | 2000 | 25.04 | 43.15 | 1.5216 | 79.0635 |
98
+ | 0.0743 | 2.27 | 2100 | 27.85 | 44.43 | 1.5313 | 68.3926 |
99
+ | 0.0878 | 2.37 | 2200 | 27.54 | 43.96 | 1.5495 | 68.3476 |
100
+ | 0.0712 | 2.48 | 2300 | 28.28 | 44.39 | 1.5355 | 65.8712 |
101
+ | 0.0789 | 2.59 | 2400 | 28.64 | 44.75 | 1.5277 | 65.7812 |
102
+ | 0.073 | 2.7 | 2500 | 29.09 | 44.65 | 1.5327 | 65.7812 |
103
+ | 0.073 | 2.8 | 2600 | 25.26 | 43.44 | 1.5304 | 78.2981 |
104
+ | 0.0697 | 2.91 | 2700 | 25.71 | 43.02 | 1.5460 | 78.4782 |
105
+ | 0.0398 | 3.02 | 2800 | 28.26 | 44.71 | 1.5580 | 72.8501 |
106
+ | 0.0302 | 3.13 | 2900 | 30.25 | 45.46 | 1.5688 | 66.1414 |
107
+ | 0.0424 | 3.24 | 3000 | 29.88 | 45.21 | 1.5693 | 66.0964 |
108
+ | 0.0397 | 3.34 | 3100 | 30.01 | 45.85 | 1.5934 | 65.6911 |
109
+ | 0.0346 | 3.45 | 3200 | 30.2 | 45.8 | 1.5818 | 65.8262 |
110
+ | 0.032 | 3.56 | 3300 | 29.81 | 46.5 | 1.5823 | 66.7267 |
111
+ | 0.0348 | 3.67 | 3400 | 30.77 | 46.43 | 1.5752 | 64.6556 |
112
+ | 0.0277 | 3.78 | 3500 | 30.3 | 46.02 | 1.5791 | 64.6105 |
113
+ | 0.0364 | 3.88 | 3600 | 1.5895| 29.92 | 45.38 | 65.0608 |
114
+ | 0.0398 | 3.99 | 3700 | 1.6167| 27.79 | 44.59 | 68.2575 |
115
+ | 0.0152 | 4.1 | 3800 | 1.6241| 28.42 | 44.83 | 67.5822 |
116
+ | 0.0201 | 4.21 | 3900 | 1.6243| 29.02 | 45.11 | 67.4921 |
117
+ | 0.0168 | 4.31 | 4000 | 1.6195| 26.85 | 44.41 | 73.5254 |
118
+
119
+
120
  ### Framework versions
121
 
122
  - Transformers 4.39.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6141e4c53ce1bfc16c89e34fa4880e33929fbbac652ad5c0f97fc4ade5bec387
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c71d67da1289c935526cd5f06d220a9692d0abe9d7f8375fce84bff9406739
3
  size 966995080