ymoslem commited on
Commit
a98035b
1 Parent(s): a3e91f3

End of training

Browse files
Files changed (2) hide show
  1. README.md +73 -4
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,19 +1,52 @@
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-v4
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-v4
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 +75,42 @@ The following hyperparameters were used during training:
42
  - training_steps: 3000
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
+ - ymoslem/Tatoeba-Speech-Irish
15
+ - ymoslem/Wikimedia-Speech-Irish
16
+ metrics:
17
+ - bleu
18
+ - wer
19
  model-index:
20
+ - name: Whisper Small GA-EN Speech Translation
21
+ results:
22
+ - task:
23
+ name: Automatic Speech Recognition
24
+ type: automatic-speech-recognition
25
+ dataset:
26
+ name: IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia as
27
+ well as a copy of the dataset with noise reduction and normalization (for
28
+ both train and test)
29
+ type: ymoslem/IWSLT2023-GA-EN
30
+ metrics:
31
+ - name: Bleu
32
+ type: bleu
33
+ value: 30.66
34
+ - name: Wer
35
+ type: wer
36
+ value: 65.46600630346691
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
40
  should probably proofread and complete it, then remove this comment. -->
41
 
42
+ # Whisper Small GA-EN Speech Translation
43
 
44
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia as well as a copy of the dataset with noise reduction and normalization (for both train and test) dataset.
45
+ It achieves the following results on the evaluation set:
46
+ - Loss: 1.3339
47
+ - Bleu: 30.66
48
+ - Chrf: 46.99
49
+ - Wer: 65.4660
50
 
51
  ## Model description
52
 
 
75
  - training_steps: 3000
76
  - mixed_precision_training: Native AMP
77
 
78
+ ### Training results
79
+
80
+ | Training Loss | Epoch | Step | Bleu | Chrf | Validation Loss | Wer |
81
+ |:-------------:|:-----:|:----:|:-----:|:-----:|:---------------:|:--------:|
82
+ | 1.41 | 0.07 | 100 | 9.78 | 25.23 | 1.8782 | 96.3980 |
83
+ | 1.2436 | 0.13 | 200 | 10.23 | 28.66 | 1.8301 | 125.9343 |
84
+ | 1.593 | 0.2 | 300 | 9.53 | 30.7 | 1.7066 | 137.1454 |
85
+ | 1.9589 | 0.26 | 400 | 12.08 | 32.94 | 1.5629 | 109.3652 |
86
+ | 1.8174 | 0.33 | 500 | 13.73 | 34.5 | 1.5154 | 123.5930 |
87
+ | 1.6775 | 0.39 | 600 | 15.8 | 35.68 | 1.5220 | 102.2062 |
88
+ | 1.7074 | 0.46 | 700 | 16.62 | 37.96 | 1.4570 | 100.5853 |
89
+ | 1.5793 | 0.53 | 800 | 24.5 | 39.91 | 1.4265 | 71.3643 |
90
+ | 1.3708 | 0.59 | 900 | 24.35 | 42.26 | 1.3845 | 73.7956 |
91
+ | 1.3217 | 0.66 | 1000 | 19.34 | 41.3 | 1.3662 | 87.7533 |
92
+ | 1.2572 | 0.72 | 1100 | 21.59 | 41.35 | 1.3529 | 88.4286 |
93
+ | 1.1447 | 0.79 | 1200 | 28.39 | 44.99 | 1.3228 | 65.9163 |
94
+ | 1.1544 | 0.85 | 1300 | 23.69 | 43.07 | 1.2972 | 80.1891 |
95
+ | 1.0291 | 0.92 | 1400 | 29.36 | 45.45 | 1.2828 | 70.9590 |
96
+ | 0.9394 | 0.98 | 1500 | 26.44 | 44.0 | 1.2812 | 74.1558 |
97
+ | 0.3764 | 1.05 | 1600 | 26.95 | 44.82 | 1.3248 | 73.8406 |
98
+ | 0.3338 | 1.12 | 1700 | 26.5 | 44.96 | 1.3212 | 77.3976 |
99
+ | 0.3148 | 1.18 | 1800 | 29.57 | 46.31 | 1.3188 | 66.7267 |
100
+ | 0.3206 | 1.25 | 1900 | 30.87 | 47.21 | 1.3050 | 64.4755 |
101
+ | 0.3069 | 1.31 | 2000 | 30.15 | 46.19 | 1.3053 | 65.6911 |
102
+ | 0.3342 | 1.38 | 2100 | 1.3506| 24.14 | 44.12 | 77.2625 |
103
+ | 0.3125 | 1.44 | 2200 | 1.3369| 30.21 | 46.08 | 63.9802 |
104
+ | 0.319 | 1.51 | 2300 | 1.3601| 27.71 | 45.45 | 69.9235 |
105
+ | 0.3067 | 1.58 | 2400 | 1.3473| 26.92 | 45.73 | 69.3381 |
106
+ | 0.2621 | 1.64 | 2500 | 1.3354| 28.36 | 46.14 | 66.9068 |
107
+ | 0.2709 | 1.71 | 2600 | 1.3339| 28.75 | 45.47 | 65.2859 |
108
+ | 0.2644 | 1.77 | 2700 | 1.3100| 28.84 | 47.35 | 65.8262 |
109
+ | 0.2511 | 1.84 | 2800 | 1.3261| 29.41 | 47.31 | 69.4732 |
110
+ | 0.2232 | 1.9 | 2900 | 1.3382| 30.79 | 46.63 | 64.1153 |
111
+ | 0.236 | 1.97 | 3000 | 1.3339| 30.66 | 46.99 | 65.4660 |
112
+
113
+
114
  ### Framework versions
115
 
116
  - Transformers 4.39.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a364719b2bec5df48b3ab907264945c94cc688d87fadd40709383e459ba9edae
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f378e337ad5545e49bc4e79c6f54fe6a7a0f6dc77f540324d2c72a30d449fe0f
3
  size 966995080