Hugging Face's logo

ymoslem
/
whisper-medium-ga2en-v6.3.0-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
aef0dd7
·
verified ·
1 Parent(s): f17a1c9

End of training

Browse files
Files changed (1) hide show
  1. README.md +83 -5
README.md CHANGED
@@ -1,19 +1,51 @@
1
  ---
 
 
 
2
  license: apache-2.0
3
- base_model: openai/whisper-medium
4
  tags:
5
  - generated_from_trainer
 
 
 
 
 
 
 
 
 
 
 
6
  model-index:
7
- - name: whisper-medium-ga2en-v6.3.0-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-medium-ga2en-v6.3.0-r
15
 
16
- This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
 
 
 
 
 
17
 
18
  ## Model description
19
 
@@ -42,6 +74,52 @@ The following hyperparameters were used during training:
42
  - training_steps: 4000
43
  - mixed_precision_training: Native AMP
44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  ### Framework versions
46
 
47
  - Transformers 4.41.2
 
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
+ - ymoslem/EUbookshop-Speech-Irish
17
+ metrics:
18
+ - bleu
19
+ - wer
20
  model-index:
21
+ - name: Whisper Medium GA-EN Speech Translation
22
+ results:
23
+ - task:
24
+ name: Automatic Speech Recognition
25
+ type: automatic-speech-recognition
26
+ dataset:
27
+ name: IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, Wikimedia, and EUbookshop
28
+ type: ymoslem/IWSLT2023-GA-EN
29
+ metrics:
30
+ - name: Bleu
31
+ type: bleu
32
+ value: 31.02
33
+ - name: Wer
34
+ type: wer
35
+ value: 68.52769022962629
36
  ---
37
 
38
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
39
  should probably proofread and complete it, then remove this comment. -->
40
 
41
+ # Whisper Medium GA-EN Speech Translation
42
 
43
+ 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, Wikimedia, and EUbookshop dataset.
44
+ It achieves the following results on the evaluation set:
45
+ - Loss: 1.0576
46
+ - Bleu: 31.02
47
+ - Chrf: 53.51
48
+ - Wer: 68.5277
49
 
50
  ## Model description
51
 
 
74
  - training_steps: 4000
75
  - mixed_precision_training: Native AMP
76
 
77
+ ### Training results
78
+
79
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf | Wer |
80
+ |:-------------:|:------:|:----:|:---------------:|:-----:|:-----:|:--------:|
81
+ | 2.5374 | 0.0138 | 100 | 2.1201 | 2.56 | 18.92 | 222.4674 |
82
+ | 2.446 | 0.0276 | 200 | 2.1960 | 3.07 | 20.56 | 170.5088 |
83
+ | 2.2819 | 0.0414 | 300 | 1.9811 | 5.87 | 25.17 | 114.5880 |
84
+ | 2.1904 | 0.0552 | 400 | 1.9974 | 8.41 | 25.65 | 99.1896 |
85
+ | 2.026 | 0.0690 | 500 | 1.8961 | 7.99 | 27.64 | 130.7069 |
86
+ | 2.0448 | 0.0828 | 600 | 1.9410 | 9.15 | 27.78 | 104.9077 |
87
+ | 1.8606 | 0.0966 | 700 | 1.8451 | 9.57 | 29.34 | 110.4908 |
88
+ | 1.9887 | 0.1103 | 800 | 1.7419 | 13.44 | 32.32 | 84.3314 |
89
+ | 1.8633 | 0.1241 | 900 | 1.7376 | 13.43 | 31.58 | 102.1162 |
90
+ | 1.7576 | 0.1379 | 1000 | 1.6879 | 11.9 | 32.68 | 106.6186 |
91
+ | 1.7142 | 0.1517 | 1100 | 1.7571 | 12.4 | 33.66 | 102.6114 |
92
+ | 1.7168 | 0.1655 | 1200 | 1.6003 | 17.35 | 36.55 | 87.9784 |
93
+ | 1.6741 | 0.1793 | 1300 | 1.5883 | 15.41 | 35.46 | 92.8411 |
94
+ | 1.6534 | 0.1931 | 1400 | 1.5366 | 17.12 | 37.24 | 90.2296 |
95
+ | 1.58 | 0.2069 | 1500 | 1.5141 | 17.49 | 38.5 | 92.1207 |
96
+ | 1.403 | 0.2207 | 1600 | 1.4606 | 16.78 | 39.13 | 88.9689 |
97
+ | 1.3806 | 0.2345 | 1700 | 1.4263 | 19.26 | 40.02 | 86.7177 |
98
+ | 1.5111 | 0.2483 | 1800 | 1.4060 | 18.4 | 39.47 | 92.2557 |
99
+ | 1.4261 | 0.2621 | 1900 | 1.3911 | 21.19 | 42.13 | 78.7033 |
100
+ | 1.2974 | 0.2759 | 2000 | 1.3871 | 15.6 | 38.66 | 100.3152 |
101
+ | 1.2694 | 0.2897 | 2100 | 1.3527 | 16.21 | 39.99 | 91.2652 |
102
+ | 1.204 | 0.3034 | 2200 | 1.3232 | 20.2 | 41.18 | 86.8978 |
103
+ | 1.1922 | 0.3172 | 2300 | 1.3338 | 16.44 | 40.85 | 103.1968 |
104
+ | 1.1237 | 0.3310 | 2400 | 1.2830 | 19.29 | 43.73 | 94.4620 |
105
+ | 1.0989 | 0.3448 | 2500 | 1.2844 | 25.11 | 46.84 | 75.0563 |
106
+ | 1.0766 | 0.3586 | 2600 | 1.2578 | 23.87 | 46.1 | 74.5160 |
107
+ | 1.0432 | 0.3724 | 2700 | 1.2414 | 22.31 | 44.91 | 86.9878 |
108
+ | 1.1588 | 0.3862 | 2800 | 1.2051 | 23.32 | 45.94 | 77.1724 |
109
+ | 1.0062 | 0.4 | 2900 | 1.2059 | 26.15 | 48.27 | 69.4282 |
110
+ | 0.9178 | 0.4138 | 3000 | 1.1756 | 29.13 | 48.92 | 64.7456 |
111
+ | 0.9108 | 0.4276 | 3100 | 1.1665 | 28.34 | 48.9 | 67.2220 |
112
+ | 0.9868 | 0.4414 | 3200 | 1.1489 | 25.64 | 48.93 | 75.3264 |
113
+ | 0.9563 | 0.4552 | 3300 | 1.1181 | 27.58 | 49.67 | 71.8145 |
114
+ | 0.9138 | 0.4690 | 3400 | 1.1247 | 28.37 | 50.96 | 71.4543 |
115
+ | 0.8508 | 0.4828 | 3500 | 1.1007 | 29.75 | 51.41 | 68.3476 |
116
+ | 0.836 | 0.4966 | 3600 | 1.1114 | 30.99 | 52.2 | 66.5916 |
117
+ | 0.8435 | 0.5103 | 3700 | 1.0782 | 30.64 | 52.77 | 68.2125 |
118
+ | 0.8323 | 0.5241 | 3800 | 1.0744 | 29.78 | 52.94 | 68.9779 |
119
+ | 0.818 | 0.5379 | 3900 | 1.0639 | 31.23 | 53.21 | 67.7623 |
120
+ | 0.8095 | 0.5517 | 4000 | 1.0576 | 31.02 | 53.51 | 68.5277 |
121
+
122
+
123
  ### Framework versions
124
 
125
  - Transformers 4.41.2