Hugging Face's logo

ymoslem
/
whisper-medium-ga2en-v3.3.1-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
eb02946
•
1 Parent(s): 4b93db4

End of training

Browse files
Files changed (2) hide show
  1. README.md +112 -5
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,19 +1,50 @@
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-v3.3.1-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-v3.3.1-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 +73,82 @@ The following hyperparameters were used during training:
42
  - training_steps: 7000
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
+ metrics:
17
+ - bleu
18
+ - wer
19
  model-index:
20
+ - name: Whisper Medium 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
27
+ type: ymoslem/IWSLT2023-GA-EN
28
+ metrics:
29
+ - name: Bleu
30
+ type: bleu
31
+ value: 35.04
32
+ - name: Wer
33
+ type: wer
34
+ value: 57.90184601530842
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
38
  should probably proofread and complete it, then remove this comment. -->
39
 
40
+ # Whisper Medium GA-EN Speech Translation
41
 
42
+ 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 dataset.
43
+ It achieves the following results on the evaluation set:
44
+ - Loss: 1.2966
45
+ - Bleu: 35.04
46
+ - Chrf: 55.03
47
+ - Wer: 57.9018
48
 
49
  ## Model description
50
 
 
73
  - training_steps: 7000
74
  - mixed_precision_training: Native AMP
75
 
76
+ ### Training results
77
+
78
+ | Training Loss | Epoch | Step | Bleu | Chrf | Validation Loss | Wer |
79
+ |:-------------:|:------:|:----:|:-----:|:-----:|:---------------:|:--------:|
80
+ | 2.5164 | 0.0328 | 100 | 2.56 | 17.46 | 2.0060 | 162.9896 |
81
+ | 2.656 | 0.0657 | 200 | 8.49 | 26.0 | 2.0232 | 99.5498 |
82
+ | 2.5156 | 0.0985 | 300 | 7.55 | 25.1 | 1.9253 | 141.2877 |
83
+ | 2.4722 | 0.1314 | 400 | 12.52 | 30.49 | 1.8289 | 90.4548 |
84
+ | 2.3376 | 0.1642 | 500 | 17.39 | 33.23 | 1.6839 | 81.1796 |
85
+ | 2.1733 | 0.1970 | 600 | 9.62 | 32.48 | 1.7342 | 137.9559 |
86
+ | 2.3382 | 0.2299 | 700 | 12.54 | 34.43 | 1.6570 | 112.2467 |
87
+ | 2.0041 | 0.2627 | 800 | 17.55 | 36.73 | 1.6048 | 85.1418 |
88
+ | 2.1142 | 0.2956 | 900 | 17.58 | 35.74 | 1.6256 | 82.7105 |
89
+ | 2.024 | 0.3284 | 1000 | 14.4 | 37.22 | 1.5861 | 86.7177 |
90
+ | 1.7556 | 0.3612 | 1100 | 17.21 | 38.88 | 1.5415 | 84.5115 |
91
+ | 1.6904 | 0.3941 | 1200 | 19.6 | 38.84 | 1.4902 | 85.3670 |
92
+ | 1.674 | 0.4269 | 1300 | 20.33 | 41.3 | 1.4748 | 88.3836 |
93
+ | 1.6899 | 0.4598 | 1400 | 22.74 | 43.25 | 1.4479 | 80.9995 |
94
+ | 1.5234 | 0.4926 | 1500 | 20.13 | 42.08 | 1.3763 | 80.6844 |
95
+ | 1.364 | 0.5255 | 1600 | 23.12 | 41.78 | 1.4164 | 72.9851 |
96
+ | 1.5267 | 0.5583 | 1700 | 19.94 | 41.63 | 1.3855 | 91.7605 |
97
+ | 1.4282 | 0.5911 | 1800 | 23.96 | 44.84 | 1.3729 | 74.6961 |
98
+ | 1.3611 | 0.6240 | 1900 | 23.1 | 45.41 | 1.3562 | 81.8100 |
99
+ | 1.1396 | 0.6568 | 2000 | 27.9 | 46.89 | 1.3131 | 67.2670 |
100
+ | 1.1849 | 0.6897 | 2100 | 24.38 | 45.25 | 1.3483 | 75.8667 |
101
+ | 1.0871 | 0.7225 | 2200 | 28.64 | 48.93 | 1.2848 | 66.6817 |
102
+ | 1.1822 | 0.7553 | 2300 | 28.41 | 47.25 | 1.2782 | 68.6628 |
103
+ | 1.1272 | 0.7882 | 2400 | 27.24 | 48.57 | 1.2549 | 75.9568 |
104
+ | 1.0241 | 0.8210 | 2500 | 25.74 | 47.44 | 1.2922 | 74.4710 |
105
+ | 0.9629 | 0.8539 | 2600 | 23.93 | 44.61 | 1.3209 | 82.1252 |
106
+ | 0.8251 | 0.8867 | 2700 | 32.21 | 51.64 | 1.2273 | 65.5110 |
107
+ | 0.7921 | 0.9195 | 2800 | 26.38 | 48.31 | 1.2881 | 80.2792 |
108
+ | 0.8873 | 0.9524 | 2900 | 26.57 | 50.09 | 1.2268 | 77.1724 |
109
+ | 0.7967 | 0.9852 | 3000 | 29.35 | 51.53 | 1.2036 | 69.6533 |
110
+ | 0.3119 | 1.0181 | 3100 | 31.77 | 51.57 | 1.2231 | 62.3143 |
111
+ | 0.3009 | 1.0509 | 3200 | 31.8 | 50.44 | 1.2446 | 61.8190 |
112
+ | 0.2855 | 1.0837 | 3300 | 30.48 | 50.86 | 1.2240 | 66.7717 |
113
+ | 0.2535 | 1.1166 | 3400 | 31.96 | 52.82 | 1.2287 | 63.3949 |
114
+ | 0.2162 | 1.1494 | 3500 | 33.91 | 52.17 | 1.2398 | 61.3688 |
115
+ | 0.2307 | 1.1823 | 3600 | 32.11 | 51.67 | 1.2280 | 64.7456 |
116
+ | 0.2184 | 1.2151 | 3700 | 34.59 | 53.32 | 1.2149 | 59.9730 |
117
+ | 0.2365 | 1.2479 | 3800 | 32.51 | 52.98 | 1.2044 | 62.3593 |
118
+ | 0.1958 | 1.2808 | 3900 | 32.45 | 52.86 | 1.2116 | 63.1697 |
119
+ | 0.2081 | 1.3136 | 4000 | 32.53 | 52.88 | 1.2087 | 62.8095 |
120
+ | 0.2768 | 1.3465 | 4100 | 1.3177| 30.73 | 49.53 | 64.3854 |
121
+ | 0.3241 | 1.3793 | 4200 | 1.3363| 24.44 | 46.88 | 78.2981 |
122
+ | 0.3326 | 1.4122 | 4300 | 1.3622| 27.77 | 47.05 | 68.7528 |
123
+ | 0.3623 | 1.4450 | 4400 | 1.3232| 27.0 | 47.25 | 70.4187 |
124
+ | 0.3114 | 1.4778 | 4500 | 1.3530| 25.64 | 46.53 | 73.7506 |
125
+ | 0.2933 | 1.5107 | 4600 | 1.3674| 29.95 | 47.77 | 65.3760 |
126
+ | 0.3162 | 1.5435 | 4700 | 1.4011| 28.58 | 47.12 | 66.2765 |
127
+ | 0.2687 | 1.5764 | 4800 | 1.2875| 32.67 | 50.02 | 61.7740 |
128
+ | 0.2733 | 1.6092 | 4900 | 1.3090| 30.86 | 50.51 | 63.2148 |
129
+ | 0.2552 | 1.6420 | 5000 | 1.2946| 27.95 | 49.41 | 69.8334 |
130
+ | 0.2781 | 1.6749 | 5100 | 1.2971| 34.16 | 52.07 | 61.5489 |
131
+ | 0.2367 | 1.7077 | 5200 | 1.2990| 32.3 | 51.69 | 63.3949 |
132
+ | 0.244 | 1.7406 | 5300 | 1.3185| 32.17 | 50.59 | 62.0891 |
133
+ | 0.2118 | 1.7734 | 5400 | 1.2813| 32.85 | 52.14 | 60.8735 |
134
+ | 0.1986 | 1.8062 | 5500 | 1.3007| 30.35 | 50.78 | 64.9707 |
135
+ | 0.2393 | 1.8391 | 5600 | 1.2729| 34.09 | 53.08 | 59.3426 |
136
+ | 0.1803 | 1.8719 | 5700 | 1.2481| 33.92 | 53.57 | 59.7929 |
137
+ | 0.199 | 1.9048 | 5800 | 1.2670| 34.53 | 52.74 | 58.9824 |
138
+ | 0.2 | 1.9376 | 5900 | 1.2591| 33.57 | 53.24 | 60.0180 |
139
+ | 0.1585 | 1.9704 | 6000 | 1.2855| 31.51 | 52.67 | 64.0702 |
140
+ | 0.132 | 2.0033 | 6100 | 1.2915| 30.79 | 51.84 | 66.5466 |
141
+ | 0.0555 | 2.0361 | 6200 | 1.3077| 34.44 | 51.8 | 61.2337 |
142
+ | 0.0623 | 2.0690 | 6300 | 1.3224| 35.52 | 53.58 | 59.4327 |
143
+ | 0.0455 | 2.1018 | 6400 | 1.2942| 35.34 | 53.46 | 58.9824 |
144
+ | 0.0573 | 2.1346 | 6500 | 1.3020| 34.32 | 53.93 | 59.5227 |
145
+ | 0.0487 | 2.1675 | 6600 | 1.3091| 35.64 | 54.4 | 58.9824 |
146
+ | 0.0646 | 2.2003 | 6700 | 1.3184| 34.75 | 53.92 | 59.0725 |
147
+ | 0.0454 | 2.2332 | 6800 | 1.3062| 35.48 | 55.12 | 58.2620 |
148
+ | 0.0574 | 2.2660 | 6900 | 1.2996| 34.97 | 55.31 | 58.6673 |
149
+ | 0.051 | 2.2989 | 7000 | 1.2966| 35.04 | 55.03 | 57.9018 |
150
+
151
+
152
  ### Framework versions
153
 
154
  - Transformers 4.41.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94b74f218bac391ffe89afc41c19c319caada5ce9405c419fe9d98899cda8ed0
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fdd3010f025f982f3b5a921f6d23078415abb3e53c08f4fefb7e27336c3a762
3
  size 3055544304