Hugging Face's logo

ymoslem
/
whisper-medium-ga2en-v7.3.1-9k-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
c6f19e3
•
1 Parent(s): eea4e2c

End of training

Browse files
Files changed (2) hide show
  1. README.md +133 -4
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,19 +1,52 @@
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-v7.3.1-9k-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-v7.3.1-9k-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 +75,102 @@ The following hyperparameters were used during training:
42
  - training_steps: 9000
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-medium
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/Tatoeba-Speech-Irish-Noise-002
17
+ - ymoslem/Wikimedia-Speech-Irish-Noise-002
18
+ metrics:
19
+ - bleu
20
+ - wer
21
  model-index:
22
+ - name: Whisper Medium GA-EN Speech Translation
23
+ results:
24
+ - task:
25
+ name: Automatic Speech Recognition
26
+ type: automatic-speech-recognition
27
+ dataset:
28
+ name: IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia
29
+ type: ymoslem/IWSLT2023-GA-EN
30
+ metrics:
31
+ - name: Bleu
32
+ type: bleu
33
+ value: 33.46
34
+ - name: Wer
35
+ type: wer
36
+ value: 61.773975686627644
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 Medium GA-EN Speech Translation
43
 
44
+ This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia dataset.
45
+ It achieves the following results on the evaluation set:
46
+ - Loss: 1.3291
47
+ - Bleu: 33.46
48
+ - Chrf: 52.93
49
+ - Wer: 61.7740
50
 
51
  ## Model description
52
 
 
75
  - training_steps: 9000
76
  - mixed_precision_training: Native AMP
77
 
78
+ ### Training results
79
+
80
+ | Training Loss | Epoch | Step | Bleu | Chrf | Validation Loss | Wer |
81
+ |:-------------:|:------:|:----:|:-----:|:-----:|:---------------:|:--------:|
82
+ | 2.4998 | 0.0236 | 100 | 4.24 | 19.77 | 2.0245 | 123.5029 |
83
+ | 2.5999 | 0.0472 | 200 | 5.55 | 23.63 | 2.0729 | 130.1666 |
84
+ | 2.4062 | 0.0708 | 300 | 5.92 | 24.15 | 1.9928 | 157.4966 |
85
+ | 2.1866 | 0.0944 | 400 | 12.74 | 30.47 | 1.8337 | 93.4714 |
86
+ | 2.2485 | 0.1180 | 500 | 10.32 | 30.65 | 1.8209 | 116.4791 |
87
+ | 2.1521 | 0.1416 | 600 | 9.84 | 30.97 | 1.7512 | 130.1666 |
88
+ | 1.9324 | 0.1653 | 700 | 17.24 | 34.37 | 1.7362 | 85.4570 |
89
+ | 1.9703 | 0.1889 | 800 | 13.05 | 32.27 | 1.6784 | 105.7632 |
90
+ | 1.7299 | 0.2125 | 900 | 9.81 | 31.71 | 1.6530 | 131.6974 |
91
+ | 1.7822 | 0.2361 | 1000 | 11.72 | 32.5 | 1.5541 | 125.7091 |
92
+ | 1.5493 | 0.2597 | 1100 | 15.04 | 36.72 | 1.5773 | 92.4358 |
93
+ | 1.4813 | 0.2833 | 1200 | 22.08 | 40.11 | 1.5341 | 75.8667 |
94
+ | 1.5285 | 0.3069 | 1300 | 18.88 | 40.93 | 1.4834 | 95.4975 |
95
+ | 1.3255 | 0.3305 | 1400 | 20.11 | 40.82 | 1.4956 | 85.2319 |
96
+ | 1.3931 | 0.3541 | 1500 | 22.81 | 41.51 | 1.4718 | 72.2197 |
97
+ | 1.3962 | 0.3777 | 1600 | 25.43 | 43.53 | 1.3794 | 71.1842 |
98
+ | 1.1412 | 0.4013 | 1700 | 22.13 | 43.19 | 1.4172 | 86.9428 |
99
+ | 1.1132 | 0.4249 | 1800 | 21.27 | 42.45 | 1.3989 | 81.0896 |
100
+ | 0.9261 | 0.4485 | 1900 | 26.39 | 45.4 | 1.4147 | 70.6889 |
101
+ | 0.994 | 0.4721 | 2000 | 24.38 | 42.87 | 1.4365 | 77.5326 |
102
+ | 0.8598 | 0.4958 | 2100 | 19.36 | 41.49 | 1.3559 | 96.6231 |
103
+ | 0.7784 | 0.5194 | 2200 | 26.54 | 45.57 | 1.3550 | 69.5633 |
104
+ | 0.7858 | 0.5430 | 2300 | 27.52 | 47.58 | 1.3156 | 68.8879 |
105
+ | 0.7715 | 0.5666 | 2400 | 26.12 | 46.47 | 1.2985 | 72.5349 |
106
+ | 0.7079 | 0.5902 | 2500 | 25.62 | 47.61 | 1.3134 | 68.6177 |
107
+ | 0.6704 | 0.6138 | 2600 | 28.2 | 47.37 | 1.3047 | 69.1130 |
108
+ | 0.6579 | 0.6374 | 2700 | 29.52 | 49.39 | 1.2486 | 68.2125 |
109
+ | 0.502 | 0.6610 | 2800 | 28.08 | 48.99 | 1.2511 | 68.6177 |
110
+ | 0.4442 | 0.6846 | 2900 | 32.57 | 50.66 | 1.2800 | 63.3498 |
111
+ | 0.5175 | 0.7082 | 3000 | 29.69 | 48.77 | 1.2650 | 66.2314 |
112
+ | 0.4416 | 0.7318 | 3100 | 32.36 | 50.29 | 1.2554 | 61.9090 |
113
+ | 0.4529 | 0.7554 | 3200 | 32.6 | 50.94 | 1.2050 | 61.5489 |
114
+ | 0.4435 | 0.7790 | 3300 | 33.2 | 52.17 | 1.2103 | 61.3688 |
115
+ | 0.3724 | 0.8026 | 3400 | 33.89 | 52.88 | 1.1756 | 59.8379 |
116
+ | 0.3883 | 0.8263 | 3500 | 32.21 | 51.86 | 1.1979 | 62.0891 |
117
+ | 0.3534 | 0.8499 | 3600 | 32.75 | 51.85 | 1.1943 | 61.2337 |
118
+ | 0.326 | 0.8735 | 3700 | 32.43 | 51.5 | 1.1891 | 62.1342 |
119
+ | 0.305 | 0.8971 | 3800 | 33.43 | 51.45 | 1.1858 | 59.4327 |
120
+ | 0.2258 | 0.9207 | 3900 | 32.53 | 51.42 | 1.1827 | 61.1887 |
121
+ | 0.3104 | 0.9443 | 4000 | 32.1 | 51.33 | 1.1857 | 61.2337 |
122
+ | 0.3847 | 0.9679 | 4100 | 1.3506| 29.91 | 48.63 | 66.5466 |
123
+ | 0.426 | 0.9915 | 4200 | 1.3458| 25.68 | 45.27 | 70.1036 |
124
+ | 0.2622 | 1.0151 | 4300 | 1.3544| 27.52 | 48.0 | 66.4115 |
125
+ | 0.2429 | 1.0387 | 4400 | 1.4330| 22.57 | 45.45 | 79.9190 |
126
+ | 0.269 | 1.0623 | 4500 | 1.4399| 24.7 | 45.73 | 74.7411 |
127
+ | 0.3171 | 1.0859 | 4600 | 1.3711| 29.55 | 47.78 | 68.4827 |
128
+ | 0.2321 | 1.1095 | 4700 | 1.4350| 24.73 | 45.52 | 77.1724 |
129
+ | 0.2595 | 1.1331 | 4800 | 1.3851| 30.54 | 47.85 | 65.1508 |
130
+ | 0.2426 | 1.1568 | 4900 | 1.4109| 28.87 | 47.5 | 68.3926 |
131
+ | 0.2496 | 1.1804 | 5000 | 1.3717| 29.97 | 48.74 | 68.6628 |
132
+ | 0.2551 | 1.2040 | 5100 | 1.4157| 29.92 | 47.59 | 66.3215 |
133
+ | 0.231 | 1.2276 | 5200 | 1.3908| 28.97 | 47.9 | 66.0063 |
134
+ | 0.245 | 1.2512 | 5300 | 1.4082| 30.22 | 47.71 | 63.7100 |
135
+ | 0.284 | 1.2748 | 5400 | 1.3696| 27.47 | 48.31 | 70.7789 |
136
+ | 0.2284 | 1.2984 | 5500 | 1.4044| 27.63 | 47.37 | 68.2575 |
137
+ | 0.2457 | 1.3220 | 5600 | 1.3722| 31.38 | 48.8 | 64.7906 |
138
+ | 0.2346 | 1.3456 | 5700 | 1.3397| 33.61 | 50.14 | 60.3332 |
139
+ | 0.2088 | 1.3692 | 5800 | 1.3920| 30.84 | 48.51 | 65.4660 |
140
+ | 0.1832 | 1.3928 | 5900 | 1.3892| 31.47 | 49.56 | 64.5205 |
141
+ | 0.2171 | 1.4164 | 6000 | 1.3606| 32.51 | 49.8 | 63.1697 |
142
+ | 0.1799 | 1.4400 | 6100 | 1.4130| 30.8 | 50.05 | 63.3949 |
143
+ | 0.1756 | 1.4636 | 6200 | 1.3458| 30.25 | 50.16 | 66.1864 |
144
+ | 0.1617 | 1.4873 | 6300 | 1.3971| 32.27 | 50.74 | 63.4849 |
145
+ | 0.1909 | 1.5109 | 6400 | 1.4275| 27.41 | 47.04 | 72.0396 |
146
+ | 0.1516 | 1.5345 | 6500 | 1.3591| 30.1 | 49.05 | 66.0513 |
147
+ | 0.1892 | 1.5581 | 6600 | 1.3646| 31.72 | 48.17 | 62.6294 |
148
+ | 0.2086 | 1.5817 | 6700 | 1.3314| 28.85 | 49.68 | 67.3120 |
149
+ | 0.1253 | 1.6053 | 6800 | 1.3461| 29.84 | 49.13 | 66.5466 |
150
+ | 0.1307 | 1.6289 | 6900 | 1.3671| 29.39 | 48.77 | 67.7172 |
151
+ | 0.1376 | 1.6525 | 7000 | 1.3769| 31.27 | 47.97 | 66.5916 |
152
+ | 0.1593 | 1.6761 | 7100 | 1.3699| 30.53 | 49.33 | 65.4660 |
153
+ | 0.1604 | 1.6997 | 7200 | 1.3540| 31.99 | 48.93 | 63.8001 |
154
+ | 0.118 | 1.7233 | 7300 | 1.3523| 29.52 | 49.26 | 67.5822 |
155
+ | 0.1148 | 1.7469 | 7400 | 1.3130| 31.49 | 49.49 | 62.8996 |
156
+ | 0.0946 | 1.7705 | 7500 | 1.3468| 32.6 | 49.76 | 63.1697 |
157
+ | 0.0891 | 1.7941 | 7600 | 1.3268| 31.84 | 50.41 | 63.5750 |
158
+ | 0.103 | 1.8178 | 7700 | 1.3243| 32.81 | 50.61 | 60.3782 |
159
+ | 0.1016 | 1.8414 | 7800 | 1.2945| 33.07 | 53.14 | 61.0086 |
160
+ | 0.1014 | 1.8650 | 7900 | 1.3163| 32.35 | 51.28 | 63.3498 |
161
+ | 0.1257 | 1.8886 | 8000 | 1.3246| 31.65 | 51.86 | 61.7740 |
162
+ | 0.0859 | 1.9122 | 8100 | 1.3247| 30.69 | 51.47 | 64.4304 |
163
+ | 0.0943 | 1.9358 | 8200 | 1.3030| 33.06 | 52.31 | 61.6389 |
164
+ | 0.11 | 1.9594 | 8300 | 1.2866| 33.32 | 52.83 | 60.1081 |
165
+ | 0.0723 | 1.9830 | 8400 | 1.3071| 32.96 | 51.64 | 61.7740 |
166
+ | 0.0312 | 2.0066 | 8500 | 1.3202| 33.2 | 52.78 | 62.0891 |
167
+ | 0.0303 | 2.0302 | 8600 | 1.3348| 33.24 | 52.75 | 62.4043 |
168
+ | 0.02 | 2.0538 | 8700 | 1.3447| 33.32 | 52.6 | 62.0891 |
169
+ | 0.0329 | 2.0774 | 8800 | 1.3328| 34.04 | 52.93 | 60.7384 |
170
+ | 0.0216 | 2.1010 | 8900 | 1.3266| 33.47 | 52.75 | 61.3237 |
171
+ | 0.0224 | 2.1246 | 9000 | 1.3291| 33.46 | 52.93 | 61.7740 |
172
+
173
+
174
  ### Framework versions
175
 
176
  - Transformers 4.41.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90fd69aeb49033011bc926db4f8cb9a9543ed68e3fdfc54abdd5bab4a03d9756
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e28a40582efa2b1006e30798e5b9d4c81f139a40762a1bccfe9c402243e757e
3
  size 3055544304