Hugging Face's logo

joeyMartig
/
whisper-large-v3-dnd-fr-test

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
French
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
joeyMartig commited on
Commit
7e2d852
•
1 Parent(s): 5b6baf4

End of training

Browse files
Files changed (4) hide show
  1. README.md +50 -20
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
  4. runs/Jul25_10-59-34_gpu027.baobab/events.out.tfevents.1721897995.gpu027.baobab.3036665.0 +2 -2
README.md CHANGED
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.1264
23
  - Wer: 33.4454
24
 
25
  ## Model description
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 50
49
- - num_epochs: 20
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
@@ -55,24 +55,54 @@ The following hyperparameters were used during training:
55
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
56
  | No log | 1.0 | 7 | 1.0810 | 38.6555 |
57
  | No log | 2.0 | 14 | 1.0631 | 38.7395 |
58
- | No log | 3.0 | 21 | 0.9919 | 38.1513 |
59
- | No log | 4.0 | 28 | 0.9135 | 37.3109 |
60
- | No log | 5.0 | 35 | 0.7922 | 37.0588 |
61
- | No log | 6.0 | 42 | 0.7013 | 35.6303 |
62
- | No log | 7.0 | 49 | 0.6073 | 34.6218 |
63
- | No log | 8.0 | 56 | 0.5099 | 45.5462 |
64
- | No log | 9.0 | 63 | 0.4297 | 40.0 |
65
- | No log | 10.0 | 70 | 0.3603 | 33.4454 |
66
- | No log | 11.0 | 77 | 0.3024 | 33.4454 |
67
- | No log | 12.0 | 84 | 0.2540 | 33.4454 |
68
- | No log | 13.0 | 91 | 0.2196 | 33.4454 |
69
- | No log | 14.0 | 98 | 0.1907 | 33.4454 |
70
- | No log | 15.0 | 105 | 0.1695 | 36.7227 |
71
- | No log | 16.0 | 112 | 0.1536 | 36.7227 |
72
- | No log | 17.0 | 119 | 0.1421 | 33.4454 |
73
- | No log | 18.0 | 126 | 0.1336 | 33.4454 |
74
- | No log | 19.0 | 133 | 0.1282 | 33.4454 |
75
- | No log | 20.0 | 140 | 0.1264 | 33.4454 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
 
77
 
78
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.0138
23
  - Wer: 33.4454
24
 
25
  ## Model description
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 50
49
+ - num_epochs: 50
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
 
55
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
56
  | No log | 1.0 | 7 | 1.0810 | 38.6555 |
57
  | No log | 2.0 | 14 | 1.0631 | 38.7395 |
58
+ | No log | 3.0 | 21 | 0.9917 | 38.1513 |
59
+ | No log | 4.0 | 28 | 0.9133 | 37.3109 |
60
+ | No log | 5.0 | 35 | 0.7915 | 37.0588 |
61
+ | No log | 6.0 | 42 | 0.7010 | 35.6303 |
62
+ | No log | 7.0 | 49 | 0.6078 | 34.6218 |
63
+ | No log | 8.0 | 56 | 0.5114 | 45.6303 |
64
+ | No log | 9.0 | 63 | 0.4258 | 40.0 |
65
+ | No log | 10.0 | 70 | 0.3484 | 33.4454 |
66
+ | No log | 11.0 | 77 | 0.2802 | 33.4454 |
67
+ | No log | 12.0 | 84 | 0.2228 | 33.4454 |
68
+ | No log | 13.0 | 91 | 0.1804 | 33.4454 |
69
+ | No log | 14.0 | 98 | 0.1436 | 36.5546 |
70
+ | No log | 15.0 | 105 | 0.1166 | 33.4454 |
71
+ | No log | 16.0 | 112 | 0.0932 | 36.5546 |
72
+ | No log | 17.0 | 119 | 0.0730 | 36.5546 |
73
+ | No log | 18.0 | 126 | 0.0573 | 36.5546 |
74
+ | No log | 19.0 | 133 | 0.0451 | 36.5546 |
75
+ | No log | 20.0 | 140 | 0.0390 | 33.4454 |
76
+ | No log | 21.0 | 147 | 0.0319 | 33.4454 |
77
+ | No log | 22.0 | 154 | 0.0287 | 33.4454 |
78
+ | No log | 23.0 | 161 | 0.0252 | 33.4454 |
79
+ | No log | 24.0 | 168 | 0.0224 | 33.4454 |
80
+ | No log | 25.0 | 175 | 0.0209 | 33.4454 |
81
+ | No log | 26.0 | 182 | 0.0199 | 33.4454 |
82
+ | No log | 27.0 | 189 | 0.0186 | 33.4454 |
83
+ | No log | 28.0 | 196 | 0.0179 | 33.4454 |
84
+ | No log | 29.0 | 203 | 0.0175 | 33.4454 |
85
+ | No log | 30.0 | 210 | 0.0168 | 33.4454 |
86
+ | No log | 31.0 | 217 | 0.0164 | 33.4454 |
87
+ | No log | 32.0 | 224 | 0.0161 | 33.4454 |
88
+ | No log | 33.0 | 231 | 0.0158 | 33.4454 |
89
+ | No log | 34.0 | 238 | 0.0156 | 33.4454 |
90
+ | No log | 35.0 | 245 | 0.0153 | 33.4454 |
91
+ | No log | 36.0 | 252 | 0.0151 | 33.4454 |
92
+ | No log | 37.0 | 259 | 0.0149 | 33.4454 |
93
+ | No log | 38.0 | 266 | 0.0148 | 33.4454 |
94
+ | No log | 39.0 | 273 | 0.0146 | 33.4454 |
95
+ | No log | 40.0 | 280 | 0.0145 | 33.4454 |
96
+ | No log | 41.0 | 287 | 0.0143 | 33.4454 |
97
+ | No log | 42.0 | 294 | 0.0143 | 33.4454 |
98
+ | No log | 43.0 | 301 | 0.0141 | 33.4454 |
99
+ | No log | 44.0 | 308 | 0.0141 | 33.4454 |
100
+ | No log | 45.0 | 315 | 0.0140 | 33.4454 |
101
+ | No log | 46.0 | 322 | 0.0139 | 33.4454 |
102
+ | No log | 47.0 | 329 | 0.0139 | 33.4454 |
103
+ | No log | 48.0 | 336 | 0.0138 | 33.4454 |
104
+ | No log | 49.0 | 343 | 0.0138 | 33.4454 |
105
+ | No log | 50.0 | 350 | 0.0138 | 33.4454 |
106
 
107
 
108
  ### Framework versions
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08a447f564bba3599171f89be321fb16ef8f6ea93f61bb12d00292f31ac0acb0
3
  size 4993448880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8f63bb8708c3183d7a2f9b78ee22c8406ebc4d3fc5d1a413e57764c8159e94c
3
  size 4993448880
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b0bb2dab347807324f5b6e6d3c1eb5300232b15540cc880e6c5a2811fe8cbaa
3
  size 1180663192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0d5aeb3dd53783aad7bdc13cf7d9a9c30c175ca998e19d05d7e72129170179
3
  size 1180663192
runs/Jul25_10-59-34_gpu027.baobab/events.out.tfevents.1721897995.gpu027.baobab.3036665.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1fffd6c85e25c121284660eebdade4b62b2c36943e21321d080b7ab1d0ac2ee
3
- size 21534
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca8eeb5ca8655317fbafe060cbf463a93ed85a18f296f61dbd0f96db82cc7a93
3
+ size 21888