Hugging Face's logo

personalizedrefrigerator
/
whisper-tiny-fr

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
personalizedrefrigerator commited on
Commit
36b5d0b
·
verified ·
1 Parent(s): fc00970

End of training

Browse files
Files changed (8) hide show
  1. README.md +38 -21
  2. model.safetensors +1 -1
  3. runs/Mar18_21-54-25_58c989e9a324/events.out.tfevents.1742335065.58c989e9a324.192.0 +3 -0
  4. runs/Mar18_21-58-18_58c989e9a324/events.out.tfevents.1742335103.58c989e9a324.192.1 +3 -0
  5. runs/Mar18_22-22-57_58c989e9a324/events.out.tfevents.1742336583.58c989e9a324.192.2 +3 -0
  6. runs/Mar18_22-58-10_58c989e9a324/events.out.tfevents.1742338887.58c989e9a324.17602.0 +3 -0
  7. runs/Mar18_22-58-10_58c989e9a324/events.out.tfevents.1742360360.58c989e9a324.17602.1 +3 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6871
22
- - Model Preparation Time: 0.0056
23
- - Wer: 0.5022
24
- - Cer: 0.3447
25
 
26
  ## Model description
27
 
@@ -46,29 +46,46 @@ The following hyperparameters were used during training:
46
  - seed: 42
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
- - training_steps: 16000
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer | Cer |
55
  |:-------------:|:------:|:-----:|:---------------:|:----------------------:|:------:|:------:|
56
- | 1.0566 | 0.0625 | 1000 | 1.3246 | 0.0056 | 0.7494 | 0.4923 |
57
- | 0.8712 | 0.125 | 2000 | 1.1335 | 0.0056 | 0.6508 | 0.4880 |
58
- | 0.7638 | 0.1875 | 3000 | 1.0380 | 0.0056 | 0.5891 | 0.4386 |
59
- | 0.8262 | 0.25 | 4000 | 0.9789 | 0.0056 | 0.5435 | 0.3623 |
60
- | 0.669 | 0.3125 | 5000 | 0.9403 | 0.0056 | 0.5613 | 0.3955 |
61
- | 0.6105 | 0.375 | 6000 | 0.9065 | 0.0056 | 0.5876 | 0.3812 |
62
- | 0.5432 | 0.4375 | 7000 | 0.8885 | 0.0056 | 0.5350 | 0.3625 |
63
- | 0.5188 | 0.5 | 8000 | 0.8876 | 0.0056 | 0.5612 | 0.3821 |
64
- | 0.6963 | 0.5625 | 9000 | 0.8451 | 0.0056 | 0.5926 | 0.3922 |
65
- | 0.6387 | 0.625 | 10000 | 0.7571 | 0.0056 | 0.4981 | 0.3410 |
66
- | 0.5572 | 0.6875 | 11000 | 0.7194 | 0.0056 | 0.5045 | 0.3508 |
67
- | 0.5207 | 0.75 | 12000 | 0.7124 | 0.0056 | 0.4742 | 0.3312 |
68
- | 0.4515 | 0.8125 | 13000 | 0.7004 | 0.0056 | 0.4817 | 0.3345 |
69
- | 0.4858 | 0.875 | 14000 | 0.7089 | 0.0056 | 0.4602 | 0.3271 |
70
- | 0.4601 | 0.9375 | 15000 | 0.6796 | 0.0056 | 0.5509 | 0.3672 |
71
- | 0.4808 | 1.0 | 16000 | 0.6719 | 0.0056 | 0.4443 | 0.2966 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.6094
22
+ - Model Preparation Time: 0.0026
23
+ - Wer: 0.3301
24
+ - Cer: 0.1774
25
 
26
  ## Model description
27
 
 
46
  - seed: 42
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
+ - training_steps: 33000
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer | Cer |
55
  |:-------------:|:------:|:-----:|:---------------:|:----------------------:|:------:|:------:|
56
+ | 0.8933 | 0.0303 | 1000 | 1.3184 | 0.0026 | 0.5726 | 0.3162 |
57
+ | 0.7455 | 0.0606 | 2000 | 1.1738 | 0.0026 | 0.5533 | 0.2930 |
58
+ | 0.735 | 0.0909 | 3000 | 1.0462 | 0.0026 | 0.6032 | 0.3290 |
59
+ | 0.6426 | 0.1212 | 4000 | 1.0629 | 0.0026 | 0.4937 | 0.2473 |
60
+ | 0.6389 | 0.1515 | 5000 | 1.0132 | 0.0026 | 0.5671 | 0.3415 |
61
+ | 0.532 | 0.1818 | 6000 | 1.0194 | 0.0026 | 0.4639 | 0.2355 |
62
+ | 0.5341 | 0.2121 | 7000 | 1.0092 | 0.0026 | 0.4619 | 0.2435 |
63
+ | 0.4773 | 0.2424 | 8000 | 0.9672 | 0.0026 | 0.4666 | 0.2822 |
64
+ | 0.4932 | 0.2727 | 9000 | 0.9778 | 0.0026 | 0.4175 | 0.2187 |
65
+ | 0.479 | 0.3030 | 10000 | 0.9639 | 0.0026 | 0.4105 | 0.2169 |
66
+ | 0.4663 | 0.3333 | 11000 | 0.9689 | 0.0026 | 0.4236 | 0.2245 |
67
+ | 0.3647 | 0.3636 | 12000 | 1.0025 | 0.0026 | 0.4326 | 0.2297 |
68
+ | 0.451 | 0.3939 | 13000 | 0.8810 | 0.0026 | 0.4648 | 0.2591 |
69
+ | 0.4522 | 0.4242 | 14000 | 0.8283 | 0.0026 | 0.3869 | 0.1965 |
70
+ | 0.5064 | 0.4545 | 15000 | 0.8165 | 0.0026 | 0.3703 | 0.1898 |
71
+ | 0.4355 | 0.4848 | 16000 | 0.7857 | 0.0026 | 0.4367 | 0.2257 |
72
+ | 0.2953 | 0.5152 | 17000 | 0.8007 | 0.0026 | 0.3650 | 0.2020 |
73
+ | 0.4345 | 0.5455 | 18000 | 0.7823 | 0.0026 | 0.4544 | 0.2381 |
74
+ | 0.4117 | 0.5758 | 19000 | 0.7648 | 0.0026 | 0.3595 | 0.1823 |
75
+ | 0.4071 | 0.6061 | 20000 | 0.7475 | 0.0026 | 0.4121 | 0.2049 |
76
+ | 0.4371 | 0.6364 | 21000 | 0.7285 | 0.0026 | 0.3509 | 0.1842 |
77
+ | 0.34 | 0.6667 | 22000 | 0.7686 | 0.0026 | 0.3566 | 0.1860 |
78
+ | 0.335 | 0.6970 | 23000 | 0.7514 | 0.0026 | 0.3595 | 0.1846 |
79
+ | 0.2946 | 0.7273 | 24000 | 0.7928 | 0.0026 | 0.3742 | 0.2006 |
80
+ | 0.3916 | 0.7576 | 25000 | 0.6843 | 0.0026 | 0.3416 | 0.1747 |
81
+ | 0.3233 | 0.7879 | 26000 | 0.6478 | 0.0026 | 0.3178 | 0.1626 |
82
+ | 0.2981 | 0.8182 | 27000 | 0.6737 | 0.0026 | 0.3274 | 0.1669 |
83
+ | 0.2945 | 0.8485 | 28000 | 0.6512 | 0.0026 | 0.3302 | 0.1643 |
84
+ | 0.2956 | 0.8788 | 29000 | 0.6867 | 0.0026 | 0.3925 | 0.1991 |
85
+ | 0.2541 | 0.9091 | 30000 | 0.6333 | 0.0026 | 0.3186 | 0.1620 |
86
+ | 0.2475 | 0.9394 | 31000 | 0.7018 | 0.0026 | 0.3343 | 0.1722 |
87
+ | 0.2951 | 0.9697 | 32000 | 0.6527 | 0.0026 | 0.3168 | 0.1632 |
88
+ | 0.2879 | 1.0 | 33000 | 0.6440 | 0.0026 | 0.3102 | 0.1560 |
89
 
90
 
91
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cefe71e77c49e46e78f5e38f5f1fc250a329f0f46766a4a751dd90496e7ef52
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5844fa3946484a8cd70a75c3ec066803563654637690c6930e03f0a195a14d7d
3
  size 151061672
runs/Mar18_21-54-25_58c989e9a324/events.out.tfevents.1742335065.58c989e9a324.192.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:383828cbac0b0cd037fda8991beb4af87dd1be2075a88af52811a979df1c709a
3
+ size 7268
runs/Mar18_21-58-18_58c989e9a324/events.out.tfevents.1742335103.58c989e9a324.192.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef8bb1256497f7248240273658f83dda8c6c67e6984d921dfa6ac6456740cdf7
3
+ size 25971
runs/Mar18_22-22-57_58c989e9a324/events.out.tfevents.1742336583.58c989e9a324.192.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adeeb470b7d2932a72f77926cfd6716c974a6ca24429323bec525d2283120307
3
+ size 33510
runs/Mar18_22-58-10_58c989e9a324/events.out.tfevents.1742338887.58c989e9a324.17602.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73bbf70242f34b3522ec8738c3825b668d75dc1d7263227583b4d30cde8428be
3
+ size 303354
runs/Mar18_22-58-10_58c989e9a324/events.out.tfevents.1742360360.58c989e9a324.17602.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b10b90a220b02d6ec16215c8afa1c1475eefc72fb62cc3d3efbc033a88fa1866
3
+ size 527
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82dc1bd201f593001f8f33ed0e96717f04f96861409b704e895d5861edaeefb4
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d4f6f303b7380c6654624c9a949e09eb27b3019f62bdc3bd68002280aa7c0aa
3
  size 5560