Hugging Face's logo

AkylaiBva
/
my_medium_wspr

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Model card Files
xet
 Metrics Community
AkylaiBva commited on
Commit
509b701
·
verified ·
1 Parent(s): fe6f7f7

End of training

Browse files
Files changed (4) hide show
  1. README.md +36 -9
  2. model.safetensors +1 -1
  3. runs/Jul12_18-02-18_archlinux-ai/events.out.tfevents.1720796539.archlinux-ai.135220.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.6723
21
- - Wer: 51.3053
22
 
23
  ## Model description
24
 
@@ -46,19 +46,46 @@ 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: 3
49
- - training_steps: 20
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:------:|:----:|:---------------:|:--------:|
56
- | 2.1468 | 0.0020 | 3 | 2.7930 | 125.5727 |
57
- | 2.7095 | 0.0041 | 6 | 2.0710 | 104.8482 |
58
- | 1.8246 | 0.0061 | 9 | 1.0897 | 64.5178 |
59
- | 0.9447 | 0.0081 | 12 | 1.1586 | 71.2307 |
60
- | 1.6315 | 0.0102 | 15 | 0.8735 | 60.9483 |
61
- | 0.4987 | 0.0122 | 18 | 0.6723 | 51.3053 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
 
63
 
64
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0939
21
+ - Wer: 11.9372
22
 
23
  ## Model description
24
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 3
49
+ - training_steps: 100
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:------:|:----:|:---------------:|:--------:|
56
+ | 2.6756 | 0.0020 | 3 | 2.8119 | 123.2984 |
57
+ | 2.7362 | 0.0041 | 6 | 2.1522 | 102.6702 |
58
+ | 1.0677 | 0.0061 | 9 | 1.2918 | 79.4764 |
59
+ | 1.1569 | 0.0081 | 12 | 0.8556 | 59.3717 |
60
+ | 1.0248 | 0.0102 | 15 | 0.7711 | 230.4712 |
61
+ | 0.5058 | 0.0122 | 18 | 0.8485 | 264.3979 |
62
+ | 0.4122 | 0.0143 | 21 | 0.7497 | 244.7644 |
63
+ | 0.4989 | 0.0163 | 24 | 0.7179 | 53.7173 |
64
+ | 0.7726 | 0.0183 | 27 | 0.8902 | 60.0524 |
65
+ | 0.793 | 0.0204 | 30 | 0.7948 | 52.2513 |
66
+ | 0.7562 | 0.0224 | 33 | 0.5553 | 41.5183 |
67
+ | 1.0738 | 0.0244 | 36 | 0.3708 | 36.7016 |
68
+ | 0.2565 | 0.0265 | 39 | 0.4904 | 40.5236 |
69
+ | 0.4824 | 0.0285 | 42 | 0.4613 | 44.7644 |
70
+ | 0.4291 | 0.0305 | 45 | 0.4332 | 56.0733 |
71
+ | 0.1382 | 0.0326 | 48 | 0.4353 | 47.6440 |
72
+ | 0.2113 | 0.0346 | 51 | 0.4286 | 37.7487 |
73
+ | 0.2521 | 0.0367 | 54 | 0.4604 | 38.4293 |
74
+ | 0.9556 | 0.0387 | 57 | 0.4387 | 43.4031 |
75
+ | 0.5493 | 0.0407 | 60 | 0.2983 | 30.8901 |
76
+ | 0.1505 | 0.0428 | 63 | 0.2391 | 26.5969 |
77
+ | 0.0664 | 0.0448 | 66 | 0.2358 | 27.6963 |
78
+ | 0.2826 | 0.0468 | 69 | 0.2045 | 27.9058 |
79
+ | 0.2103 | 0.0489 | 72 | 0.1674 | 20.1571 |
80
+ | 0.3009 | 0.0509 | 75 | 0.1725 | 17.9581 |
81
+ | 0.2875 | 0.0530 | 78 | 0.1275 | 18.1675 |
82
+ | 0.0258 | 0.0550 | 81 | 0.1209 | 16.6492 |
83
+ | 0.0935 | 0.0570 | 84 | 0.1545 | 19.0052 |
84
+ | 0.26 | 0.0591 | 87 | 0.1516 | 18.7435 |
85
+ | 0.0844 | 0.0611 | 90 | 0.1500 | 19.7906 |
86
+ | 0.0386 | 0.0631 | 93 | 0.1495 | 20.2618 |
87
+ | 0.403 | 0.0652 | 96 | 0.1036 | 12.9319 |
88
+ | 0.0091 | 0.0672 | 99 | 0.0939 | 11.9372 |
89
 
90
 
91
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e41fc0198a2ddda4941adf0a55f11aa28dd91c79df21efb8a2a950381179c4d
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:648b30564d3e65fc73d4f67d4f41091f195ae9d90e9ee7d2f069ad9140c8e6b2
3
  size 3055544304
runs/Jul12_18-02-18_archlinux-ai/events.out.tfevents.1720796539.archlinux-ai.135220.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e935f7eed3f697c90a21e0a2e0f32dfb0e04bb7aa19710d9f255ebd50f1808ce
3
+ size 24089
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c192b44a290d59f71215f442c241ca67309be7cb0eca823fc612f733d8f075d9
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d22d534e39e855c7c7a38f024844017c8bf2f0d7900a5361250de723352e81a3
3
  size 5240