Hugging Face's logo

DevforMM
/
exo-5

Automatic Speech Recognition
Transformers
Safetensors
whisper
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
DevforMM commited on
Commit
fd21d92
·
verified ·
1 Parent(s): e70afd3

End of training

Browse files
Files changed (2) hide show
  1. README.md +21 -21
  2. model.safetensors +1 -1
README.md CHANGED
@@ -20,7 +20,7 @@ model-index:
20
  metrics:
21
  - name: Wer
22
  type: wer
23
- value: 0.10517885744794447
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
32
  It achieves the following results on the evaluation set:
33
- - Loss: 0.1371
34
- - Wer: 0.1052
35
- - Wer Ortho: 0.1544
36
 
37
  ## Model description
38
 
@@ -63,23 +63,23 @@ The following hyperparameters were used during training:
63
 
64
  ### Training results
65
 
66
- | Training Loss | Epoch | Step | Validation Loss | Wer | Wer Ortho |
67
- |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|
68
- | 2.1611 | 1.0 | 57 | 0.6315 | 0.1731 | 0.2685 |
69
- | 0.3924 | 2.0 | 114 | 0.6604 | 0.2028 | 0.2476 |
70
- | 0.1426 | 3.0 | 171 | 0.6680 | 0.1893 | 0.2234 |
71
- | 0.0668 | 4.0 | 228 | 0.7255 | 0.2145 | 0.2436 |
72
- | 0.0222 | 5.0 | 285 | 0.7556 | 0.2429 | 0.2826 |
73
- | 0.0115 | 6.0 | 342 | 0.7887 | 0.2145 | 0.2537 |
74
- | 0.0076 | 7.0 | 399 | 0.7913 | 0.2280 | 0.2591 |
75
- | 0.003 | 8.0 | 456 | 0.8279 | 0.2642 | 0.3015 |
76
- | 0.001 | 9.0 | 513 | 0.8377 | 0.2048 | 0.2470 |
77
- | 0.0012 | 10.0 | 570 | 0.8281 | 0.1957 | 0.2450 |
78
- | 0.0006 | 11.0 | 627 | 0.8269 | 0.1867 | 0.2362 |
79
- | 0.0003 | 12.0 | 684 | 0.8332 | 0.1867 | 0.2355 |
80
- | 0.1651 | 13.0 | 741 | 0.1350 | 0.1212 | 0.1807 |
81
- | 0.061 | 14.0 | 798 | 0.1365 | 0.1078 | 0.1539 |
82
- | 0.0353 | 15.0 | 855 | 0.1371 | 0.1052 | 0.1544 |
83
 
84
 
85
  ### Framework versions
 
20
  metrics:
21
  - name: Wer
22
  type: wer
23
+ value: 0.09080525414049115
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
32
  It achieves the following results on the evaluation set:
33
+ - Loss: 0.1314
34
+ - Wer Ortho: 0.1507
35
+ - Wer: 0.0908
36
 
37
  ## Model description
38
 
 
63
 
64
  ### Training results
65
 
66
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
67
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
68
+ | 0.0443 | 1.0 | 57 | 0.0811 | 0.1175 | 0.0680 |
69
+ | 0.0262 | 2.0 | 114 | 0.1065 | 0.1454 | 0.0977 |
70
+ | 0.0409 | 3.0 | 171 | 0.1275 | 0.1074 | 0.0748 |
71
+ | 0.0204 | 4.0 | 228 | 0.1301 | 0.1371 | 0.1057 |
72
+ | 0.0095 | 5.0 | 285 | 0.1293 | 0.1982 | 0.1605 |
73
+ | 0.0071 | 6.0 | 342 | 0.1422 | 0.1822 | 0.1365 |
74
+ | 0.0011 | 7.0 | 399 | 0.1329 | 0.1448 | 0.0982 |
75
+ | 0.0049 | 8.0 | 456 | 0.1294 | 0.1359 | 0.0788 |
76
+ | 0.0012 | 9.0 | 513 | 0.1296 | 0.1478 | 0.0891 |
77
+ | 0.0002 | 10.0 | 570 | 0.1305 | 0.1484 | 0.0891 |
78
+ | 0.0013 | 11.0 | 627 | 0.1298 | 0.1490 | 0.0897 |
79
+ | 0.0002 | 12.0 | 684 | 0.1309 | 0.1490 | 0.0891 |
80
+ | 0.0004 | 13.0 | 741 | 0.1311 | 0.1513 | 0.0914 |
81
+ | 0.0001 | 14.0 | 798 | 0.1313 | 0.1507 | 0.0908 |
82
+ | 0.0001 | 15.0 | 855 | 0.1314 | 0.1507 | 0.0908 |
83
 
84
 
85
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f4637a47c562779e6bcb904a6c543e755c67da53fb70a39b2f079358f098d42
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ced4244a7ba07c27df9925f5901a8ec7327aa602c6285cf0d67f6f1c80b794
3
  size 151061672