patrickvonplaten commited on
Commit
edf6414
1 Parent(s): 53c1de1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -32
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  tags:
3
  - automatic-speech-recognition
4
  - timit_asr
@@ -15,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # distilhubert-timit
17
 
18
- This model is a fine-tuned version of [anton-l/distilhubert](https://huggingface.co/anton-l/distilhubert) on the TIMIT_ASR - NA dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.3688
21
- - Wer: 0.6818
22
 
23
  ## Model description
24
 
@@ -51,35 +52,35 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|
54
- | 4.2247 | 0.69 | 100 | 3.8607 | 1.0 |
55
- | 2.9444 | 1.38 | 200 | 2.9509 | 1.0 |
56
- | 2.8858 | 2.07 | 300 | 2.8446 | 1.0 |
57
- | 2.2804 | 2.76 | 400 | 2.1985 | 1.0014 |
58
- | 1.505 | 3.45 | 500 | 1.4972 | 0.9609 |
59
- | 1.06 | 4.14 | 600 | 1.2014 | 0.8058 |
60
- | 1.0166 | 4.83 | 700 | 1.0605 | 0.7536 |
61
- | 0.966 | 5.52 | 800 | 0.9963 | 0.7101 |
62
- | 0.6857 | 6.21 | 900 | 0.9443 | 0.6898 |
63
- | 0.5859 | 6.9 | 1000 | 0.9043 | 0.6796 |
64
- | 0.6812 | 7.59 | 1100 | 0.9095 | 0.6716 |
65
- | 0.6088 | 8.28 | 1200 | 0.9422 | 0.6677 |
66
- | 0.4162 | 8.97 | 1300 | 0.9548 | 0.6657 |
67
- | 0.3411 | 9.66 | 1400 | 0.9901 | 0.6689 |
68
- | 0.3323 | 10.34 | 1500 | 0.9996 | 0.6638 |
69
- | 0.431 | 11.03 | 1600 | 1.0521 | 0.6708 |
70
- | 0.2029 | 11.72 | 1700 | 1.0946 | 0.6793 |
71
- | 0.1424 | 12.41 | 1800 | 1.1288 | 0.6712 |
72
- | 0.1922 | 13.1 | 1900 | 1.1456 | 0.6740 |
73
- | 0.326 | 13.79 | 2000 | 1.2077 | 0.6915 |
74
- | 0.0892 | 14.48 | 2100 | 1.2525 | 0.6796 |
75
- | 0.0769 | 15.17 | 2200 | 1.2313 | 0.6736 |
76
- | 0.0927 | 15.86 | 2300 | 1.3001 | 0.6864 |
77
- | 0.232 | 16.55 | 2400 | 1.3490 | 0.6963 |
78
- | 0.0485 | 17.24 | 2500 | 1.3268 | 0.6763 |
79
- | 0.0487 | 17.93 | 2600 | 1.3376 | 0.6780 |
80
- | 0.0607 | 18.62 | 2700 | 1.3701 | 0.6895 |
81
- | 0.1618 | 19.31 | 2800 | 1.3657 | 0.6796 |
82
- | 0.0415 | 20.0 | 2900 | 1.3688 | 0.6818 |
83
 
84
 
85
  ### Framework versions
1
  ---
2
+ license: apache-2.0
3
  tags:
4
  - automatic-speech-recognition
5
  - timit_asr
16
 
17
  # distilhubert-timit
18
 
19
+ This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the TIMIT_ASR - NA dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.3601
22
+ - Wer: 0.6776
23
 
24
  ## Model description
25
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | 5.4447 | 0.69 | 100 | 4.9546 | 1.0 |
56
+ | 2.9499 | 1.38 | 200 | 2.9519 | 1.0 |
57
+ | 2.8989 | 2.07 | 300 | 2.8624 | 1.0 |
58
+ | 2.2076 | 2.76 | 400 | 2.1089 | 1.0008 |
59
+ | 1.4186 | 3.45 | 500 | 1.4112 | 0.9165 |
60
+ | 0.9951 | 4.14 | 600 | 1.1378 | 0.7701 |
61
+ | 0.9754 | 4.83 | 700 | 1.0152 | 0.7274 |
62
+ | 0.9364 | 5.52 | 800 | 0.9619 | 0.7011 |
63
+ | 0.6557 | 6.21 | 900 | 0.9144 | 0.6868 |
64
+ | 0.5681 | 6.9 | 1000 | 0.8899 | 0.6683 |
65
+ | 0.66 | 7.59 | 1100 | 0.8992 | 0.6654 |
66
+ | 0.6144 | 8.28 | 1200 | 0.9299 | 0.6898 |
67
+ | 0.4099 | 8.97 | 1300 | 0.9510 | 0.6674 |
68
+ | 0.3384 | 9.66 | 1400 | 0.9598 | 0.6612 |
69
+ | 0.3163 | 10.34 | 1500 | 0.9954 | 0.6612 |
70
+ | 0.4204 | 11.03 | 1600 | 1.0164 | 0.6607 |
71
+ | 0.1932 | 11.72 | 1700 | 1.0637 | 0.6658 |
72
+ | 0.1449 | 12.41 | 1800 | 1.1190 | 0.6652 |
73
+ | 0.1803 | 13.1 | 1900 | 1.1260 | 0.6689 |
74
+ | 0.328 | 13.79 | 2000 | 1.2186 | 0.6751 |
75
+ | 0.0838 | 14.48 | 2100 | 1.2591 | 0.6909 |
76
+ | 0.0766 | 15.17 | 2200 | 1.2529 | 0.6780 |
77
+ | 0.0956 | 15.86 | 2300 | 1.2537 | 0.6668 |
78
+ | 0.2339 | 16.55 | 2400 | 1.3210 | 0.6797 |
79
+ | 0.0431 | 17.24 | 2500 | 1.3241 | 0.6781 |
80
+ | 0.0508 | 17.93 | 2600 | 1.3184 | 0.6683 |
81
+ | 0.0616 | 18.62 | 2700 | 1.3728 | 0.6889 |
82
+ | 0.1608 | 19.31 | 2800 | 1.3572 | 0.6771 |
83
+ | 0.0378 | 20.0 | 2900 | 1.3601 | 0.6776 |
84
 
85
 
86
  ### Framework versions