Hugging Face's logo

ptah23
/
whisper-tiny-en-US

Automatic Speech Recognition
Transformers
PyTorch
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
ptah23 commited on
Commit
3513e6a
·
1 Parent(s): 85b2769

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +48 -16
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.20146619603584034
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.6756
36
- - Wer Ortho: 0.2044
37
- - Wer: 0.2015
38
 
39
  ## Model description
40
 
@@ -59,21 +59,53 @@ The following hyperparameters were used during training:
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: constant_with_warmup
62
- - lr_scheduler_warmup_steps: 50
63
- - training_steps: 4000
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
68
- |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|
69
- | 0.0007 | 17.86 | 500 | 0.5138 | 0.1941 | 0.1920 |
70
- | 0.0002 | 35.71 | 1000 | 0.5565 | 0.1958 | 0.1936 |
71
- | 0.0001 | 53.57 | 1500 | 0.5851 | 0.1981 | 0.1958 |
72
- | 0.0001 | 71.43 | 2000 | 0.6081 | 0.2030 | 0.1998 |
73
- | 0.0 | 89.29 | 2500 | 0.6273 | 0.2038 | 0.2009 |
74
- | 0.0 | 107.14 | 3000 | 0.6441 | 0.2021 | 0.1996 |
75
- | 0.0 | 125.0 | 3500 | 0.6602 | 0.2035 | 0.2007 |
76
- | 0.0 | 142.86 | 4000 | 0.6756 | 0.2044 | 0.2015 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
 
78
 
79
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.19386369807222373
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.5874
36
+ - Wer Ortho: 0.1978
37
+ - Wer: 0.1939
38
 
39
  ## Model description
40
 
 
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: constant_with_warmup
62
+ - lr_scheduler_warmup_steps: 5
63
+ - training_steps: 400
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
68
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
69
+ | No log | 0.36 | 10 | 0.5445 | 0.1970 | 0.1930 |
70
+ | No log | 0.71 | 20 | 0.5571 | 0.1973 | 0.1939 |
71
+ | 0.0009 | 1.07 | 30 | 0.5571 | 0.1981 | 0.1936 |
72
+ | 0.0009 | 1.43 | 40 | 0.5535 | 0.1958 | 0.1920 |
73
+ | 0.0024 | 1.79 | 50 | 0.5568 | 0.1967 | 0.1930 |
74
+ | 0.0024 | 2.14 | 60 | 0.5679 | 0.2024 | 0.1996 |
75
+ | 0.0024 | 2.5 | 70 | 0.5574 | 0.1970 | 0.1944 |
76
+ | 0.0019 | 2.86 | 80 | 0.5454 | 0.1956 | 0.1936 |
77
+ | 0.0019 | 3.21 | 90 | 0.5541 | 0.2044 | 0.1982 |
78
+ | 0.0043 | 3.57 | 100 | 0.5330 | 0.1998 | 0.1936 |
79
+ | 0.0043 | 3.93 | 110 | 0.5524 | 0.1981 | 0.1958 |
80
+ | 0.0043 | 4.29 | 120 | 0.5482 | 0.1958 | 0.1933 |
81
+ | 0.0043 | 4.64 | 130 | 0.5554 | 0.1984 | 0.1952 |
82
+ | 0.0043 | 5.0 | 140 | 0.5634 | 0.1998 | 0.1949 |
83
+ | 0.001 | 5.36 | 150 | 0.5526 | 0.1990 | 0.1930 |
84
+ | 0.001 | 5.71 | 160 | 0.5511 | 0.1973 | 0.1920 |
85
+ | 0.001 | 6.07 | 170 | 0.5548 | 0.1953 | 0.1917 |
86
+ | 0.0006 | 6.43 | 180 | 0.5589 | 0.2047 | 0.1998 |
87
+ | 0.0006 | 6.79 | 190 | 0.5657 | 0.2027 | 0.1982 |
88
+ | 0.0004 | 7.14 | 200 | 0.5686 | 0.1961 | 0.1933 |
89
+ | 0.0004 | 7.5 | 210 | 0.5714 | 0.1944 | 0.1911 |
90
+ | 0.0004 | 7.86 | 220 | 0.5710 | 0.1976 | 0.1941 |
91
+ | 0.0002 | 8.21 | 230 | 0.5656 | 0.1973 | 0.1925 |
92
+ | 0.0002 | 8.57 | 240 | 0.5661 | 0.1981 | 0.1928 |
93
+ | 0.0001 | 8.93 | 250 | 0.5688 | 0.1984 | 0.1930 |
94
+ | 0.0001 | 9.29 | 260 | 0.5720 | 0.1967 | 0.1920 |
95
+ | 0.0001 | 9.64 | 270 | 0.5745 | 0.1970 | 0.1930 |
96
+ | 0.0001 | 10.0 | 280 | 0.5758 | 0.1964 | 0.1925 |
97
+ | 0.0001 | 10.36 | 290 | 0.5767 | 0.1970 | 0.1930 |
98
+ | 0.0001 | 10.71 | 300 | 0.5780 | 0.1978 | 0.1941 |
99
+ | 0.0001 | 11.07 | 310 | 0.5793 | 0.1978 | 0.1941 |
100
+ | 0.0001 | 11.43 | 320 | 0.5803 | 0.1976 | 0.1939 |
101
+ | 0.0001 | 11.79 | 330 | 0.5815 | 0.1973 | 0.1933 |
102
+ | 0.0001 | 12.14 | 340 | 0.5824 | 0.1973 | 0.1933 |
103
+ | 0.0001 | 12.5 | 350 | 0.5833 | 0.1973 | 0.1933 |
104
+ | 0.0001 | 12.86 | 360 | 0.5843 | 0.1970 | 0.1933 |
105
+ | 0.0001 | 13.21 | 370 | 0.5850 | 0.1976 | 0.1936 |
106
+ | 0.0001 | 13.57 | 380 | 0.5856 | 0.1978 | 0.1939 |
107
+ | 0.0001 | 13.93 | 390 | 0.5865 | 0.1978 | 0.1939 |
108
+ | 0.0001 | 14.29 | 400 | 0.5874 | 0.1978 | 0.1939 |
109
 
110
 
111
  ### Framework versions