Hugging Face's logo

Baselhany
/
Distilation_Whisper_base_CKP

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
Baselhany commited on
Commit
32df7b7
·
verified ·
1 Parent(s): 0e71205

Model save

Browse files
Files changed (3) hide show
  1. README.md +26 -95
  2. model.safetensors +1 -1
  3. runs/Jun01_21-55-56_8205cfdf9d1f/events.out.tfevents.1748834414.8205cfdf9d1f.19.1 +3 -0
README.md CHANGED
@@ -1,27 +1,25 @@
1
  ---
2
  library_name: transformers
3
- language:
4
- - ar
5
  license: apache-2.0
6
- base_model: openai/whisper-base
7
  tags:
8
  - generated_from_trainer
9
  metrics:
10
  - wer
11
  model-index:
12
- - name: Whisper base AR - BA
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # Whisper base AR - BA
20
 
21
- This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0897
24
- - Wer: 0.1988
25
 
26
  ## Model description
27
 
@@ -49,97 +47,30 @@ The following hyperparameters were used during training:
49
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: linear
51
  - lr_scheduler_warmup_steps: 500
52
- - num_epochs: 20
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | Wer |
58
- |:-------------:|:-------:|:-----:|:---------------:|:------:|
59
- | 2.9866 | 0.2371 | 400 | 0.1061 | 0.2197 |
60
- | 3.6342 | 0.4742 | 800 | 0.1022 | 0.2051 |
61
- | 3.2101 | 0.7113 | 1200 | 0.1011 | 0.2044 |
62
- | 3.3175 | 0.9484 | 1600 | 0.1018 | 0.2042 |
63
- | 2.5835 | 1.1855 | 2000 | 0.0999 | 0.1982 |
64
- | 2.6437 | 1.4226 | 2400 | 0.0986 | 0.1979 |
65
- | 2.4359 | 1.6598 | 2800 | 0.0976 | 0.1976 |
66
- | 2.5958 | 1.8969 | 3200 | 0.0967 | 0.2090 |
67
- | 2.0623 | 2.1340 | 3600 | 0.0954 | 0.1942 |
68
- | 1.8728 | 2.3711 | 4000 | 0.0946 | 0.1895 |
69
- | 2.1926 | 2.6082 | 4400 | 0.0979 | 0.1958 |
70
- | 1.9814 | 2.8453 | 4800 | 0.0968 | 0.1973 |
71
- | 1.7723 | 3.0824 | 5200 | 0.0940 | 0.2020 |
72
- | 1.7258 | 3.3195 | 5600 | 0.0939 | 0.1954 |
73
- | 1.6528 | 3.5566 | 6000 | 0.0940 | 0.1951 |
74
- | 1.6309 | 3.7937 | 6400 | 0.0920 | 0.1985 |
75
- | 1.4672 | 4.0308 | 6800 | 0.0927 | 0.1961 |
76
- | 1.4974 | 4.2679 | 7200 | 0.0920 | 0.1954 |
77
- | 1.3805 | 4.5050 | 7600 | 0.0933 | 0.1929 |
78
- | 1.5116 | 4.7421 | 8000 | 0.0918 | 0.1955 |
79
- | 1.4897 | 4.9793 | 8400 | 0.0909 | 0.1917 |
80
- | 1.3287 | 5.2164 | 8800 | 0.0901 | 0.1942 |
81
- | 1.3186 | 5.4535 | 9200 | 0.0904 | 0.1944 |
82
- | 1.3753 | 5.6906 | 9600 | 0.0911 | 0.1941 |
83
- | 1.3055 | 5.9277 | 10000 | 0.0907 | 0.1920 |
84
- | 1.2468 | 6.1648 | 10400 | 0.0904 | 0.1982 |
85
- | 1.183 | 6.4019 | 10800 | 0.0894 | 0.1944 |
86
- | 1.2316 | 6.6390 | 11200 | 0.0911 | 0.1986 |
87
- | 1.2264 | 6.8761 | 11600 | 0.0901 | 0.1950 |
88
- | 1.2133 | 7.1132 | 12000 | 0.0904 | 0.1988 |
89
- | 1.1362 | 7.3503 | 12400 | 0.0899 | 0.2034 |
90
- | 1.162 | 7.5874 | 12800 | 0.0899 | 0.1985 |
91
- | 1.1639 | 7.8245 | 13200 | 0.0904 | 0.1948 |
92
- | 1.0533 | 8.0616 | 13600 | 0.0891 | 0.1948 |
93
- | 1.1351 | 8.2988 | 14000 | 0.0895 | 0.1967 |
94
- | 1.1125 | 8.5359 | 14400 | 0.0893 | 0.2047 |
95
- | 1.1177 | 8.7730 | 14800 | 0.0890 | 0.2020 |
96
- | 1.0468 | 9.0101 | 15200 | 0.0891 | 0.2020 |
97
- | 1.0404 | 9.2472 | 15600 | 0.0890 | 0.2069 |
98
- | 1.073 | 9.4843 | 16000 | 0.0892 | 0.1975 |
99
- | 1.0436 | 9.7214 | 16400 | 0.0888 | 0.1981 |
100
- | 1.0786 | 9.9585 | 16800 | 0.0889 | 0.1972 |
101
- | 1.1565 | 10.1956 | 17200 | 0.0886 | 0.2019 |
102
- | 1.0682 | 10.4327 | 17600 | 0.0898 | 0.1966 |
103
- | 1.1408 | 10.6698 | 18000 | 0.0885 | 0.2010 |
104
- | 1.0517 | 10.9069 | 18400 | 0.0891 | 0.2019 |
105
- | 1.0097 | 11.1440 | 18800 | 0.0885 | 0.1950 |
106
- | 1.0962 | 11.3811 | 19200 | 0.0890 | 0.2004 |
107
- | 1.0616 | 11.6183 | 19600 | 0.0890 | 0.1975 |
108
- | 1.1527 | 11.8554 | 20000 | 0.0896 | 0.1963 |
109
- | 1.0396 | 12.0925 | 20400 | 0.0885 | 0.2029 |
110
- | 0.9842 | 12.3296 | 20800 | 0.0885 | 0.1917 |
111
- | 1.0012 | 12.5667 | 21200 | 0.0885 | 0.1973 |
112
- | 0.941 | 12.8038 | 21600 | 0.0881 | 0.2010 |
113
- | 0.9645 | 13.0409 | 22000 | 0.0879 | 0.2025 |
114
- | 0.9253 | 13.2780 | 22400 | 0.0884 | 0.1986 |
115
- | 0.946 | 13.5151 | 22800 | 0.0882 | 0.1954 |
116
- | 0.9513 | 13.7522 | 23200 | 0.0884 | 0.1957 |
117
- | 0.9912 | 13.9893 | 23600 | 0.0876 | 0.2010 |
118
- | 0.9332 | 14.2264 | 24000 | 0.0878 | 0.1992 |
119
- | 0.9282 | 14.4635 | 24400 | 0.0880 | 0.2025 |
120
- | 0.922 | 14.7007 | 24800 | 0.0880 | 0.2009 |
121
- | 0.8976 | 14.9378 | 25200 | 0.0878 | 0.2016 |
122
- | 0.9299 | 15.1749 | 25600 | 0.0885 | 0.2025 |
123
- | 0.9786 | 15.4120 | 26000 | 0.0878 | 0.1992 |
124
- | 0.992 | 15.6491 | 26400 | 0.0885 | 0.2017 |
125
- | 1.002 | 15.8862 | 26800 | 0.0880 | 0.1978 |
126
- | 0.9183 | 16.1233 | 27200 | 0.0882 | 0.2031 |
127
- | 0.9715 | 16.3604 | 27600 | 0.0883 | 0.2050 |
128
- | 0.8899 | 16.5975 | 28000 | 0.0881 | 0.2023 |
129
- | 0.9589 | 16.8346 | 28400 | 0.0880 | 0.2006 |
130
- | 0.8958 | 17.0717 | 28800 | 0.0881 | 0.1981 |
131
- | 0.9416 | 17.3088 | 29200 | 0.0875 | 0.1992 |
132
- | 0.8884 | 17.5459 | 29600 | 0.0877 | 0.1998 |
133
- | 0.8735 | 17.7830 | 30000 | 0.0873 | 0.1948 |
134
- | 0.9706 | 18.0202 | 30400 | 0.0876 | 0.1933 |
135
- | 0.8571 | 18.2573 | 30800 | 0.0872 | 0.1982 |
136
- | 0.913 | 18.4944 | 31200 | 0.0871 | 0.1986 |
137
- | 0.9239 | 18.7315 | 31600 | 0.0872 | 0.1948 |
138
- | 0.8846 | 18.9686 | 32000 | 0.0875 | 0.2001 |
139
- | 0.8666 | 19.2057 | 32400 | 0.0873 | 0.2009 |
140
- | 0.8834 | 19.4428 | 32800 | 0.0874 | 0.1981 |
141
- | 0.8454 | 19.6799 | 33200 | 0.0873 | 0.1979 |
142
- | 0.8416 | 19.9170 | 33600 | 0.0872 | 0.2003 |
143
 
144
 
145
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  license: apache-2.0
4
+ base_model: Baselhany/Distilation_Whisper_base_CKP
5
  tags:
6
  - generated_from_trainer
7
  metrics:
8
  - wer
9
  model-index:
10
+ - name: Distilation_Whisper_base_CKP
11
  results: []
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
+ # Distilation_Whisper_base_CKP
18
 
19
+ This model is a fine-tuned version of [Baselhany/Distilation_Whisper_base_CKP](https://huggingface.co/Baselhany/Distilation_Whisper_base_CKP) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0870
22
+ - Wer: 0.1935
23
 
24
  ## Model description
25
 
 
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
  - lr_scheduler_warmup_steps: 500
50
+ - num_epochs: 10
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:------:|:-----:|:---------------:|:------:|
57
+ | 2.1291 | 0.5858 | 1000 | 0.0912 | 0.1978 |
58
+ | 1.7057 | 1.1716 | 2000 | 0.0912 | 0.2003 |
59
+ | 1.7162 | 1.7575 | 3000 | 0.0912 | 0.2060 |
60
+ | 1.4996 | 2.3433 | 4000 | 0.0901 | 0.2047 |
61
+ | 1.3942 | 2.9291 | 5000 | 0.0883 | 0.1951 |
62
+ | 1.2285 | 3.5149 | 6000 | 0.0876 | 0.1957 |
63
+ | 1.0637 | 4.1008 | 7000 | 0.0873 | 0.1920 |
64
+ | 1.1144 | 4.6866 | 8000 | 0.0865 | 0.1927 |
65
+ | 1.0164 | 5.2724 | 9000 | 0.0858 | 0.1923 |
66
+ | 0.9812 | 5.8582 | 10000 | 0.0856 | 0.1941 |
67
+ | 0.8927 | 6.4441 | 11000 | 0.0849 | 0.2017 |
68
+ | 0.8936 | 7.0299 | 12000 | 0.0844 | 0.1961 |
69
+ | 0.8718 | 7.6157 | 13000 | 0.0854 | 0.1979 |
70
+ | 0.9019 | 8.2015 | 14000 | 0.0847 | 0.1854 |
71
+ | 0.8293 | 8.7873 | 15000 | 0.0847 | 0.1983 |
72
+ | 0.8363 | 9.3732 | 16000 | 0.0842 | 0.1982 |
73
+ | 0.8034 | 9.9590 | 17000 | 0.0840 | 0.1975 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf29b318c3b664e026f2d7eeee5f490c11ed0e0a4f94588f656f978ca6f13931
3
  size 223144592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04f91bc09632d0ca44900fee5a57b22786f0ffd1c54b0da4556e61fa28621f2f
3
  size 223144592
runs/Jun01_21-55-56_8205cfdf9d1f/events.out.tfevents.1748834414.8205cfdf9d1f.19.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77a1c9d71f6a016022be9d89d58d03e54c3758f8806d7a0af27212e0374a6c7f
3
+ size 412