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
64f229f
·
verified ·
1 Parent(s): 87038cc

Model save

Browse files
Files changed (2) hide show
  1. README.md +51 -63
  2. runs/May24_13-09-04_1386259d94b5/events.out.tfevents.1748116376.1386259d94b5.19.1 +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: 0.1024
24
- - Wer: 0.2232
25
 
26
  ## Model description
27
 
@@ -49,65 +47,55 @@ 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: 15
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | Wer |
58
- |:-------------:|:-------:|:-----:|:---------------:|:------:|
59
- | 46.3716 | 0.2851 | 400 | 0.1697 | 0.6098 |
60
- | 16.3386 | 0.5701 | 800 | 0.1358 | 0.3553 |
61
- | 11.9313 | 0.8552 | 1200 | 0.1236 | 0.3021 |
62
- | 8.1383 | 1.1397 | 1600 | 0.1211 | 0.2676 |
63
- | 6.2069 | 1.4247 | 2000 | 0.1188 | 0.2626 |
64
- | 5.6497 | 1.7098 | 2400 | 0.1146 | 0.2371 |
65
- | 5.2035 | 1.9948 | 2800 | 0.1113 | 0.2395 |
66
- | 4.7207 | 2.2794 | 3200 | 0.1112 | 0.2258 |
67
- | 4.1488 | 2.5644 | 3600 | 0.1108 | 0.2389 |
68
- | 4.0903 | 2.8495 | 4000 | 0.1094 | 0.2219 |
69
- | 4.2814 | 3.1361 | 4400 | 0.1135 | 0.2302 |
70
- | 4.0634 | 3.4212 | 4800 | 0.1100 | 0.2300 |
71
- | 3.8832 | 3.7062 | 5200 | 0.1101 | 0.2203 |
72
- | 4.0159 | 3.9913 | 5600 | 0.1073 | 0.2238 |
73
- | 3.1347 | 4.2758 | 6000 | 0.1089 | 0.2230 |
74
- | 3.4745 | 4.5608 | 6400 | 0.1049 | 0.2140 |
75
- | 3.1785 | 4.8459 | 6800 | 0.1070 | 0.2119 |
76
- | 2.8142 | 5.1304 | 7200 | 0.1034 | 0.2094 |
77
- | 2.6992 | 5.4155 | 7600 | 0.1051 | 0.2149 |
78
- | 2.5099 | 5.7005 | 8000 | 0.1071 | 0.2203 |
79
- | 2.4995 | 5.9856 | 8400 | 0.1032 | 0.2216 |
80
- | 2.1725 | 6.2701 | 8800 | 0.1032 | 0.2318 |
81
- | 2.171 | 6.5551 | 9200 | 0.1023 | 0.2187 |
82
- | 2.3072 | 6.8402 | 9600 | 0.1019 | 0.2191 |
83
- | 1.9543 | 7.1247 | 10000 | 0.1028 | 0.2119 |
84
- | 2.0848 | 7.4098 | 10400 | 0.1017 | 0.2112 |
85
- | 1.9636 | 7.6948 | 10800 | 0.1020 | 0.2159 |
86
- | 1.9283 | 7.9799 | 11200 | 0.1010 | 0.2131 |
87
- | 1.8101 | 8.2644 | 11600 | 0.1010 | 0.2107 |
88
- | 1.9462 | 8.5494 | 12000 | 0.1010 | 0.2137 |
89
- | 1.9585 | 8.8345 | 12400 | 0.1006 | 0.2151 |
90
- | 1.6228 | 9.1190 | 12800 | 0.1005 | 0.2160 |
91
- | 1.7241 | 9.4041 | 13200 | 0.0999 | 0.2218 |
92
- | 1.7732 | 9.6891 | 13600 | 0.1001 | 0.2163 |
93
- | 1.6427 | 9.9742 | 14000 | 0.1001 | 0.2157 |
94
- | 1.6996 | 10.2637 | 14400 | 0.1009 | 0.2200 |
95
- | 1.7166 | 10.5487 | 14800 | 0.1010 | 0.2123 |
96
- | 1.8227 | 10.8338 | 15200 | 0.1000 | 0.2171 |
97
- | 1.7927 | 11.1183 | 15600 | 0.1001 | 0.2188 |
98
- | 1.6751 | 11.4033 | 16000 | 0.0995 | 0.2196 |
99
- | 1.5983 | 11.6884 | 16400 | 0.0995 | 0.2045 |
100
- | 1.6088 | 11.9735 | 16800 | 0.0988 | 0.2135 |
101
- | 1.5573 | 12.2580 | 17200 | 0.0983 | 0.2100 |
102
- | 1.5286 | 12.5430 | 17600 | 0.0998 | 0.2122 |
103
- | 1.6379 | 12.8281 | 18000 | 0.0981 | 0.2115 |
104
- | 1.3574 | 13.1126 | 18400 | 0.0980 | 0.2078 |
105
- | 1.3832 | 13.3976 | 18800 | 0.0988 | 0.2100 |
106
- | 1.3473 | 13.6827 | 19200 | 0.0983 | 0.2047 |
107
- | 1.5205 | 13.9678 | 19600 | 0.0986 | 0.2119 |
108
- | 1.415 | 14.2523 | 20000 | 0.0982 | 0.2128 |
109
- | 1.4434 | 14.5373 | 20400 | 0.0982 | 0.2113 |
110
- | 1.3422 | 14.8224 | 20800 | 0.0981 | 0.2109 |
111
 
112
 
113
  ### 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: 0.0912
22
+ - Wer: 0.1977
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
+ | 2.9866 | 0.2371 | 400 | 0.1061 | 0.2197 |
58
+ | 3.6342 | 0.4742 | 800 | 0.1022 | 0.2051 |
59
+ | 3.2101 | 0.7113 | 1200 | 0.1011 | 0.2044 |
60
+ | 3.3175 | 0.9484 | 1600 | 0.1018 | 0.2042 |
61
+ | 2.5835 | 1.1855 | 2000 | 0.0999 | 0.1982 |
62
+ | 2.6437 | 1.4226 | 2400 | 0.0986 | 0.1979 |
63
+ | 2.4359 | 1.6598 | 2800 | 0.0976 | 0.1976 |
64
+ | 2.5958 | 1.8969 | 3200 | 0.0967 | 0.2090 |
65
+ | 2.0623 | 2.1340 | 3600 | 0.0954 | 0.1942 |
66
+ | 1.8728 | 2.3711 | 4000 | 0.0946 | 0.1895 |
67
+ | 2.1926 | 2.6082 | 4400 | 0.0979 | 0.1958 |
68
+ | 1.9814 | 2.8453 | 4800 | 0.0968 | 0.1973 |
69
+ | 1.7723 | 3.0824 | 5200 | 0.0940 | 0.2020 |
70
+ | 1.7258 | 3.3195 | 5600 | 0.0939 | 0.1954 |
71
+ | 1.6528 | 3.5566 | 6000 | 0.0940 | 0.1951 |
72
+ | 1.6309 | 3.7937 | 6400 | 0.0920 | 0.1985 |
73
+ | 1.4672 | 4.0308 | 6800 | 0.0927 | 0.1961 |
74
+ | 1.4974 | 4.2679 | 7200 | 0.0920 | 0.1954 |
75
+ | 1.3805 | 4.5050 | 7600 | 0.0933 | 0.1929 |
76
+ | 1.5116 | 4.7421 | 8000 | 0.0918 | 0.1955 |
77
+ | 1.4897 | 4.9793 | 8400 | 0.0909 | 0.1917 |
78
+ | 1.3287 | 5.2164 | 8800 | 0.0901 | 0.1942 |
79
+ | 1.3186 | 5.4535 | 9200 | 0.0904 | 0.1944 |
80
+ | 1.3753 | 5.6906 | 9600 | 0.0911 | 0.1941 |
81
+ | 1.3055 | 5.9277 | 10000 | 0.0907 | 0.1920 |
82
+ | 1.2468 | 6.1648 | 10400 | 0.0904 | 0.1982 |
83
+ | 1.183 | 6.4019 | 10800 | 0.0894 | 0.1944 |
84
+ | 1.2316 | 6.6390 | 11200 | 0.0911 | 0.1986 |
85
+ | 1.2264 | 6.8761 | 11600 | 0.0901 | 0.1950 |
86
+ | 1.2133 | 7.1132 | 12000 | 0.0904 | 0.1988 |
87
+ | 1.1362 | 7.3503 | 12400 | 0.0899 | 0.2034 |
88
+ | 1.162 | 7.5874 | 12800 | 0.0899 | 0.1985 |
89
+ | 1.1639 | 7.8245 | 13200 | 0.0904 | 0.1948 |
90
+ | 1.0533 | 8.0616 | 13600 | 0.0891 | 0.1948 |
91
+ | 1.1351 | 8.2988 | 14000 | 0.0895 | 0.1967 |
92
+ | 1.1125 | 8.5359 | 14400 | 0.0893 | 0.2047 |
93
+ | 1.1177 | 8.7730 | 14800 | 0.0890 | 0.2020 |
94
+ | 1.0468 | 9.0101 | 15200 | 0.0891 | 0.2020 |
95
+ | 1.0404 | 9.2472 | 15600 | 0.0890 | 0.2069 |
96
+ | 1.073 | 9.4843 | 16000 | 0.0892 | 0.1975 |
97
+ | 1.0436 | 9.7214 | 16400 | 0.0888 | 0.1981 |
98
+ | 1.0786 | 9.9585 | 16800 | 0.0889 | 0.1972 |
 
 
 
 
 
 
 
 
 
 
99
 
100
 
101
  ### Framework versions
runs/May24_13-09-04_1386259d94b5/events.out.tfevents.1748116376.1386259d94b5.19.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4c3b2c297005c0f2a0206a8d3b998494c3b9ac93e276bf5d62477ea9218941c
3
+ size 412