Hugging Face's logo

Baselhany
/
Distilation_Whisper_base_CKP2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
Baselhany commited on
Commit
be26996
·
verified ·
1 Parent(s): 97e2d35

Model save

Browse files
Files changed (4) hide show
  1. README.md +68 -46
  2. generation_config.json +1 -14
  3. model.safetensors +1 -1
  4. runs/May23_23-59-44_7cd4622fd13c/events.out.tfevents.1748083266.7cd4622fd13c.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: 0.1003
24
- - Wer: 0.2163
25
 
26
  ## Model description
27
 
@@ -49,48 +47,72 @@ 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: 10
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
- | 16.3556 | 0.5701 | 800 | 0.1355 | 0.3556 |
61
- | 11.9327 | 0.8552 | 1200 | 0.1230 | 0.3000 |
62
- | 8.1222 | 1.1397 | 1600 | 0.1196 | 0.2543 |
63
- | 6.2775 | 1.4247 | 2000 | 0.1165 | 0.2619 |
64
- | 5.6861 | 1.7098 | 2400 | 0.1143 | 0.2390 |
65
- | 5.238 | 1.9948 | 2800 | 0.1115 | 0.2346 |
66
- | 4.5097 | 2.2794 | 3200 | 0.1107 | 0.2256 |
67
- | 3.9677 | 2.5644 | 3600 | 0.1095 | 0.2262 |
68
- | 3.8998 | 2.8495 | 4000 | 0.1085 | 0.2300 |
69
- | 3.3351 | 3.1340 | 4400 | 0.1067 | 0.2140 |
70
- | 3.1317 | 3.4190 | 4800 | 0.1067 | 0.2199 |
71
- | 2.9814 | 3.7041 | 5200 | 0.1046 | 0.2119 |
72
- | 3.167 | 3.9891 | 5600 | 0.1039 | 0.2104 |
73
- | 2.498 | 4.2737 | 6000 | 0.1066 | 0.2177 |
74
- | 2.8372 | 4.5587 | 6400 | 0.1022 | 0.2098 |
75
- | 2.5573 | 4.8438 | 6800 | 0.1028 | 0.2181 |
76
- | 2.3309 | 5.1283 | 7200 | 0.1006 | 0.2091 |
77
- | 2.2589 | 5.4133 | 7600 | 0.1015 | 0.2100 |
78
- | 2.1409 | 5.6984 | 8000 | 0.1024 | 0.2065 |
79
- | 2.1048 | 5.9834 | 8400 | 0.0992 | 0.2138 |
80
- | 1.8826 | 6.2679 | 8800 | 0.0987 | 0.2116 |
81
- | 1.8778 | 6.5530 | 9200 | 0.0988 | 0.2073 |
82
- | 2.0199 | 6.8381 | 9600 | 0.0981 | 0.2045 |
83
- | 1.7238 | 7.1226 | 10000 | 0.0997 | 0.2022 |
84
- | 1.8087 | 7.4076 | 10400 | 0.0983 | 0.2037 |
85
- | 1.7075 | 7.6977 | 10800 | 0.0985 | 0.2059 |
86
- | 1.7072 | 7.9827 | 11200 | 0.0977 | 0.2062 |
87
- | 1.5864 | 8.2679 | 11600 | 0.0977 | 0.2066 |
88
- | 1.6869 | 8.5530 | 12000 | 0.0972 | 0.2081 |
89
- | 1.7383 | 8.8381 | 12400 | 0.0976 | 0.2041 |
90
- | 1.4336 | 9.1226 | 12800 | 0.0970 | 0.2045 |
91
- | 1.5429 | 9.4076 | 13200 | 0.0969 | 0.2010 |
92
- | 1.5726 | 9.6927 | 13600 | 0.0969 | 0.2084 |
93
- | 1.4709 | 9.9777 | 14000 | 0.0971 | 0.2044 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
94
 
95
 
96
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  license: apache-2.0
4
+ base_model: Baselhany/Distilation_Whisper_base_CKP2
5
  tags:
6
  - generated_from_trainer
7
  metrics:
8
  - wer
9
  model-index:
10
+ - name: Distilation_Whisper_base_CKP2
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_CKP2
18
 
19
+ This model is a fine-tuned version of [Baselhany/Distilation_Whisper_base_CKP2](https://huggingface.co/Baselhany/Distilation_Whisper_base_CKP2) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0982
22
+ - Wer: 0.2127
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: 17
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|
57
+ | 46.3716 | 0.2851 | 400 | 0.1697 | 0.6098 |
58
+ | 16.3556 | 0.5701 | 800 | 0.1355 | 0.3556 |
59
+ | 11.9327 | 0.8552 | 1200 | 0.1230 | 0.3000 |
60
+ | 8.1222 | 1.1397 | 1600 | 0.1196 | 0.2543 |
61
+ | 6.2775 | 1.4247 | 2000 | 0.1165 | 0.2619 |
62
+ | 5.6861 | 1.7098 | 2400 | 0.1143 | 0.2390 |
63
+ | 5.238 | 1.9948 | 2800 | 0.1115 | 0.2346 |
64
+ | 4.5097 | 2.2794 | 3200 | 0.1107 | 0.2256 |
65
+ | 3.9677 | 2.5644 | 3600 | 0.1095 | 0.2262 |
66
+ | 3.8998 | 2.8495 | 4000 | 0.1085 | 0.2300 |
67
+ | 3.3351 | 3.1340 | 4400 | 0.1067 | 0.2140 |
68
+ | 3.1317 | 3.4190 | 4800 | 0.1067 | 0.2199 |
69
+ | 2.9814 | 3.7041 | 5200 | 0.1046 | 0.2119 |
70
+ | 3.167 | 3.9891 | 5600 | 0.1039 | 0.2104 |
71
+ | 2.498 | 4.2737 | 6000 | 0.1066 | 0.2177 |
72
+ | 2.8372 | 4.5587 | 6400 | 0.1022 | 0.2098 |
73
+ | 2.5573 | 4.8438 | 6800 | 0.1028 | 0.2181 |
74
+ | 2.3309 | 5.1283 | 7200 | 0.1006 | 0.2091 |
75
+ | 2.2589 | 5.4133 | 7600 | 0.1015 | 0.2100 |
76
+ | 2.1409 | 5.6984 | 8000 | 0.1024 | 0.2065 |
77
+ | 2.1048 | 5.9834 | 8400 | 0.0992 | 0.2138 |
78
+ | 1.8826 | 6.2679 | 8800 | 0.0987 | 0.2116 |
79
+ | 1.8778 | 6.5530 | 9200 | 0.0988 | 0.2073 |
80
+ | 2.0199 | 6.8381 | 9600 | 0.0981 | 0.2045 |
81
+ | 1.7238 | 7.1226 | 10000 | 0.0997 | 0.2022 |
82
+ | 1.8087 | 7.4076 | 10400 | 0.0983 | 0.2037 |
83
+ | 1.7075 | 7.6977 | 10800 | 0.0985 | 0.2059 |
84
+ | 1.7072 | 7.9827 | 11200 | 0.0977 | 0.2062 |
85
+ | 1.5864 | 8.2679 | 11600 | 0.0977 | 0.2066 |
86
+ | 1.6869 | 8.5530 | 12000 | 0.0972 | 0.2081 |
87
+ | 1.7383 | 8.8381 | 12400 | 0.0976 | 0.2041 |
88
+ | 1.4336 | 9.1226 | 12800 | 0.0970 | 0.2045 |
89
+ | 1.5429 | 9.4076 | 13200 | 0.0969 | 0.2010 |
90
+ | 1.5726 | 9.6927 | 13600 | 0.0969 | 0.2084 |
91
+ | 1.4709 | 9.9777 | 14000 | 0.0971 | 0.2044 |
92
+ | 1.5442 | 10.2637 | 14400 | 0.0978 | 0.2088 |
93
+ | 1.5764 | 10.5487 | 14800 | 0.0985 | 0.2151 |
94
+ | 1.6821 | 10.8338 | 15200 | 0.0970 | 0.2066 |
95
+ | 1.6529 | 11.1183 | 15600 | 0.0974 | 0.2082 |
96
+ | 1.5455 | 11.4033 | 16000 | 0.0971 | 0.2057 |
97
+ | 1.4845 | 11.6884 | 16400 | 0.0973 | 0.2140 |
98
+ | 1.4953 | 11.9735 | 16800 | 0.0960 | 0.2029 |
99
+ | 1.4349 | 12.2580 | 17200 | 0.0958 | 0.2009 |
100
+ | 1.4104 | 12.5430 | 17600 | 0.0974 | 0.2025 |
101
+ | 1.5073 | 12.8281 | 18000 | 0.0953 | 0.2044 |
102
+ | 1.2488 | 13.1126 | 18400 | 0.0949 | 0.1966 |
103
+ | 1.277 | 13.3976 | 18800 | 0.0955 | 0.2084 |
104
+ | 1.2443 | 13.6827 | 19200 | 0.0960 | 0.1995 |
105
+ | 1.3972 | 13.9678 | 19600 | 0.0955 | 0.2028 |
106
+ | 1.2847 | 14.2523 | 20000 | 0.0949 | 0.2034 |
107
+ | 1.3107 | 14.5373 | 20400 | 0.0951 | 0.2013 |
108
+ | 1.2232 | 14.8224 | 20800 | 0.0947 | 0.2003 |
109
+ | 1.2233 | 15.1069 | 21200 | 0.0949 | 0.1985 |
110
+ | 1.1999 | 15.3919 | 21600 | 0.0946 | 0.2025 |
111
+ | 1.236 | 15.6770 | 22000 | 0.0949 | 0.2029 |
112
+ | 1.2252 | 15.9621 | 22400 | 0.0945 | 0.1994 |
113
+ | 1.2094 | 16.2466 | 22800 | 0.0941 | 0.2050 |
114
+ | 1.2505 | 16.5316 | 23200 | 0.0941 | 0.2003 |
115
+ | 1.1193 | 16.8167 | 23600 | 0.0942 | 0.1991 |
116
 
117
 
118
  ### Framework versions
generation_config.json CHANGED
@@ -2,20 +2,7 @@
2
  "bos_token_id": 50257,
3
  "decoder_start_token_id": 50258,
4
  "eos_token_id": 50257,
5
- "input_ids": [
6
- [
7
- 1,
8
- 50272
9
- ],
10
- [
11
- 2,
12
- 50359
13
- ],
14
- [
15
- 3,
16
- 50363
17
- ]
18
- ],
19
  "max_length": 448,
20
  "pad_token_id": 50257,
21
  "transformers_version": "4.51.3"
 
2
  "bos_token_id": 50257,
3
  "decoder_start_token_id": 50258,
4
  "eos_token_id": 50257,
5
+ "input_ids": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "max_length": 448,
7
  "pad_token_id": 50257,
8
  "transformers_version": "4.51.3"
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20a2efcd378e68e5423f165a4a0387d8b6aa67ec332f08647788d627623f31fa
3
  size 223144592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7838ce3c9c1decda0611b9fbf70e46b7cb6ca1c8dda3eff59f67dfbafb8e0702
3
  size 223144592
runs/May23_23-59-44_7cd4622fd13c/events.out.tfevents.1748083266.7cd4622fd13c.19.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b7e9281d472d5dca2ffb0bdf9d342929e91b2839d7aee8892d817f2994b155
3
+ size 412