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
cdcbf9a
·
verified ·
1 Parent(s): c2a8f47

Model save

Browse files
Files changed (4) hide show
  1. README.md +98 -0
  2. generation_config.json +22 -0
  3. model.safetensors +1 -1
  4. runs/May23_14-40-57_b265a1c16fc0/events.out.tfevents.1748026074.b265a1c16fc0.19.1 +3 -0
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: Baselhany/Distilation_Whisper_base_CKP2
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: Distilation_Whisper_base_CKP2
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # Distilation_Whisper_base_CKP2
17
+
18
+ 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.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.1003
21
+ - Wer: 0.2163
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0001
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 32
46
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 500
49
+ - num_epochs: 10
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
55
+ |:-------------:|:------:|:-----:|:---------------:|:------:|
56
+ | 46.3716 | 0.2851 | 400 | 0.1697 | 0.6098 |
57
+ | 16.3556 | 0.5701 | 800 | 0.1355 | 0.3556 |
58
+ | 11.9327 | 0.8552 | 1200 | 0.1230 | 0.3000 |
59
+ | 8.1222 | 1.1397 | 1600 | 0.1196 | 0.2543 |
60
+ | 6.2775 | 1.4247 | 2000 | 0.1165 | 0.2619 |
61
+ | 5.6861 | 1.7098 | 2400 | 0.1143 | 0.2390 |
62
+ | 5.238 | 1.9948 | 2800 | 0.1115 | 0.2346 |
63
+ | 4.5097 | 2.2794 | 3200 | 0.1107 | 0.2256 |
64
+ | 3.9677 | 2.5644 | 3600 | 0.1095 | 0.2262 |
65
+ | 3.8998 | 2.8495 | 4000 | 0.1085 | 0.2300 |
66
+ | 3.3351 | 3.1340 | 4400 | 0.1067 | 0.2140 |
67
+ | 3.1317 | 3.4190 | 4800 | 0.1067 | 0.2199 |
68
+ | 2.9814 | 3.7041 | 5200 | 0.1046 | 0.2119 |
69
+ | 3.167 | 3.9891 | 5600 | 0.1039 | 0.2104 |
70
+ | 2.498 | 4.2737 | 6000 | 0.1066 | 0.2177 |
71
+ | 2.8372 | 4.5587 | 6400 | 0.1022 | 0.2098 |
72
+ | 2.5573 | 4.8438 | 6800 | 0.1028 | 0.2181 |
73
+ | 2.3309 | 5.1283 | 7200 | 0.1006 | 0.2091 |
74
+ | 2.2589 | 5.4133 | 7600 | 0.1015 | 0.2100 |
75
+ | 2.1409 | 5.6984 | 8000 | 0.1024 | 0.2065 |
76
+ | 2.1048 | 5.9834 | 8400 | 0.0992 | 0.2138 |
77
+ | 1.8826 | 6.2679 | 8800 | 0.0987 | 0.2116 |
78
+ | 1.8778 | 6.5530 | 9200 | 0.0988 | 0.2073 |
79
+ | 2.0199 | 6.8381 | 9600 | 0.0981 | 0.2045 |
80
+ | 1.7238 | 7.1226 | 10000 | 0.0997 | 0.2022 |
81
+ | 1.8087 | 7.4076 | 10400 | 0.0983 | 0.2037 |
82
+ | 1.7075 | 7.6977 | 10800 | 0.0985 | 0.2059 |
83
+ | 1.7072 | 7.9827 | 11200 | 0.0977 | 0.2062 |
84
+ | 1.5864 | 8.2679 | 11600 | 0.0977 | 0.2066 |
85
+ | 1.6869 | 8.5530 | 12000 | 0.0972 | 0.2081 |
86
+ | 1.7383 | 8.8381 | 12400 | 0.0976 | 0.2041 |
87
+ | 1.4336 | 9.1226 | 12800 | 0.0970 | 0.2045 |
88
+ | 1.5429 | 9.4076 | 13200 | 0.0969 | 0.2010 |
89
+ | 1.5726 | 9.6927 | 13600 | 0.0969 | 0.2084 |
90
+ | 1.4709 | 9.9777 | 14000 | 0.0971 | 0.2044 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.51.3
96
+ - Pytorch 2.6.0+cu124
97
+ - Datasets 3.6.0
98
+ - Tokenizers 0.21.1
generation_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
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"
22
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6474908382e59a55f6f58eb9e8a1dfb400ba67f9e060b54394d3d9825c65397
3
  size 223144592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac4290640598dceb77135310af03477fc527a08702173117820a3f0b608a550
3
  size 223144592
runs/May23_14-40-57_b265a1c16fc0/events.out.tfevents.1748026074.b265a1c16fc0.19.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a02201253f7296bbbc1b0f29fccfd2e0e2f01261956e36d3d82fe9dbb0d38511
3
+ size 406