Hugging Face's logo

Baselhany
/
Distilation_Whisper_base_CKP_256

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Model card Files
xet
 Metrics Community
Baselhany commited on
Commit
815c1bb
·
verified ·
1 Parent(s): 5d7dc2e

Model save

Browse files
Files changed (3) hide show
  1. README.md +19 -32
  2. model.safetensors +1 -1
  3. runs/Jun09_00-14-58_93c2f1de5144/events.out.tfevents.1749466572.93c2f1de5144.19.1 +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: 0.1005
24
- - Wer: 0.2236
25
 
26
  ## Model description
27
 
@@ -49,34 +47,23 @@ 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
- | 12.8034 | 0.7126 | 1000 | 0.1280 | 0.3420 |
60
- | 6.2023 | 1.4247 | 2000 | 0.1193 | 0.2798 |
61
- | 4.0891 | 2.1368 | 3000 | 0.1101 | 0.2380 |
62
- | 3.8063 | 2.8495 | 4000 | 0.1078 | 0.2206 |
63
- | 3.1293 | 3.5616 | 5000 | 0.1058 | 0.2109 |
64
- | 2.494 | 4.2737 | 6000 | 0.1045 | 0.2238 |
65
- | 2.5376 | 4.9863 | 7000 | 0.1033 | 0.2100 |
66
- | 2.1642 | 5.6984 | 8000 | 0.1018 | 0.2193 |
67
- | 2.3079 | 6.4148 | 9000 | 0.1027 | 0.2106 |
68
- | 2.0513 | 7.1268 | 10000 | 0.1025 | 0.2243 |
69
- | 2.0667 | 7.8395 | 11000 | 0.1021 | 0.2231 |
70
- | 1.992 | 8.5516 | 12000 | 0.0993 | 0.2207 |
71
- | 1.6136 | 9.2637 | 13000 | 0.0985 | 0.2203 |
72
- | 1.6703 | 9.9763 | 14000 | 0.0979 | 0.2178 |
73
- | 1.5747 | 10.6884 | 15000 | 0.0973 | 0.2138 |
74
- | 1.5171 | 11.4005 | 16000 | 0.0972 | 0.2224 |
75
- | 1.5088 | 12.1169 | 17000 | 0.0972 | 0.2188 |
76
- | 1.6396 | 12.8295 | 18000 | 0.0972 | 0.2203 |
77
- | 1.4925 | 13.5416 | 19000 | 0.0977 | 0.2283 |
78
- | 1.4158 | 14.2537 | 20000 | 0.0973 | 0.2147 |
79
- | 1.4426 | 14.9663 | 21000 | 0.0968 | 0.2165 |
80
 
81
 
82
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  license: apache-2.0
4
+ base_model: Baselhany/Distilation_Whisper_base_CKP_256
5
  tags:
6
  - generated_from_trainer
7
  metrics:
8
  - wer
9
  model-index:
10
+ - name: Distilation_Whisper_base_CKP_256
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_256
18
 
19
+ This model is a fine-tuned version of [Baselhany/Distilation_Whisper_base_CKP_256](https://huggingface.co/Baselhany/Distilation_Whisper_base_CKP_256) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0963
22
+ - Wer: 0.2053
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: 6
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:------:|:-----:|:---------------:|:------:|
57
+ | 3.2982 | 0.5928 | 1000 | 0.1013 | 0.2140 |
58
+ | 2.442 | 1.1855 | 2000 | 0.1004 | 0.2026 |
59
+ | 2.4875 | 1.7783 | 3000 | 0.0967 | 0.1972 |
60
+ | 1.7274 | 2.3711 | 4000 | 0.0925 | 0.1963 |
61
+ | 1.8653 | 2.9638 | 5000 | 0.0941 | 0.2039 |
62
+ | 1.5181 | 3.5566 | 6000 | 0.0921 | 0.2011 |
63
+ | 1.4064 | 4.1494 | 7000 | 0.0911 | 0.2023 |
64
+ | 1.3914 | 4.7421 | 8000 | 0.0905 | 0.1998 |
65
+ | 1.2463 | 5.3349 | 9000 | 0.0891 | 0.2022 |
66
+ | 1.2122 | 5.9277 | 10000 | 0.0896 | 0.2093 |
 
 
 
 
 
 
 
 
 
 
 
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10760f7b4bd0f11e96c49e3fa0df8c6897497ac6570543dad506a9f60f5bda06
3
  size 223144592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4380065c3c820b67f5f10da2947cfe4f2a7d2bbc2a02ac12da3353b03e53fa49
3
  size 223144592
runs/Jun09_00-14-58_93c2f1de5144/events.out.tfevents.1749466572.93c2f1de5144.19.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1022c6aeca5a2a719d812d2df9816aced196c0365f097b1ed2da930a1a838d87
3
+ size 406