Hugging Face's logo

Baselhany
/
Graduation_Project_Whisper_base_with_segments

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Baselhany commited on
Commit
14b81ce
·
verified ·
1 Parent(s): 30d77d0

Training finished

Browse files
Files changed (3) hide show
  1. README.md +12 -20
  2. model.safetensors +1 -1
  3. runs/Dec13_08-28-26_0651ac4b9e63/events.out.tfevents.1734082484.0651ac4b9e63.23.1 +3 -0
README.md CHANGED
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
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-segments dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0231
24
- - Wer: 0.2331
25
 
26
  ## Model description
27
 
@@ -41,11 +41,11 @@ More information needed
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 1e-05
44
- - train_batch_size: 8
45
- - eval_batch_size: 4
46
  - seed: 42
47
  - gradient_accumulation_steps: 2
48
- - total_train_batch_size: 16
49
  - optimizer: Use 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
@@ -56,21 +56,13 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Wer |
58
  |:-------------:|:-------:|:----:|:---------------:|:------:|
59
- | 0.017 | 1.3333 | 100 | 0.0233 | 0.2610 |
60
- | 0.0148 | 2.6667 | 200 | 0.0216 | 0.2495 |
61
- | 0.0094 | 4.0 | 300 | 0.0204 | 0.2438 |
62
- | 0.0048 | 5.3333 | 400 | 0.0203 | 0.2409 |
63
- | 0.0027 | 6.6667 | 500 | 0.0206 | 0.2421 |
64
- | 0.0017 | 8.0 | 600 | 0.0213 | 0.2491 |
65
- | 0.0007 | 9.3333 | 700 | 0.0218 | 0.2384 |
66
- | 0.0005 | 10.6667 | 800 | 0.0221 | 0.2368 |
67
- | 0.0003 | 12.0 | 900 | 0.0224 | 0.2372 |
68
- | 0.0003 | 13.3333 | 1000 | 0.0226 | 0.2347 |
69
- | 0.0003 | 14.6667 | 1100 | 0.0228 | 0.2327 |
70
- | 0.0002 | 16.0 | 1200 | 0.0229 | 0.2335 |
71
- | 0.0002 | 17.3333 | 1300 | 0.0230 | 0.2331 |
72
- | 0.0002 | 18.6667 | 1400 | 0.0231 | 0.2331 |
73
- | 0.0002 | 20.0 | 1500 | 0.0231 | 0.2335 |
74
 
75
 
76
  ### Framework versions
 
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-segments dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0162
24
+ - Wer: 0.2193
25
 
26
  ## Model description
27
 
 
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 1e-05
44
+ - train_batch_size: 16
45
+ - eval_batch_size: 8
46
  - seed: 42
47
  - gradient_accumulation_steps: 2
48
+ - total_train_batch_size: 32
49
  - optimizer: Use 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
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Wer |
58
  |:-------------:|:-------:|:----:|:---------------:|:------:|
59
+ | 0.0163 | 2.6667 | 100 | 0.0165 | 0.2207 |
60
+ | 0.0081 | 5.3333 | 200 | 0.0153 | 0.2286 |
61
+ | 0.0037 | 8.0 | 300 | 0.0154 | 0.2295 |
62
+ | 0.0005 | 10.6667 | 400 | 0.0162 | 0.2193 |
63
+ | 0.0001 | 13.3333 | 500 | 0.0177 | 0.2220 |
64
+ | 0.0 | 16.0 | 600 | 0.0193 | 0.2193 |
65
+ | 0.0 | 18.6667 | 700 | 0.0207 | 0.2127 |
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74e5303e9d465258445cf724ffdc95b5c0876e2d7e3fe54881356f3d90534cbb
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9848e7b2f8dcea96916df6d46b670ffd2fe17f5abf9d06d4f86dacf180d0872
3
  size 290403936
runs/Dec13_08-28-26_0651ac4b9e63/events.out.tfevents.1734082484.0651ac4b9e63.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28adc69cc00ef03aafef432754fcddc52a1ed78bb5d0c47e208cb1c1cd0e883b
3
+ size 406