deepdml commited on
Commit
13c7268
·
1 Parent(s): 0588b2b

End of training

Browse files
Files changed (1) hide show
  1. README.md +9 -23
README.md CHANGED
@@ -22,8 +22,9 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 39.6116504854369
26
  ---
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
  should probably proofread and complete it, then remove this comment. -->
29
 
@@ -31,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 17.0 dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.9379
35
- - Wer: 39.6117
36
 
37
  ## Model description
38
 
@@ -57,18 +58,14 @@ The following hyperparameters were used during training:
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
- - lr_scheduler_warmup_steps: 500
61
- - training_steps: 5000
62
 
63
  ### Training results
64
 
65
- | Training Loss | Epoch | Step | Validation Loss | Wer |
66
- |:-------------:|:-----:|:----:|:---------------:|:-------:|
67
- | 0.0492 | 0.2 | 1000 | 0.7698 | 39.3078 |
68
- | 0.0288 | 0.4 | 2000 | 0.6834 | 1.5808 |
69
- | 0.0225 | 0.6 | 3000 | 0.7354 | 11.6002 |
70
- | 0.0082 | 0.8 | 4000 | 0.9359 | 41.3866 |
71
- | 0.0438 | 1.0 | 5000 | 0.9379 | 39.6117 |
72
 
73
 
74
  ### Framework versions
@@ -77,14 +74,3 @@ The following hyperparameters were used during training:
77
  - Pytorch 2.3.0+cu121
78
  - Datasets 2.19.1
79
  - Tokenizers 0.19.1
80
-
81
- ## Citation
82
-
83
- ```bibtex
84
- @misc{deepdml/whisper-medium-ar-quran-mix,
85
- title={Fine-tuned Whisper medium ASR model for speech recognition in Arabic},
86
- author={Jimenez, David},
87
- howpublished={\url{https://huggingface.co/deepdml/whisper-medium-ar-quran-mix}},
88
- year={2025}
89
- }
90
- ```
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.15533980582524273
26
  ---
27
+
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
  should probably proofread and complete it, then remove this comment. -->
30
 
 
32
 
33
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 17.0 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.0757
36
+ - Wer: 0.1553
37
 
38
  ## Model description
39
 
 
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_ratio: 0.04
62
+ - training_steps: 15000
63
 
64
  ### Training results
65
 
66
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
67
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
68
+ | 0.0377 | 1.0 | 15000 | 1.0757 | 0.1553 |
 
 
 
 
69
 
70
 
71
  ### Framework versions
 
74
  - Pytorch 2.3.0+cu121
75
  - Datasets 2.19.1
76
  - Tokenizers 0.19.1