Training finished

README.md

@@ -20,9 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the quran-ayat-speech-to-text dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0324
-- Wer: 19.4875
-- Cer: 6.0481
+- Loss: 0.0295
+- Wer: 18.2294
+- Cer: 5.7631
 
 ## Model description
 
@@ -50,33 +50,28 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 20
+- num_epochs: 15
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch   | Step | Validation Loss | Wer     | Cer    |
 |:-------------:|:-------:|:----:|:---------------:|:-------:|:------:|
-| 0.0124        | 1.0     | 157  | 0.0209          | 21.0028 | 6.7946 |
-| 0.0072        | 2.0     | 314  | 0.0219          | 22.0836 | 6.9899 |
-| 0.0053        | 3.0     | 471  | 0.0248          | 22.0550 | 7.1469 |
-| 0.0044        | 4.0     | 628  | 0.0264          | 23.7930 | 7.5191 |
-| 0.0032        | 5.0     | 785  | 0.0268          | 22.6978 | 7.1774 |
-| 0.0027        | 6.0     | 942  | 0.0268          | 23.4501 | 7.8043 |
-| 0.0018        | 7.0     | 1099 | 0.0290          | 22.7693 | 7.4282 |
-| 0.0015        | 8.0     | 1256 | 0.0280          | 20.9932 | 6.8523 |
-| 0.0012        | 9.0     | 1413 | 0.0275          | 21.3027 | 6.6809 |
-| 0.0009        | 10.0    | 1570 | 0.0298          | 21.3646 | 6.6471 |
-| 0.0007        | 11.0    | 1727 | 0.0288          | 20.5266 | 6.4107 |
-| 0.0004        | 12.0    | 1884 | 0.0287          | 20.0933 | 6.4185 |
-| 0.0003        | 13.0    | 2041 | 0.0304          | 19.9076 | 6.3125 |
-| 0.0001        | 14.0    | 2198 | 0.0288          | 19.2934 | 5.9481 |
-| 0.0001        | 15.0    | 2355 | 0.0300          | 19.0363 | 6.1728 |
-| 0.0           | 16.0    | 2512 | 0.0301          | 17.7793 | 5.5348 |
-| 0.0           | 17.0    | 2669 | 0.0313          | 17.9031 | 5.6768 |
-| 0.0           | 18.0    | 2826 | 0.0317          | 17.7412 | 5.5980 |
-| 0.0           | 19.0    | 2983 | 0.0324          | 17.6745 | 5.5647 |
-| 0.0           | 19.8768 | 3120 | 0.0325          | 17.7269 | 5.5792 |
+| 0.01          | 1.0     | 157  | 0.0199          | 19.8029 | 6.3519 |
+| 0.0055        | 2.0     | 314  | 0.0211          | 20.8552 | 6.9799 |
+| 0.0036        | 3.0     | 471  | 0.0257          | 21.6265 | 7.0476 |
+| 0.0033        | 4.0     | 628  | 0.0259          | 22.0074 | 7.2900 |
+| 0.0026        | 5.0     | 785  | 0.0277          | 21.6265 | 7.7954 |
+| 0.0019        | 6.0     | 942  | 0.0297          | 21.4122 | 7.2057 |
+| 0.0014        | 7.0     | 1099 | 0.0271          | 20.3695 | 6.4618 |
+| 0.0009        | 8.0     | 1256 | 0.0295          | 19.7981 | 6.5333 |
+| 0.0006        | 9.0     | 1413 | 0.0283          | 18.8077 | 6.0707 |
+| 0.0003        | 10.0    | 1570 | 0.0283          | 18.8696 | 5.9392 |
+| 0.0001        | 11.0    | 1727 | 0.0280          | 18.8077 | 5.9087 |
+| 0.0           | 12.0    | 1884 | 0.0281          | 17.9126 | 5.5364 |
+| 0.0           | 13.0    | 2041 | 0.0284          | 17.2079 | 5.3184 |
+| 0.0           | 14.0    | 2198 | 0.0289          | 17.2031 | 5.3118 |
+| 0.0           | 14.9088 | 2340 | 0.0290          | 17.1269 | 5.2729 |
 
 
 ### Framework versions

runs/Feb19_12-43-19_1fe71ee75448/events.out.tfevents.1739996154.1fe71ee75448.18.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:834ce7e92d1a64dfe07390c72d983c4f478ac301b5bd960f248958cb81457e7a
+size 453