Model save

README.md

@@ -1,27 +1,25 @@
 ---
 library_name: transformers
-language:
-- ar
 license: apache-2.0
-base_model: openai/whisper-base
+base_model: Baselhany/Distilation_Whisper_base_CKP_256
 tags:
 - generated_from_trainer
 metrics:
 - wer
 model-index:
-- name: Whisper base AR - BA
+- name: Distilation_Whisper_base_CKP_256
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Whisper base AR - BA
+# Distilation_Whisper_base_CKP_256
 
-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.
+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.
 It achieves the following results on the evaluation set:
-- Loss: 0.1070
-- Wer: 0.2234
+- Loss: 0.1013
+- Wer: 0.2231
 
 ## Model description
 
@@ -49,21 +47,29 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 6
+- num_epochs: 12
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer    |
-|:-------------:|:------:|:----:|:---------------:|:------:|
-| 12.8034       | 0.7126 | 1000 | 0.1280          | 0.3420 |
-| 6.2023        | 1.4247 | 2000 | 0.1193          | 0.2798 |
-| 4.0891        | 2.1368 | 3000 | 0.1101          | 0.2380 |
-| 3.8063        | 2.8495 | 4000 | 0.1078          | 0.2206 |
-| 3.1293        | 3.5616 | 5000 | 0.1058          | 0.2109 |
-| 2.494         | 4.2737 | 6000 | 0.1045          | 0.2238 |
-| 2.5376        | 4.9863 | 7000 | 0.1033          | 0.2100 |
-| 2.1642        | 5.6984 | 8000 | 0.1018          | 0.2193 |
+| Training Loss | Epoch   | Step  | Validation Loss | Wer    |
+|:-------------:|:-------:|:-----:|:---------------:|:------:|
+| 12.8034       | 0.7126  | 1000  | 0.1280          | 0.3420 |
+| 6.2023        | 1.4247  | 2000  | 0.1193          | 0.2798 |
+| 4.0891        | 2.1368  | 3000  | 0.1101          | 0.2380 |
+| 3.8063        | 2.8495  | 4000  | 0.1078          | 0.2206 |
+| 3.1293        | 3.5616  | 5000  | 0.1058          | 0.2109 |
+| 2.494         | 4.2737  | 6000  | 0.1045          | 0.2238 |
+| 2.5376        | 4.9863  | 7000  | 0.1033          | 0.2100 |
+| 2.1642        | 5.6984  | 8000  | 0.1018          | 0.2193 |
+| 2.3079        | 6.4148  | 9000  | 0.1027          | 0.2106 |
+| 2.0513        | 7.1268  | 10000 | 0.1025          | 0.2243 |
+| 2.0667        | 7.8395  | 11000 | 0.1021          | 0.2231 |
+| 1.992         | 8.5516  | 12000 | 0.0993          | 0.2207 |
+| 1.6136        | 9.2637  | 13000 | 0.0985          | 0.2203 |
+| 1.6703        | 9.9763  | 14000 | 0.0979          | 0.2178 |
+| 1.5747        | 10.6884 | 15000 | 0.0973          | 0.2138 |
+| 1.5171        | 11.4005 | 16000 | 0.0972          | 0.2224 |
 
 
 ### Framework versions

generation_config.json

@@ -65,20 +65,7 @@
     "1": "LABEL_1"
   },
   "init_std": 0.02,
-  "input_ids": [
-    [
-      1,
-      50272
-    ],
-    [
-      2,
-      50359
-    ],
-    [
-      3,
-      50363
-    ]
-  ],
+  "input_ids": null,
   "is_decoder": false,
   "is_encoder_decoder": true,
   "is_multilingual": true,

runs/Jun08_07-01-42_ff9e9c151bf3/events.out.tfevents.1749397235.ff9e9c151bf3.19.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5992a2230a73ade4462e374d46d23a1840c4991ff2a3af6d6443700d62faf9f3
+size 412