End of training

README.md

@@ -2,38 +2,30 @@
 language:
 - ar
 license: apache-2.0
-base_model: openai/whisper-small
+base_model: openai/whisper-medium
 tags:
 - generated_from_trainer
 datasets:
 - fawzanaramam/the-amma-juz
-metrics:
-- wer
 model-index:
-- name: Whisper Small Finetuned on Last Chapters of Quran
-  results:
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: The Truth Last Chapters
-      type: fawzanaramam/the-amma-juz
-      args: 'config: ar, split: train'
-    metrics:
-    - name: Wer
-      type: wer
-      value: 5.250596658711217
+- name: Whisper Medium Finetuned on Amma Juz of Quran
+  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 Small Finetuned on Last Chapters of Quran
+# Whisper Medium Finetuned on Amma Juz of Quran
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the The Truth Last Chapters dataset.
+This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the The Truth Amma Juz dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0584
-- Wer: 5.2506
+- eval_loss: 0.0032
+- eval_wer: 0.5102
+- eval_runtime: 47.9061
+- eval_samples_per_second: 2.087
+- eval_steps_per_second: 0.271
+- epoch: 0.6653
+- step: 950
 
 ## Model description
 
@@ -59,25 +51,9 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 10
-- training_steps: 100
+- num_epochs: 3.0
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss | Wer      |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| No log        | 0.0725 | 10   | 0.8505          | 117.6611 |
-| No log        | 0.1449 | 20   | 0.2837          | 43.3174  |
-| 0.7614        | 0.2174 | 30   | 0.1635          | 33.8902  |
-| 0.7614        | 0.2899 | 40   | 0.1166          | 10.7399  |
-| 0.1326        | 0.3623 | 50   | 0.0962          | 12.0525  |
-| 0.1326        | 0.4348 | 60   | 0.0759          | 8.2339   |
-| 0.1326        | 0.5072 | 70   | 0.0681          | 14.2005  |
-| 0.1009        | 0.5797 | 80   | 0.0635          | 5.7279   |
-| 0.1009        | 0.6522 | 90   | 0.0601          | 5.4893   |
-| 0.0653        | 0.7246 | 100  | 0.0584          | 5.2506   |
-
-
 ### Framework versions
 
 - Transformers 4.41.1

generation_config.json

@@ -1,44 +1,28 @@
 {
   "alignment_heads": [
     [
-      5,
-      3
+      13,
+      15
     ],
     [
-      5,
-      9
-    ],
-    [
-      8,
-      0
-    ],
-    [
-      8,
+      15,
       4
     ],
     [
-      8,
-      7
+      15,
+      15
     ],
     [
-      8,
-      8
+      16,
+      1
     ],
     [
-      9,
+      20,
       0
     ],
     [
-      9,
-      7
-    ],
-    [
-      9,
-      9
-    ],
-    [
-      10,
-      5
+      23,
+      4
     ]
   ],
   "begin_suppress_tokens": [

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d84c4b2675dc60a13d28b6d3a83d7ddbd34db7481f2e79cb7749f90efe60ca8
+oid sha256:c3a2abd5ff337b8c90cd9f6d25d3866015765854afe3e5d722f8ba9f556e7715
 size 3055544304