End of training

README.md

@@ -3,7 +3,7 @@ library_name: transformers
 language:
 - ar
 license: apache-2.0
-base_model: openai/whisper-small
+base_model: openai/whisper-base
 tags:
 - generated_from_trainer
 datasets:
@@ -11,7 +11,7 @@ datasets:
 metrics:
 - wer
 model-index:
-- name: Whisper Small Ar - Sanchit Gandhi
+- name: Whisper Base Ar - GPTeam
   results:
   - task:
       name: Automatic Speech Recognition
@@ -23,18 +23,18 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 221.36990801576871
+      value: 29.20499342969777
 ---
 
 <!-- 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 Ar - Sanchit Gandhi
+# Whisper Base Ar - GPTeam
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the quranic_audio_dataset dataset.
+This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the quranic_audio_dataset dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4500
-- Wer: 221.3699
+- Loss: 0.0527
+- Wer: 29.2050
 
 ## Model description
 
@@ -59,21 +59,23 @@ The following hyperparameters were used during training:
 - seed: 42
 - 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: 1
-- training_steps: 2
+- lr_scheduler_warmup_steps: 500
+- training_steps: 4000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer      |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 2.3047        | 0.0029 | 1    | 2.4500          | 221.3699 |
-| 2.6272        | 0.0058 | 2    | 2.4500          | 221.3699 |
+| Training Loss | Epoch   | Step | Validation Loss | Wer     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|
+| 0.0771        | 2.9240  | 1000 | 0.0722          | 34.2806 |
+| 0.0183        | 5.8480  | 2000 | 0.0553          | 30.8476 |
+| 0.0062        | 8.7719  | 3000 | 0.0527          | 30.7654 |
+| 0.0023        | 11.6959 | 4000 | 0.0527          | 29.2050 |
 
 
 ### Framework versions
 
-- Transformers 4.48.1
+- Transformers 4.49.0
 - Pytorch 2.5.1+cu124
-- Datasets 3.2.0
+- Datasets 3.3.2
 - Tokenizers 0.21.0

generation_config.json

@@ -1,44 +1,36 @@
 {
   "alignment_heads": [
     [
-      5,
-      3
-    ],
-    [
-      5,
-      9
+      3,
+      1
     ],
     [
-      8,
-      0
+      4,
+      2
     ],
     [
-      8,
-      4
+      4,
+      3
     ],
     [
-      8,
+      4,
       7
     ],
     [
-      8,
-      8
-    ],
-    [
-      9,
-      0
+      5,
+      1
     ],
     [
-      9,
-      7
+      5,
+      2
     ],
     [
-      9,
-      9
+      5,
+      4
     ],
     [
-      10,
-      5
+      5,
+      6
     ]
   ],
   "begin_suppress_tokens": [
@@ -241,6 +233,8 @@
     49870,
     50254,
     50258,
+    50358,
+    50359,
     50360,
     50361,
     50362
@@ -250,5 +244,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.48.1"
+  "transformers_version": "4.49.0"
 }