End of training

README.md

@@ -7,18 +7,36 @@ tags:
 - hf-asr-leaderboard
 - generated_from_trainer
 datasets:
-- AsemBadr/Al-Rahman
+- AsemBadr/GP
+metrics:
+- wer
 model-index:
-- name: Whisper Small testing
-  results: []
+- name: Whisper Small for Quran Recognition
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Quran_Reciters
+      type: AsemBadr/GP
+      config: default
+      split: test
+      args: 'config: default, split: train'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 3.747636238610968
 ---
 
 <!-- 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 testing
+# Whisper Small for Quran Recognition
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the testing dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Quran_Reciters dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0193
+- Wer: 3.7476
 
 ## Model description
 
@@ -44,15 +62,26 @@ 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: 500
-- training_steps: 500
+- training_steps: 4000
+- mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.0264        | 1.62  | 500  | 0.0319          | 8.0110 |
+| 0.0012        | 3.24  | 1000 | 0.0228          | 5.5011 |
+| 0.0009        | 4.85  | 1500 | 0.0209          | 4.1258 |
+| 0.0003        | 6.47  | 2000 | 0.0185          | 3.7992 |
+| 0.0002        | 8.09  | 2500 | 0.0188          | 3.7820 |
+| 0.0001        | 9.71  | 3000 | 0.0191          | 3.7476 |
+| 0.0001        | 11.33 | 3500 | 0.0193          | 3.7133 |
+| 0.0           | 12.94 | 4000 | 0.0193          | 3.7476 |
 
 
 ### Framework versions
 
-- Transformers 4.38.0.dev0
-- Pytorch 2.2.0+cpu
-- Datasets 2.17.0
-- Tokenizers 0.15.2
+- Transformers 4.40.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.17.1
+- Tokenizers 0.15.1

generation_config.json

@@ -160,6 +160,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
+  "language": "ar",
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,
@@ -260,5 +261,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.38.0.dev0"
+  "transformers_version": "4.40.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f015c7f1b9feafb7ee823bcb372388e9cfa94118ad3016204cf5a8fff7d1f819
+oid sha256:26588d6642077134603219d49fcdef4c0a247c80636445d0ddae79d5099d8f03
 size 966995080