End of training

README.md

@@ -6,9 +6,24 @@ tags:
 - generated_from_trainer
 datasets:
 - fleurs
+metrics:
+- wer
 model-index:
 - name: whisper-base-khmer
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: fleurs
+      type: fleurs
+      config: km_kh
+      split: test
+      args: km_kh
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.9567538446468802
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,6 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
 # whisper-base-khmer
 
 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the fleurs dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6861
+- Wer: 0.9568
 
 ## Model description
 
@@ -36,23 +54,28 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 64
+- eval_batch_size: 64
 - seed: 42
-- gradient_accumulation_steps: 16
+- gradient_accumulation_steps: 2
 - total_train_batch_size: 128
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- 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
 - num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 1.1913        | 1.0   | 158  | 1.1945          | 1.0348 |
+| 0.8548        | 2.0   | 316  | 0.8276          | 0.9761 |
+| 0.6434        | 3.0   | 474  | 0.6861          | 0.9568 |
 
 
 ### Framework versions
 
-- Transformers 4.49.0
-- Pytorch 2.6.0+cu124
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
 - Datasets 3.3.1
 - Tokenizers 0.21.0

generation_config.json

@@ -163,5 +163,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.49.0"
+  "transformers_version": "4.48.3"
 }

runs/Feb20_15-07-12_744d769afcce/events.out.tfevents.1740072199.744d769afcce.1513.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e4d4970d912804d05ab678c4bcc7a476e85d60e658b32406717938c80722a03
+size 406