End of training

README.md

@@ -9,9 +9,22 @@ tags:
 - generated_from_trainer
 datasets:
 - Spanish_english
+metrics:
+- wer
 model-index:
 - name: Whisper tiny Russian (Trained with Spanish accent)
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Spanish English
+      type: Spanish_english
+      args: 'config: default, split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 16.29353233830846
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -21,13 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Spanish English dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.2479
-- eval_wer: 12.1144
-- eval_runtime: 122.3571
-- eval_samples_per_second: 3.539
-- eval_steps_per_second: 3.539
-- epoch: 0.9728
-- step: 1000
+- Loss: 0.2750
+- Wer: 16.2935
 
 ## Model description
 
@@ -55,6 +63,15 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 500
 - training_steps: 1500
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.4622        | 0.4864 | 500  | 0.3288          | 17.9851 |
+| 0.2832        | 0.9728 | 1000 | 0.2934          | 17.0896 |
+| 0.1902        | 1.4591 | 1500 | 0.2750          | 16.2935 |
+
+
 ### Framework versions
 
 - Transformers 4.49.0