End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 92.72042673360528
+      value: 19.76780671477879
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Quechua_dataset dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5509
-- Wer: 92.7204
+- Loss: 0.2232
+- Wer: 19.7678
 
 ## Model description
 
@@ -60,14 +60,17 @@ The following hyperparameters were used during training:
 - optimizer: Use 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: 500
-- training_steps: 100
+- training_steps: 4000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 1.7598        | 0.1355 | 100  | 1.5509          | 92.7204 |
+| 0.2739        | 1.3550 | 1000 | 0.3388          | 31.3461 |
+| 0.1322        | 2.7100 | 2000 | 0.2377          | 25.1961 |
+| 0.0275        | 4.0650 | 3000 | 0.2216          | 20.6464 |
+| 0.0127        | 5.4201 | 4000 | 0.2232          | 19.7678 |
 
 
 ### Framework versions