End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 46.84852002321532
+      value: 80.51073708647708
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the Common Voice 17.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6241
-- Wer: 46.8485
+- Loss: 1.1000
+- Wer: 80.5107
 
 ## Model description
 
@@ -59,18 +59,14 @@ 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: 5000
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Wer      |
-|:-------------:|:-------:|:----:|:---------------:|:--------:|
-| 0.5001        | 5.4945  | 1000 | 1.1547          | 110.5630 |
-| 0.0995        | 10.9890 | 2000 | 1.3888          | 50.6094  |
-| 0.0139        | 16.4835 | 3000 | 1.5189          | 48.9959  |
-| 0.0028        | 21.9780 | 4000 | 1.6030          | 46.3610  |
-| 0.0008        | 27.4725 | 5000 | 1.6241          | 46.8485  |
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.4601        | 5.4945 | 1000 | 1.1000          | 80.5107 |
 
 
 ### Framework versions