End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0722
-- Wer: 66.0915
+- Loss: 0.0759
+- Wer: 71.7860
 
 ## Model description
 
@@ -46,18 +46,16 @@ 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: 250
-- training_steps: 1500
+- training_steps: 1000
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer      |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 3.058         | 2.76  | 250  | 0.5285          | 243.4858 |
-| 0.4211        | 5.52  | 500  | 0.0833          | 84.1242  |
-| 0.1963        | 8.29  | 750  | 0.0767          | 121.1389 |
-| 0.1269        | 11.05 | 1000 | 0.0716          | 57.2908  |
-| 0.103         | 13.81 | 1250 | 0.0732          | 113.0285 |
-| 0.1177        | 16.57 | 1500 | 0.0722          | 66.0915  |
+| 3.07          | 2.76  | 250  | 0.4848          | 242.7955 |
+| 0.4114        | 5.52  | 500  | 0.0852          | 76.2726  |
+| 0.1862        | 8.29  | 750  | 0.0795          | 122.6057 |
+| 0.1434        | 11.05 | 1000 | 0.0759          | 71.7860  |
 
 
 ### Framework versions