End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 36.434108527131784
+      value: 34.75452196382429
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +32,9 @@ 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 PolyAI/minds14 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7774
-- Wer Ortho: 36.2719
-- Wer: 36.4341
+- Loss: 0.8213
+- Wer Ortho: 34.7914
+- Wer: 34.7545
 
 ## Model description
 
@@ -60,14 +60,14 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 500
+- training_steps: 800
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
-| 0.0001        | 17.24 | 500  | 0.7774          | 36.2719   | 36.4341 |
+| 0.0           | 17.24 | 500  | 0.8213          | 34.7914   | 34.7545 |
 
 
 ### Framework versions

runs/Jan31_13-35-17_280ac53becce/events.out.tfevents.1706708122.280ac53becce.333.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97cdddb14c7af158ecfc66ad510e41b42eff9661a5cb105576cc0947ffbad588
-size 9535
+oid sha256:628cd71a309e60b70c590f3ba729f18a317280a113a275e955b5c3840c3a667a
+size 11773