End of training

README.md

@@ -20,7 +20,7 @@ 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 Common Voice 16.1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9143
+- Loss: 0.8821
 
 ## Model description
 
@@ -48,15 +48,17 @@ 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_ratio: 0.1
-- num_epochs: 2
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.0204        | 1.0   | 2572 | 1.0091          |
-| 0.8829        | 2.0   | 5144 | 0.9143          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.0204        | 1.0   | 2572  | 1.0091          |
+| 0.9044        | 2.0   | 5144  | 0.9392          |
+| 0.7166        | 3.0   | 7716  | 0.8862          |
+| 0.4918        | 4.0   | 10288 | 0.8821          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6af824d7558804e887096862a6820570e31bbaba8c9503c12f6e3f0e41d3bbe4
+oid sha256:a9aeb60ea3c8d782267928d3dc5ddbb49eadc361347fe785eab4994de55d8aea
 size 19548472

runs/Sep06_08-19-34_280808e77886/events.out.tfevents.1725610776.280808e77886.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18bd2846c1897bac4cb3d8466b8135c04e38982783bc4b67ea0ae4db07d7b536
-size 48199
+oid sha256:86629a67ce110484fb30433d75f5f180af0df0b06998807d6979c606ceed0840
+size 51145