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: 0.8997
+- Loss: 0.9261
 
 ## Model description
 
@@ -48,7 +48,7 @@ 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: 6
+- num_epochs: 8
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -60,7 +60,9 @@ The following hyperparameters were used during training:
 | 0.7166        | 3.0   | 7716  | 0.8862          |
 | 0.5224        | 4.0   | 10288 | 0.9016          |
 | 0.5268        | 5.0   | 12860 | 0.8868          |
-| 0.3808        | 6.0   | 15432 | 0.8997          |
+| 0.414         | 6.0   | 15432 | 0.9129          |
+| 0.3592        | 7.0   | 18004 | 0.9097          |
+| 0.2912        | 8.0   | 20576 | 0.9261          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb65ae2bf327b4eb838e05521d8025854c31e31a200e6f9dd93b013d0c742a7d
+oid sha256:bb429b65555a1559dfa9412a005c47ca41fba1533874a8acb3e946b060c1c3a7
 size 19548472

runs/Sep08_18-24-33_0dab175ad260/events.out.tfevents.1725819875.0dab175ad260.23.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dce7634635307271495768ab0c3f3800eb7dbb633817e88fabd2e7741836755
-size 53084
+oid sha256:9d9bb69f14cc141bd53aecb5ecb82acc617b0d242dd3fc2118403a171220e12b
+size 54365