End of training

README.md

@@ -19,13 +19,11 @@ model-index:
     dataset:
       name: Common Voice 17.0
       type: mozilla-foundation/common_voice_17_0
-      config: am
-      split: None
       args: 'config: am, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 75.43489720611491
+      value: 50.96566523605151
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +33,8 @@ 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 17.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8731
-- Wer: 75.4349
+- Loss: 0.4352
+- Wer: 50.9657
 
 ## Model description
 
@@ -69,15 +67,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss | Wer     |
 |:-------------:|:-------:|:----:|:---------------:|:-------:|
-| 0.0081        | 22.7273 | 1000 | 0.7249          | 78.0706 |
-| 0.0005        | 45.4545 | 2000 | 0.8315          | 74.9605 |
-| 0.0           | 68.1818 | 3000 | 0.8628          | 74.9077 |
-| 0.0           | 90.9091 | 4000 | 0.8731          | 75.4349 |
+| 0.0108        | 9.6154  | 1000 | 0.3446          | 54.9759 |
+| 0.0009        | 19.2308 | 2000 | 0.4052          | 51.7570 |
+| 0.0001        | 28.8462 | 3000 | 0.4277          | 50.9388 |
+| 0.0001        | 38.4615 | 4000 | 0.4352          | 50.9657 |
 
 
 ### Framework versions
 
 - Transformers 4.49.0
 - Pytorch 2.5.1+cu124
-- Datasets 3.3.1
+- Datasets 3.3.2
 - Tokenizers 0.21.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6a83b07776ef8e735e196c3c3a969296a537d5f6de9c9d1697bf9ca5f721be2
+oid sha256:29daf8a46595685d125ab53735002f42dbfe4871271eee85354d32b12c64775e
 size 966995080