End of training

README.md

@@ -20,8 +20,8 @@ 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 16.1 and the Common Voice 15.0 datasets.
 It achieves the following results on the evaluation set:
-- Loss: 0.4201
-- Cer: 32.6710
+- Loss: 0.3736
+- Cer: 29.5906
 
 ## Model description
 
@@ -47,13 +47,18 @@ 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: 100
-- num_epochs: 1
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Cer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.3162        | 1.0   | 3111 | 0.4201          | 32.6710 |
+| 0.2295        | 1.13  | 3500 | 0.4268          | 32.4577 |
+| 0.179         | 1.29  | 4000 | 0.4088          | 32.1109 |
+| 0.161         | 1.45  | 4500 | 0.3923          | 30.9241 |
+| 0.1607        | 1.61  | 5000 | 0.3840          | 30.1640 |
+| 0.1336        | 1.77  | 5500 | 0.3783          | 29.7573 |
+| 0.1258        | 1.93  | 6000 | 0.3736          | 29.5906 |
 
 
 ### Framework versions

runs/Mar15_16-35-54_bf7e71710b7f/events.out.tfevents.1710520580.bf7e71710b7f.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c70fb421b056ac2fe8e772845fd4e33171fa93b106adec5f231fc16c62d0c3
-size 32644
+oid sha256:7272a925e48b7b0dfd7cd349c47ee2c053d5881c226cdd30201fb38380be4c0c
+size 34686