End of training

README.md

@@ -19,8 +19,8 @@ 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 dataset.
 It achieves the following results on the evaluation set:
-- Cer: 48.6382
-- Loss: 0.6474
+- Loss: 1.0036
+- Cer: 52.3096
 
 ## Model description
 
@@ -48,16 +48,14 @@ 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: 3
+- num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Cer     | Validation Loss |
-|:-------------:|:------:|:----:|:-------:|:---------------:|
-| 0.9789        | 0.6452 | 1000 | 60.2169 | 0.9021          |
-| 0.61          | 1.2903 | 2000 | 53.3884 | 0.7536          |
-| 0.5611        | 1.9355 | 3000 | 51.3360 | 0.6703          |
-| 0.3359        | 2.5806 | 4000 | 48.6382 | 0.6474          |
+| Training Loss | Epoch  | Step | Validation Loss | Cer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 1.2118        | 0.4002 | 1000 | 1.1272          | 57.4322 |
+| 1.083         | 0.8005 | 2000 | 1.0036          | 52.3096 |
 
 
 ### Framework versions

runs/May03_06-33-04_e0ea6eafb4a7/events.out.tfevents.1714717985.e0ea6eafb4a7.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e16cc92b1a456b3ef2fdd4129107f17a4d1ce423f3e7e58e0552edf1be3e2196
-size 23016
+oid sha256:52a53a6ada2354afdcca56aae9f61e98a27abe4cb2a2889d2ff9fb6651f28e48
+size 27379