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:
-- Loss: 1.0036
-- Cer: 52.3096
+- Loss: 0.8478
+- Cer: 49.1156
 
 ## Model description
 
@@ -48,14 +48,16 @@ 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: 1
+- num_epochs: 2
 
 ### Training results
 
-| 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 |
+| Training Loss | Epoch  | Step | Cer     | Validation Loss |
+|:-------------:|:------:|:----:|:-------:|:---------------:|
+| 1.2118        | 0.4002 | 1000 | 57.4322 | 1.1272          |
+| 1.083         | 0.8005 | 2000 | 52.3096 | 1.0036          |
+| 0.7856        | 1.2007 | 3000 | 0.8861  | 54.0876         |
+| 0.8188        | 1.6010 | 4000 | 0.8478  | 49.1156         |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea614f3b3aa19454a5699c56950d12db7aa21853af22c420618f1fe5638b84a9
+oid sha256:20afd595c1364976416d3a730d27e8bba39fa4b1d6e7882e80b59f77799a68ad
 size 966995080

runs/May03_13-58-27_1c608c41b394/events.out.tfevents.1714744732.1c608c41b394.27.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f3c73730daf37a42e009150d82a85248ec002b80f0edf1172139a8a7f1bb2f9
-size 23036
+oid sha256:a5c38e0279d5bb5febef23209188775ee0ec4c03842493e2404d82c00c64fcb0
+size 31619