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: 0.9567
+- Loss: 0.8206
 
 ## 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: 2
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -56,7 +56,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 1.0718        | 0.9998 | 2498 | 1.0502          |
-| 0.8117        | 1.9996 | 4996 | 0.9567          |
+| 0.827         | 1.9998 | 4996 | 0.8812          |
+| 0.7326        | 3.0    | 7495 | 0.8333          |
+| 0.6033        | 3.9994 | 9992 | 0.8206          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d74ac2cc8125beb4645adc6dadd623f8fb1c1d95a946d73849da40c88522f03
+oid sha256:6f90fcc358f1aaea7cd5879815768befd4964f12d7d80616dcef893d4b214f34
 size 19548472

runs/May02_07-34-02_1a1e678fde7f/events.out.tfevents.1714635244.1a1e678fde7f.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7544075bf06434cb57587e6f5cffce9cef2db2eab70920040f03cea5d1aee9c4
-size 48294
+oid sha256:0a327983503115e80ca378a48423e228600e31f50d559db02bcc836f962107f5
+size 52928