End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 104.8076923076923
+      value: 101.73076923076923
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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 Paula dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.1480
-- Wer: 104.8077
+- Loss: 3.7583
+- Wer: 101.7308
 
 ## Model description
 
@@ -59,14 +59,18 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
-- training_steps: 100
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer      |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.0443        | 5.0   | 100  | 3.1480          | 104.8077 |
+| 0.1565        | 10.0  | 200  | 3.3003          | 109.4231 |
+| 0.0107        | 20.0  | 400  | 3.5648          | 104.8077 |
+| 0.0013        | 30.0  | 600  | 3.6987          | 115.9615 |
+| 0.0008        | 40.0  | 800  | 3.7444          | 101.3462 |
+| 0.0007        | 50.0  | 1000 | 3.7583          | 101.7308 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0760fc5cad72daabc34bebe090ecc85870bb1ac7fe1715eee2b65469fb2dfed7
+oid sha256:5b09d4fdf97e19e6c82d910e4e12ba34ec192a6ce87963de147319da67fdff34
 size 966995080