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-tiny](https://huggingface.co/openai/whisper-tiny) on the bial2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3045
-- Wer: 26.8198
+- Loss: 0.3229
+- Wer: 31.7789
 
 ## Model description
 
@@ -47,15 +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: 500
-- training_steps: 2000
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer     |
-|:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.179         | 3.8911 | 1000 | 0.3229          | 27.5749 |
-| 0.0687        | 7.7821 | 2000 | 0.3045          | 26.8198 |
+| Training Loss | Epoch | Step | Validation Loss | Wer      |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.4255        | 1.0   | 257  | 1.3274          | 102.7404 |
+| 0.5538        | 2.0   | 514  | 0.5221          | 44.0872  |
+| 0.3054        | 3.0   | 771  | 0.3637          | 30.5956  |
+| 0.202         | 4.0   | 1028 | 0.3305          | 28.6649  |
+| 0.1601        | 5.0   | 1285 | 0.3229          | 31.7789  |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:041abfb9dde50162d91420279a9d670f5512b35a29c3cbadd6752a967ad85eca
+oid sha256:534c36c7fc038acb52915d585e03be4bfaf39b5c04378869cc309ea70659a53e
 size 151061672