devkyle
/

Akan

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

devkyle commited on 19 days ago

Commit

eee4b99

•

1 Parent(s): 59ecd64

End of training

Files changed (1) hide show

README.md +7 -5

README.md CHANGED Viewed

@@ -18,8 +18,8 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9100
-- Wer: 66.6103
 ## Model description
@@ -38,7 +38,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
@@ -52,8 +52,10 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch   | Step | Validation Loss | Wer     |
 |:-------------:|:-------:|:----:|:---------------:|:-------:|
-| 0.2912        | 11.6279 | 1000 | 0.7922          | 61.7088 |
-| 0.0927        | 23.2558 | 2000 | 0.9100          | 66.6103 |
 ### Framework versions

 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.1556
+- Wer: 47.8713
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 0.0001
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 | Training Loss | Epoch   | Step | Validation Loss | Wer     |
 |:-------------:|:-------:|:----:|:---------------:|:-------:|
+| 0.0927        | 11.1111 | 500  | 0.9787          | 57.8713 |
+| 0.0218        | 22.2222 | 1000 | 1.0956          | 50.1155 |
+| 0.0012        | 33.3333 | 1500 | 1.1502          | 48.7129 |
+| 0.0003        | 44.4444 | 2000 | 1.1556          | 47.8713 |
 ### Framework versions