techiaith
/

whisper-tiny-ft-cy-en

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

DewiBrynJones commited on Feb 21

Commit

c5bb596

•

1 Parent(s): e12e680

Model save

Files changed (1) hide show

README.md +7 -9

README.md CHANGED Viewed

@@ -1,6 +1,4 @@
 ---
-license: apache-2.0
-base_model: openai/whisper-tiny
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
 # whisper-tiny-ft-cy
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5462
-- Wer: 35.3782
 ## Model description
@@ -52,10 +50,10 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.7059        | 0.25  | 1000 | 0.7389          | 44.4713 |
-| 0.5534        | 0.5   | 2000 | 0.6116          | 39.2685 |
-| 0.5087        | 0.75  | 3000 | 0.5615          | 36.0156 |
-| 0.4749        | 1.01  | 4000 | 0.5462          | 35.3782 |
 ### Framework versions

 ---
 tags:
 - generated_from_trainer
 metrics:
 # whisper-tiny-ft-cy
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.7176
+- Wer: 53.1135
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.8115        | 1.41  | 1000 | 0.8426          | 60.0795 |
+| 0.6396        | 2.83  | 2000 | 0.7508          | 54.4259 |
+| 0.5259        | 4.24  | 3000 | 0.7255          | 53.1328 |
+| 0.4854        | 5.66  | 4000 | 0.7176          | 53.1135 |
 ### Framework versions