igoeldc
/

whisper-tiny-en-US

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

igoeldc commited on Aug 15, 2023

Commit

5e2f843

•

1 Parent(s): e8e174a

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 33.76623376623377
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,7 +34,7 @@ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.
 It achieves the following results on the evaluation set:
 - Loss: 0.6503
 - Wer Ortho: 34.1764
-- Wer: 33.7662
 ## Model description
@@ -66,7 +66,7 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
-| 0.0007        | 17.86 | 500  | 0.6503          | 34.1764   | 33.7662 |
 ### Framework versions

     metrics:
     - name: Wer
       type: wer
+      value: 0.3376623376623377
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 It achieves the following results on the evaluation set:
 - Loss: 0.6503
 - Wer Ortho: 34.1764
+- Wer: 0.337662
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
+| 0.0007        | 17.86 | 500  | 0.6503          | 34.1764   | 0.33766 |
 ### Framework versions