CKSINGH
/

whisper-small-hi-firefox

Automatic Speech Recognition

hf-asr-leaderboard

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

CKSINGH commited on Nov 27, 2023

Commit

eb46a47

•

1 Parent(s): 83c917a

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [CKSINGH/whisper-small-hi-iiib](https://huggingface.co/CKSINGH/whisper-small-hi-iiib) on the Common Voice 13.0 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.2473
-- Wer: 21.4253
 - Cer: 7.5700
 ## Model description
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer     | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|
-| 0.0382        | 3.57  | 1000 | 0.2021          | 22.8043 | 8.1173 |
-| 0.0027        | 7.14  | 2000 | 0.2321          | 21.6614 | 7.6820 |
-| 0.0001        | 10.71 | 3000 | 0.2473          | 21.4253 | 7.5700 |
 ### Framework versions

 This model is a fine-tuned version of [CKSINGH/whisper-small-hi-iiib](https://huggingface.co/CKSINGH/whisper-small-hi-iiib) on the Common Voice 13.0 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.2473
+- Wer: 11.4253
 - Cer: 7.5700
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Wer     | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|
+| 0.0382        | 3.57  | 1000 | 0.2021          | 12.8043 | 8.1173 |
+| 0.0027        | 7.14  | 2000 | 0.2321          | 11.6614 | 7.6820 |
+| 0.0001        | 10.71 | 3000 | 0.2473          | 11.4253 | 7.5700 |
 ### Framework versions