thennal
/

whisper-medium-ml

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

thennal commited on Dec 15, 2022

Commit

7b36b9b

·

1 Parent(s): 1b56d78

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -29,7 +29,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 40.00000000000000
     - name: Cer
       type: cer
       value: 9.313970956434652
@@ -43,7 +43,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
 - eval_loss: 0.0833
-- eval_wer: 40.000
 - eval_cer: 9.6895
 - eval_runtime: 437.7464
 - eval_samples_per_second: 0.256

     metrics:
     - name: Wer
       type: wer
+      value: 41.37931034482759
     - name: Cer
       type: cer
       value: 9.313970956434652
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
 - eval_loss: 0.0833
+- eval_wer: 41.3793
 - eval_cer: 9.6895
 - eval_runtime: 437.7464
 - eval_samples_per_second: 0.256