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 17, 2022

Commit

b71fe6d

•

1 Parent(s): 3ee06de

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -29,10 +29,10 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 41.61
     - name: Cer
       type: cer
-      value: 7.8
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,8 +43,8 @@ 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: 41.3793
-- eval_cer: 9.6895
 - eval_runtime: 437.7464
 - eval_samples_per_second: 0.256
 - eval_steps_per_second: 0.016

     metrics:
     - name: Wer
       type: wer
+      value: 38.62068965517241
     - name: Cer
       type: cer
+      value: 7.325639739086803
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 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: 38.6207
+- eval_cer: 7.3256
 - eval_runtime: 437.7464
 - eval_samples_per_second: 0.256
 - eval_steps_per_second: 0.016