RedHatAI
/

whisper-large-v3-turbo-quantized.w8a8

Automatic Speech Recognition

8-bit precision

compressed-tensors

Model card Files Files and versions Community

nm-research commited on Apr 21

Commit

d38f467

·

verified ·

1 Parent(s): f8fbf58

Update README.md

Files changed (1) hide show

README.md +9 -9

README.md CHANGED Viewed

@@ -259,21 +259,21 @@ lmms-eval \
     <tr>
       <td rowspan="3"><b>Fleurs (X→en, BLEU)</b></td>
       <td>cmn_hans_cn</td>
-      <td></td>
-      <td></td>
-      <td></td>
     </tr>
     <tr>
       <td>en</td>
-      <td></td>
-      <td></td>
-      <td></td>
     </tr>
     <tr>
       <td>yue_hant_hk</td>
-      <td></td>
-      <td></td>
-      <td></td>
     </tr>
   </tbody>
 </table>

     <tr>
       <td rowspan="3"><b>Fleurs (X→en, BLEU)</b></td>
       <td>cmn_hans_cn</td>
+      <td>8.2384</td>
+      <td>8.2608</td>
+      <td>99.73%</td>
     </tr>
     <tr>
       <td>en</td>
+      <td>4.2914</td>
+      <td>4.3395</td>
+      <td>98.90%</td>
     </tr>
     <tr>
       <td>yue_hant_hk</td>
+      <td>10.5004</td>
+      <td>10.5555</td>
+      <td>99.48%</td>
     </tr>
   </tbody>
 </table>