update whisper woq int8 accuracy to good (green sign) (#3153)

Author: ZailiWang

README.md

@@ -54,7 +54,7 @@ In the current technological landscape, Generative AI (GenAI) workloads and mode
 |Phi| microsoft/Phi-3-mini-128k-instruct | 🟩 | 🟩 | 🟨 | 🟩 | 🟨 |
 |Phi| microsoft/Phi-3-medium-4k-instruct | 🟩 | 🟩 | 🟨 | 🟩 | 🟨 |
 |Phi| microsoft/Phi-3-medium-128k-instruct | 🟩 | 🟩 | 🟨 | 🟩 | 🟨 |
-|Whisper| openai/whisper-large-v2 | 🟩 | 🟩 | 🟩 |   |   |
+|Whisper| openai/whisper-large-v2 | 🟩 | 🟩 | 🟩 | 🟩 |   |
 
 - 🟩 signifies that the model can perform well and with good accuracy (<1% difference as compared with FP32).
 

docs/_static/htmls/tbl_single.html

@@ -341,7 +341,7 @@
       <td><p style="text-align: center; vertical-align: middle;">🟩</p></td>
       <td><p style="text-align: center; vertical-align: middle;">🟩</p></td>
       <td><p style="text-align: center; vertical-align: middle;">🟩</p></td>
-      <td><p style="text-align: center; vertical-align: middle;"></p></td>
+      <td><p style="text-align: center; vertical-align: middle;">🟩</p></td>
       <td><p style="text-align: center; vertical-align: middle;"></p></td>
     </tr>
   </tbody>

examples/cpu/llm/inference/README.md

@@ -40,7 +40,7 @@
 |Phi| microsoft/Phi-3-mini-128k-instruct | 🟩 | 🟩 | 🟨 | 🟩 | 🟨 |
 |Phi| microsoft/Phi-3-medium-4k-instruct | 🟩 | 🟩 | 🟨 | 🟩 | 🟨 |
 |Phi| microsoft/Phi-3-medium-128k-instruct | 🟩 | 🟩 | 🟨 | 🟩 | 🟨 |
-|Whisper| openai/whisper-large-v2 | 🟩 | 🟩 | 🟩 |   |   |
+|Whisper| openai/whisper-large-v2 | 🟩 | 🟩 | 🟩 | 🟩 |   |
 
 ## 1.2 Verified for distributed inference mode via DeepSpeed