Update README.md

README.md

@@ -287,15 +287,15 @@ We have evaluated the models using the Hugging Face Open ASR Leaderboard methodo
 
 We measured RTFx (Real-Time Factor) for each model size on various GPUs. RTFx indicates how many times faster than real-time the model transcribes audio. Higher RTFx is better.
 
-![Latency Benchmarking](https://cdn.thestage.ai/production/cms_file_upload/1773836612-a78e8844-81e7-4539-8538-d1ffab6308c5/Elastic_Whisper_Large_RTF_h100.png)
+![Latency Benchmarking](https://cdn.thestage.ai/production/cms_file_upload/1779128558-e11a4ca6-fc5b-4b7b-aeaf-7796436f0caf/Elastic_Whisper_Large_RTF_h100.png)
 
 ### RTFx, batch size 1
 
 | **GPU/Model Size**| **S**| **M**| **L**| **XL**| **Original** |
  | ---  | ---  | ---  | ---  | ---  | ---  |
-| **H100** | 63.0 | 62.8 | 59.0 | 59.1 | 26.1 |
-| **L40s** | 55.2 | 54.3 | 54.0 | 51.0 | 18.1 |
-| **GeForce RTX 5090** | 64 | 62 | 62 | 62 | 25 |
+| **H100** | 68.9 | 68.4 | 64.3 | 63.8 | 26.1 |
+| **L40s** | 59.4 | 59.4 | 58.3 | 54.6 | 18.1 |
+| **GeForce RTX 5090** | 72 | 70 | 70 | 67 | 25 |
 | **GeForce RTX 4090** | 69.3 | 67.9 | 67.2 | 64.3 | 38.5 |
 
 
@@ -303,10 +303,10 @@ We measured RTFx (Real-Time Factor) for each model size on various GPUs. RTFx in
 
 | **GPU/Model Size**| **S**| **M**| **L**| **XL**| **Original** |
  | ---  | ---  | ---  | ---  | ---  | ---  |
-| **RTX 4090 (bs=24)** | 355 | 353 | 335 | 315 | 302 |
-| **L40s (bs=32)** | 279 | 279 | 269 | 261 | 238 |
-| **RTX 5090 (bs=32)** | 401 | 396 | 396 | 376 | 287 |
-| **H100 (bs=64)** | 532 | 528 | 525 | 522 | 415 |
+| **RTX 4090 (bs=24)** | 355 | 353 | 335 | 320 | 302 |
+| **L40s (bs=32)** | 288 | 288 | 285 | 279 | 238 |
+| **RTX 5090 (bs=32)** | 425 | 422 | 419 | 416 | 287 |
+| **H100 (bs=64)** | 567 | 567 | 567 | 567 | 415 |
 
 
 ## Benchmarking Methodology