Update README.md

README.md

@@ -83,12 +83,12 @@ The result is a distilled model that performs within **2% WER of [Whisper large-
 
 | Model                  | Params (M) | Rel. Latency | Short-Form WER | Long-Form WER |
 | :--------------------- | :--------: | :----------: | :------------: | :-----------: |
-| whisper-tiny           |    37.8    |     4.7      |     43.73      |    28.158     |
-| whisper-base           |    72.6    |     3.7      |     30.57      |    18.665     |
-| whisper-small          |    242     |     2.3      |     16.20      |    12.557     |
-| whisper-medium         |    764     |     1.3      |     11.720     |    11.023     |
-| whisper-large-v3       |    1540    |     1.0      |      7.81      |     9.008     |
-| **distil-large-v3-fr** |  **756**   |   **5.9**    |    **9.34**    |   **11.13**   |
+| whisper-tiny           |    37.8    |     4.7      |     43.7       |    28.2       |
+| whisper-base           |    72.6    |     3.7      |     30.6       |    18.7       |
+| whisper-small          |    242     |     2.3      |     16.2       |    12.6       |
+| whisper-medium         |    764     |     1.3      |     11.7       |    11.0       |
+| whisper-large-v3       |    1540    |     1.0      |      7.8       |     9.0       |
+| **distil-large-v3-fr** |  **756**   |   **5.9**    |    **9.3**     |   **11.1**    |
 
 *latencies benchmarked to generate 128 tokens on A100 40GB with a batch size of 1. More details about inference performances in [inference speed](#inference-speed) section.   
 *WERs are averaged on the test sets. More details in [short-form](#short-form) and [long-form](#long-form) results sections.