Update README.md

README.md

@@ -52,6 +52,14 @@ The full dataset being prohibitively large, we used [mosaicml streaming dataset]
 The French ASR datasets lacked a publicly available dataset of real call-center conditions, akin to the Switchboard dataset in English.
 To address this gap, we filtered and cleaned the [Accueil_UBS dataset sourced from Ortolang](https://huggingface.co/datasets/BrunoHays/UBS). This preparation enabled the evaluation of ASR models under conditions similar to those encountered in call-center environments.
 
+| Model                                            | librispeech | voxpopuli | fleurs | Accueil_UBS | Common Voice | TEDX | TEDX long form |
+|--------------------------------------------------|-------------|-----------|--------|-------------|--------------|------|----------------|
+| google-latest-long                               |             | 0.14      |        | 0.31        | 0.08         | 0.2  |                |
+| azure                                            | 0.27        | 0.14      | 0.08   | 0.3         | 0.08         | 0.23 |                |
+| [Whisper-large-v3](https://huggingface.co/openai/whisper-large-v3)                                 | 0.05        | 0.1       | 0.05   | 0.3         | 0.13         | 0.2  | 0.11           |
+| [whisper-large-v3-french-distil-dec16](https://huggingface.co/bofenghuang/whisper-large-v3-french-distil-dec16) | **0.04**        | **0.08**      | 0.05   | 0.25        | **0.04**         | **0.1**  | 0.09           |
+| **whisper-large-v3-french-illuin**         | **0.04**        | **0.08**      | **0.04**   | **0.2**         | 0.07         | **0.1**  | **0.08**           |
+
 # Inference
 
 We offer the model in various formats to ensure compatibility with the most widely used inference frameworks.