Update README.md

README.md

@@ -27,24 +27,24 @@ Evaluation results
 
 | **class**      | **precision (%)** | **recall (%)** | **f1 (%)** | **support (#sub-word)** |
 | :------------: | :---------------: | :------------: | :--------: | :---------------------: |
-| **global**     | 98.35             | 98.36          | 98.35      | 492'243                 |
-| **PER**        | 96.22             | 97.41          | 96.81      | 27'842                  |
-| **LOC**        | 93.93             | 93.50          | 93.72      | 31'431                  |
-| **ORG**        | 85.13             | 87.08          | 86.10      | 7'662                   |
-| **MISC**       | 88.55             | 81.84          | 85.06      | 13'553                  |
-| **O**          | 99.40             | 99.55          | 99.47      | 411'755                 |
+| **global**     | 98.17             | 98.19          | 98.18      | 378'776                 |
+| **PER**        | 96.78             | 96.87          | 96.82      | 23'754                  |
+| **LOC**        | 94.05             | 93.59          | 93.82      | 27'196                  |
+| **ORG**        | 86.05             | 85.92          | 85.98      | 6'526                   |
+| **MISC**       | 88.78             | 84.69          | 86.69      | 11'891                  |
+| **O**          | 99.26             | 99.47          | 99.37      | 309'409                 |
 
 Benchmark
 ---------
 
-This model performance is compared to 2 reference models (see below) with the metric [MCC (Matthews Correlation Coefficient)](https://en.wikipedia.org/wiki/Phi_coefficient). The score is given with a factor x100 and the delta gain with DistilCamemBERT-NER used in reference is in parantheses. For the mean inference time measure, an AMD Ryzen 5 4500U @ 2.3GHz with 6 cores was used:
+This model performance is compared to 3 reference models (see below) with the metric f1 score. For the mean inference time measure, an AMD Ryzen 5 4500U @ 2.3GHz with 6 cores was used:
 
-| **model**                                                                                                         | **time (ms)**      | **PER**          | **LOC**          | **ORG**          | **MISC**         | **O**            |
+| **model**                                                                                                         | **time (ms)** | **PER (%)** | **LOC (%)** | **ORG (%)**         | **MISC (%)**        | **O (%)**           |
 | :---------------------------------------------------------------------------------------------------------------: | :----------------: | :--------------: | :--------------: | :--------------: | :--------------: | :------------- : |
-| [cmarkea/distilcamembert-base-ner](https://huggingface.co/cmarkea/distilcamembert-base-ner)                       | **43.44**          | **93.91**        | **88.26**        | **84.03**        | **82.74**        | **91.45**        |
-| [Davlan/bert-base-multilingual-cased-ner-hrl](https://huggingface.co/Davlan/bert-base-multilingual-cased-ner-hrl) | 87.56<br/>(+102%)  | 79.93<br/>(-15%) | 70.39<br/>(-22%) | 60.26<br/>(-28%) | n/a<br/>(n/a%)   | 69.95<br/>(-24%) |
-| [flair/ner-french](https://huggingface.co/flair/ner-french)                                                       | 314.96<br/>(+625%) | 80.18<br/>(-15%) | 72.11<br/>(-18%) | 67.29<br/>(-20%) | 72.39<br/>(-17%) | 74.34<br/>(-19%) |
-<!--- | [Jean-Baptiste/camembert-ner](https://huggingface.co/Jean-Baptiste/camembert-ner)                                 | 83.70<br/>(+93%)   | 95.20<br/>(+1%)  | 90.85<br/>(+3%)  | 89.50<br/>(+6%)  | 89.02<br/>(+8%)  | 92.86<br/>(+2%)  | problème de sur-apprentissage car pas moyen de savoir quelles sont les observations d'éval  --->
+| [cmarkea/distilcamembert-base-ner](https://huggingface.co/cmarkea/distilcamembert-base-ner)                       | **43.44** | 96.82 | 93.82 | 85.98 | 86.69 | 99.37 |
+| [Jean-Baptiste/camembert-ner](https://huggingface.co/Jean-Baptiste/camembert-ner)                                 | 88.49  | **98.82** | **97.35** | **95.03** | **95.34** | **99.67** |
+| [Davlan/bert-base-multilingual-cased-ner-hrl](https://huggingface.co/Davlan/bert-base-multilingual-cased-ner-hrl) | 87.56  | 79.93 | 72.89 | 61.34 | n/a   | 96.04 |
+| [flair/ner-french](https://huggingface.co/flair/ner-french)                                                       | 314.96 | 83.55 | 78.13 | 74.19 | 77.13 | 97.88 |
 
 How to use DistilCamemBERT-NER
 ------------------------------