Update README.md

README.md

@@ -24,14 +24,14 @@ model-index:
       type: hackathon-pln-es/neutral-es
       name: neutral-es
     metrics:
-      - type: sacrebleu    # Required. Example: wer
-        value: 93.8347  # Required. Example: 20.90
+      - type: sacrebleu
+        value: 0.96  
         name: sacrebleu    # Optional. Example: Test WER
       - type: bertscore    # Required. Example: wer
-        value: 0.99
+        value: 0.98
         name: BertScoreF1    # Optional. Example: Test WER
       - type: DiffBleu    # Required. Example: wer
-        value: 0.38
+        value: 0.35
         name: DiffBleu    # Optional. Example: Test WER
 ---
 
@@ -51,7 +51,7 @@ By using gender inclusive models we can help reducing gender bias in a language
 
 
 ## Training and evaluation data
-One of the major challenges was to obtain a valuable dataset that would suit our purpose, therefore, the team opted to dedicate a considerable amount of time to build it from a scratch.
+
 The data used for the model training has been created form a compilation of sources, obtained from a series of guidelines and manuals issued by Spanish Ministry of Health, Social Services and Equality in the matter of the usage of non-sexist language, stipulated in this linked [document:](https://www.inmujeres.gob.es/servRecursos/formacion/GuiasLengNoSexista/docs/Guiaslenguajenosexista_.pdf):
 
 ### Compiled sources