Update README.md

README.md

@@ -4,26 +4,26 @@ tags:
 model-index:
 - name: mHuBERT-147-br
   results: []
+language:
+- br
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
 
 # mHuBERT-147-br
 
-This model was trained from scratch on the None dataset.
+This model was fine-tuned on the Mozilla Common Voice 15 Breton dataset and the [Roadennoù](https://github.com/gweltou/roadennou) dataset.
 
 ## Model description
 
-More information needed
+This model was trained to assess the performance mHubert-147 for finetuning a Breton ASR model. 
 
 ## Intended uses & limitations
 
-More information needed
+This model is a research model and shouldn't be used in production.
 
 ## Training and evaluation data
 
-More information needed
+90% of the Roadennoù dataset was used for training, the remaining 10% was used for validation in addition to MCV15-br validation dataset.
 
 ## Training procedure
 
@@ -47,4 +47,4 @@ The following hyperparameters were used during training:
 - Transformers 4.39.1
 - Pytorch 2.0.1+cu117
 - Datasets 2.18.0
-- Tokenizers 0.15.2
+- Tokenizers 0.15.2