Update README.md

Added the speaker embeddings model reference.

README.md

@@ -4,14 +4,15 @@ base_model: microsoft/speecht5_tts
 tags:
 - generated_from_trainer
 datasets:
-- voxpopuli-it
+- facebook/voxpopuli
 model-index:
 - name: speecht5_tts-ft-voxpopuli-it
   results: []
+language:
+- it
 ---
 
-<!-- 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. -->
+
 
 # speecht5_tts-ft-voxpopuli-it
 
@@ -21,7 +22,7 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+It uses the speaker embedding model speechbrain/spkrec-xvect-voxceleb
 
 ## Intended uses & limitations
 
@@ -29,7 +30,7 @@ More information needed
 
 ## Training and evaluation data
 
-More information needed
+test_size=0.15
 
 ## Training procedure
 
@@ -61,4 +62,4 @@ The following hyperparameters were used during training:
 - Transformers 4.33.0
 - Pytorch 1.12.1+cu116
 - Datasets 2.14.4
-- Tokenizers 0.12.1
+- Tokenizers 0.12.1