Update README.md

README.md

@@ -52,7 +52,8 @@ with torch.no_grad():
 
 prediction_ids = torch.argmax(logits, dim=-1)
 transcription = processor.batch_decode(prediction_ids)
-# => 'bien y qué regalo vas a abrir primero'
+# => 'm ɪ a n n o f a tː o ʊ n o f f ɛ r t a k e n o n p o t e v o p r ɔ p r i o r i f j ʊ t a r e'
+# for "Mi hanno fatto un\'offerta che non potevo proprio rifiutare."
 ```
 
 ## Evaluation
@@ -103,7 +104,7 @@ out = ds.map(decode, remove_columns=ds.column_names)
 per = wer.compute(predictions=out["prediction"], references=out["target"])                 
 
 print("per", per)  
-# -> should give per 0.06685252146070828
+# -> should give per 0.06685252146070828 - compare to results below
 ```
 
 # Contribution
@@ -114,6 +115,8 @@ The model was contributed by [cywang](https://huggingface.co/cywang) and [patric
 
 The official license can be found [here](https://github.com/microsoft/UniSpeech/blob/main/LICENSE)
 
+# Official Results
+
 See *UniSpeeech-L^{+}* - *it*:
 
 ![design](https://raw.githubusercontent.com/patrickvonplaten/scientific_images/master/unispeech_results.png)