Update README.md

README.md

@@ -49,11 +49,15 @@ model_id = "litus-ai/whisper-small-ita"
 processor = WhisperProcessor.from_pretrained(model_id)
 model = WhisperForConditionalGeneration.from_pretrained(model_id)
 
-# load dummy dataset and read audio files
+# load Meta voxpopuli in italian
 ds = load_dataset("facebook/voxpopuli", "it", split="test")
-sample = ds[171]["audio"]
+sample = ds[171]["audio"]  # sample having an "[UNINT]" token
 
-input_features = processor(sample["array"], sampling_rate=sample["sampling_rate"], return_tensors="pt").input_features 
+input_features = processor(
+  sample["array"],
+  sampling_rate=sample["sampling_rate"],
+  return_tensors="pt",
+).input_features 
 
 # generate token ids
 predicted_ids = model.generate(input_features)