Update app.py

app.py

@@ -35,24 +35,6 @@ vocabs = dataset.map(
 dataset_vocab = set(vocabs["vocab"][0])
 tokenizer_vocab = {k for k,_ in tokenizer.get_vocab().items()}
 
-replacements = [
-    ('à', 'a'),
-    ('ç', 'c'),
-    ('è', 'e'),
-    ('ë', 'e'),
-    ('í', 'i'),
-    ('ï', 'i'),
-    ('ö', 'o'),
-    ('ü', 'u'),
-]
-
-def cleanup_text(inputs):
-    for src, dst in replacements:
-        inputs["transcription"] = inputs["transcription"].replace(src, dst)
-    return inputs
-
-dataset = dataset.map(cleanup_text)
-
 import os
 import torch
 from speechbrain.inference.speaker import EncoderClassifier
@@ -119,7 +101,7 @@ def predict(text, speaker):
     # input_ids = input_ids[..., :model.config.max_text_positions]
 
     ### ### ### 
-    example = dataset['test'][11]
+    example = dataset['train'][888]
     speaker_embeddings = torch.tensor(example["speaker_embeddings"]).unsqueeze(0)
     
     spectrogram = model.generate_speech(inputs["input_ids"], speaker_embeddings)