Fix: filter the espeak redundant symbols

app.py

@@ -146,7 +146,8 @@ sampler = DiffusionSampler(
 def inference(text, ref_s, alpha = 0.3, beta = 0.7, diffusion_steps=5, embedding_scale=1):
     text = text.strip()
     ps = vi_phonemizer.phonemize([text])
-    ps = word_tokenize(ps[0])
+    temp = ps[0].replace("(en)", "").replace("(vi)", "").strip()
+    ps = word_tokenize(temp)
     ps = ' '.join(ps)
     ps = ps.replace(" .", ".").replace(" ,", ",").replace(" !", "!").replace(" ?", "?").replace(" :", ":").replace(" ;", ";")
     tokens = textclenaer(ps)