init

text/cleaner.py

@@ -0,0 +1,32 @@
+from text import chinese, japanese, english, cleaned_text_to_sequence
+
+
+language_module_map = {
+    'ZH': chinese,
+    "JA": japanese,
+    "EN": english
+}
+
+
+def clean_text(text, language):
+    language_module = language_module_map[language]
+    norm_text = language_module.text_normalize(text)
+    phones, tones, word2ph = language_module.g2p(norm_text)
+    return norm_text, phones, tones, word2ph
+
+def clean_text_bert(text, language):
+    language_module = language_module_map[language]
+    norm_text = language_module.text_normalize(text)
+    phones, tones, word2ph = language_module.g2p(norm_text)
+    bert = language_module.get_bert_feature(norm_text, word2ph)
+    return phones, tones, bert
+
+def text_to_sequence(text, language):
+    _, _, phones, tones = clean_text(text, language)
+    return cleaned_text_to_sequence(phones, tones, language)
+
+if __name__ == '__main__':
+    print(text_to_sequence("你好，啊啊啊额、还是到付红四方。", 'ZH'))
+    print(text_to_sequence("hello", 'EN'))
+
+