Refine the multilingual front-end processing for TTS (open-mmlab#137)

Refine the multilingual front-end processing for TTS

config/tts.json

@@ -8,7 +8,7 @@
   ],
   "task_type": "tts",
   "preprocess": {
-    "language": "en-us",
+    "language": "en-us", //  espeak supports 100 languages https://github.com/espeak-ng/espeak-ng/blob/master/docs/languages.md
     // linguistic features
     "extract_phone": true,
     "phone_extractor": "espeak", // "espeak, pypinyin, pypinyin_initials_finals, lexicon (only for language=en-us right now)"

processors/phone_extractor.py

@@ -40,7 +40,9 @@ def __init__(self, cfg, dataset_name=None, phone_symbol_file=None):
             "pypinyin",
             "pypinyin_initials_finals",
         ]:
-            self.g2p_module = G2PModule(backend=cfg.preprocess.phone_extractor)
+            self.g2p_module = G2PModule(
+                backend=cfg.preprocess.phone_extractor, language=cfg.preprocess.language
+            )
         elif cfg.preprocess.phone_extractor == "lexicon":
             assert cfg.preprocess.lexicon_path != ""
             self.g2p_module = LexiconModule(cfg.preprocess.lexicon_path)

text/g2p_module.py

@@ -98,6 +98,9 @@ def phonemize(
 class G2PModule:
     """Phonemize Text."""
 
+    # We support espeak to extract IPA (International Phonetic Alphabet), which supports 100 languages,
+    # https://github.com/espeak-ng/espeak-ng/blob/master/docs/languages.md
+
     def __init__(
         self,
         language="en-us",
@@ -144,6 +147,10 @@ def _initialize_backend(
                 words_mismatch=words_mismatch,
             )
         elif backend in ["pypinyin", "pypinyin_initials_finals"]:
+            if language != "cmn":
+                raise ValueError(
+                    f"{language} is not supported for pypinyin and pypinyin_initials_finals."
+                )
             return PypinyinBackend(
                 backend=backend,
                 punctuation_marks=punctuation_marks + self.separator.word,