espnet2.text.phoneme_tokenizer.pyopenjtalk_g2p_accent

source

espnet2.text.phoneme_tokenizer.pyopenjtalk_g2p_accent(text) → List[str]

Convert input text to phonemes with accent information.

This function uses the PyOpenJTalk library to extract phonemes from input text while also incorporating accentuation details. It returns a list of phonemes, each represented as a string, where the accent type and position are included.

• Parameters:text (str) – The input text to be converted into phonemes.
• Returns: A list of phonemes with accent information.
• Return type: List[str]

Examples

>>> pyopenjtalk_g2p_accent("こんにちは。")
['k', 'o', 'N', 'n', 'i', 'ch', 'i', 'w', 'a']

NOTE

This function assumes that the input text is in Japanese.