CosyVoice
CosyVoice copied to clipboard
Mispronunciations in Japanese TTS results / 日语TTS出现拼读错误
Locally deployed on my MACBookPro (M2 chip). Results: cozyvoice_results.zip
- Input text: 自民党は、岸田総理大臣の後任を選ぶ総裁選挙について、9月12日に告示し、27日に投開票を行うことを決めました。総裁選挙の期間は、いまの規程が設けられて以降、最も長くなります。 Cozyvoice result: audio1.wav
Issues: There are 6 mispronunciations occurred in the result. I have marked with BOLD font.
- Input text: 晴子、お前が見つけてきた変な男は、湘北に必要な男になったぞ Cozyvoice result: audio2.wav
Issues: '晴子' was wrong and not sure what it said. Only the middle part remains. The last part was missing.
- Input text: 自分がバスケの試合をしている時も、そうでない時も、心が折れそうな自分を奮起させる最高の名言です。この言葉から、何度も力を貰いました。 Cozyvoice result: audio3.wav
Issues: 4 mispronunciations occurred in the result. I have marked with BOLD font.
In conclusion, this result means cozyvoice is basically unusable for Japanese language. The mispronunciation issue looks quite strange. These are all simple words in Japanese. Is it caused by the polluted original Japanese training material? Is there any improvement plan for Japanese capability?
*BTW, Chinese TTS result is great (wow!)