Total duration of training dataset

[changjinhan]

Thank you for your excellent work!

Could you share the duration of the language-specific datasets and the overall total duration used to train OpenVoice V2? For instance:

• English: 10K hours
• Chinese: 5K hours
• Japanese: 3K hours
• Total: 18K hours

Having this information would greatly help us better understand the OpenVoice model and also provide a baseline for our research.