ENH: Support fish speech reference audio

[codingl2k1]

• Fixes: Fish-Speech启用reference-audio #2532

[qinxuye]

Is reference_audio in fish equivalent to prompt_speech in cosyvoice? I wonder if it's possible to reuse the option?

[codingl2k1]

Is reference_audio in fish equivalent to prompt_speech in cosyvoice? I wonder if it's possible to reuse the option?

We can reuse the option, then users will need to pass prompt_speech instead of reference_audio. I am not sure which name is better.

[qinxuye]

Is reference_audio in fish equivalent to prompt_speech in cosyvoice? I wonder if it's possible to reuse the option?

We can reuse the option, then users will need to pass prompt_speech instead of reference_audio. I am not sure which name is better.

Yeah, we can unify the APIs since prompt_speech is added already, we can add it in doc that it can be used as reference_audio for fish speech.

[codingl2k1]

Is reference_audio in fish equivalent to prompt_speech in cosyvoice? I wonder if it's possible to reuse the option?

We can reuse the option, then users will need to pass prompt_speech instead of reference_audio. I am not sure which name is better.

Yeah, we can unify the APIs since prompt_speech is added already, we can add it in doc that it can be used as reference_audio for fish speech.

I will fix it.