GPT-SoVITS
GPT-SoVITS copied to clipboard
不懂就问,fast_inference分支里api调用的parallel_infer,repetition_penalty,split_bucket分别起到什么效果?
"parallel_infer": True, # bool.(optional) whether to use parallel inference. "repetition_penalty": 1.35 # float.(optional) repetition penalty for T2S model. "split_bucket": true, # bool.(optional) whether to split the batch into multiple buckets
我自己实测了一下,parallel_infer和split_bucket设置为true之后整个程序流程耗时其实差不多,156句话分别是420秒左右完成,跑了好几次,这两个参数设置为true会让程序跑得更快对吗?为啥实际上好像没效果。另外repetition_penalty是起到什么作用?