You're looking at a specific version of this model. Jump to the model overview.

archcollege /voice:7aac3754

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
train_audio
string
请输入要训练的声音文件.建议10-20分钟
total_epoch
integer
20
总训练轮数
if_f0_3
boolean
False
模型是否带音高指导(唱歌一定要, 语音可以不要)
f0method8
string (enum)
harvest

Options:

pm, harvest, dio, rmvpe, rmvpe_gpu

选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢,rmvpe效果最好且微吃CPU/GPU
if_cache_gpu17
boolean
False
是否缓存所有训练集至显存. 10min以下小数据可缓存以加速训练, 大数据缓存会炸显存也加不了多少速
audio_pth
string
(推理音频用)请输入训练好的声音模型
audio
string
(推理音频用)请输入需要合成的声音源文件

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}