Updata readme.md

README.md

@@ -346,7 +346,7 @@ Required parameters:
 
 Optional parameters: see the next section
 - `-lg` | `--linear_gradient`: The cross fade length of two audio slices in seconds. If there is a discontinuous voice after forced slicing, you can adjust this value. Otherwise, it is recommended to use the default value of 0.
-- `-f0p` | `--f0_predictor`: Select a F0 predictor, options are `crepe`, `pm`, `dio`, `harvest`, default value is `pm`(note: f0 mean pooling will be enable when using `crepe`)
+- `-f0p` | `--f0_predictor`: Select a F0 predictor, options are `crepe`, `pm`, `dio`, `harvest`, `rmvpe`, default value is `pm`(note: f0 mean pooling will be enable when using `crepe`)
 - `-a` | `--auto_predict_f0`: automatic pitch prediction, do not enable this when converting singing voices as it can cause serious pitch issues.
 - `-cm` | `--cluster_model_path`: Cluster model or feature retrieval index path, if left blank, it will be automatically set as the default path of these models. If there is no training cluster or feature retrieval, fill in at will.
 - `-cr` | `--cluster_infer_ratio`: The proportion of clustering scheme or feature retrieval ranges from 0 to 1. If there is no training clustering model or feature retrieval, the default is 0.

README_zh_CN.md

@@ -349,7 +349,7 @@ python inference_main.py -m "logs/44k/G_30400.pth" -c "configs/config.json" -n "
 
 可选项部分：部分具体见下一节
 + `-lg` | `--linear_gradient`：两段音频切片的交叉淡入长度，如果强制切片后出现人声不连贯可调整该数值，如果连贯建议采用默认值 0，单位为秒
-+ `-f0p` | `--f0_predictor`：选择 F0 预测器，可选择 crepe,pm,dio,harvest, 默认为 pm（注意：crepe 为原 F0 使用均值滤波器）
++ `-f0p` | `--f0_predictor`：选择 F0 预测器，可选择 crepe,pm,dio,harvest,rmvpe, 默认为 pm（注意：crepe 为原 F0 使用均值滤波器）
 + `-a` | `--auto_predict_f0`：语音转换自动预测音高，转换歌声时不要打开这个会严重跑调
 + `-cm` | `--cluster_model_path`：聚类模型或特征检索索引路径，留空则自动设为各方案模型的默认路径，如果没有训练聚类或特征检索则随便填
 + `-cr` | `--cluster_infer_ratio`：聚类方案或特征检索占比，范围 0-1，若没有训练聚类模型或特征检索则默认 0 即可

inference_main.py

@@ -29,7 +29,7 @@ def main():
     parser.add_argument('-cm', '--cluster_model_path', type=str, default="", help='聚类模型或特征检索索引路径，留空则自动设为各方案模型的默认路径，如果没有训练聚类或特征检索则随便填')
     parser.add_argument('-cr', '--cluster_infer_ratio', type=float, default=0, help='聚类方案或特征检索占比，范围0-1，若没有训练聚类模型或特征检索则默认0即可')
     parser.add_argument('-lg', '--linear_gradient', type=float, default=0, help='两段音频切片的交叉淡入长度，如果强制切片后出现人声不连贯可调整该数值，如果连贯建议采用默认值0，单位为秒')
-    parser.add_argument('-f0p', '--f0_predictor', type=str, default="pm", help='选择F0预测器,可选择crepe,pm,dio,harvest,默认为pm(注意：crepe为原F0使用均值滤波器)')
+    parser.add_argument('-f0p', '--f0_predictor', type=str, default="pm", help='选择F0预测器,可选择crepe,pm,dio,harvest,rmvpe,默认为pm(注意：crepe为原F0使用均值滤波器)')
     parser.add_argument('-eh', '--enhance', action='store_true', default=False, help='是否使用NSF_HIFIGAN增强器,该选项对部分训练集少的模型有一定的音质增强效果，但是对训练好的模型有反面效果，默认关闭')
     parser.add_argument('-shd', '--shallow_diffusion', action='store_true', default=False, help='是否使用浅层扩散，使用后可解决一部分电音问题，默认关闭，该选项打开时，NSF_HIFIGAN增强器将会被禁止')
     parser.add_argument('-usm', '--use_spk_mix', action='store_true', default=False, help='是否使用角色融合')

preprocess_hubert_f0.py

@@ -134,7 +134,7 @@ if __name__ == "__main__":
         '--use_diff',action='store_true', help='Whether to use the diffusion model'
     )
     parser.add_argument(
-        '--f0_predictor', type=str, default="dio", help='Select F0 predictor, can select crepe,pm,dio,harvest, default pm(note: crepe is original F0 using mean filter)'
+        '--f0_predictor', type=str, default="dio", help='Select F0 predictor, can select crepe,pm,dio,harvest,rmvpe, default pm(note: crepe is original F0 using mean filter)'
     )
     parser.add_argument(
         '--num_processes', type=int, default=1, help='You are advised to set the number of processes to the same as the number of CPU cores'

webUI.py

@@ -287,7 +287,7 @@ with gr.Blocks(
                         <font size=2> 推理设置</font>
                         """)
                     auto_f0 = gr.Checkbox(label="自动f0预测，配合聚类模型f0预测效果更好,会导致变调功能失效（仅限转换语音，歌声勾选此项会究极跑调）", value=False)
-                    f0_predictor = gr.Dropdown(label="选择F0预测器,可选择crepe,pm,dio,harvest,默认为pm(注意：crepe为原F0使用均值滤波器)", choices=["pm","dio","harvest","crepe"], value="pm")
+                    f0_predictor = gr.Dropdown(label="选择F0预测器,可选择crepe,pm,dio,harvest,rmvpe,默认为pm(注意：crepe为原F0使用均值滤波器)", choices=["pm","dio","harvest","crepe","rmvpe"], value="pm")
                     vc_transform = gr.Number(label="变调（整数，可以正负，半音数量，升高八度就是12）", value=0)
                     cluster_ratio = gr.Number(label="聚类模型/特征检索混合比例，0-1之间，0即不启用聚类/特征检索。使用聚类/特征检索能提升音色相似度，但会导致咬字下降（如果使用建议0.5左右）", value=0)
                     slice_db = gr.Number(label="切片阈值", value=-40)