code

README_ZH.md

@@ -306,6 +306,7 @@ eva_conf = {
 |DSD100         |https://sigsep.github.io/datasets/dsd100.html|
 |Aishell-3      |http://www.aishelltech.com/aishell_3|
 |VCTK           |https://datashare.ed.ac.uk/handle/10283/2651|
+|Korean Songs   |http://urisori.co.kr/urisori-en/doku.php/|
 
 ## 代码来源和参考文献
 
@@ -362,10 +363,3 @@ https://github.com/OlaWod/FreeVC/blob/main/preprocess_sr.py
 <a href="https://github.com/PlayVoice/so-vits-svc/graphs/contributors">
   <img src="https://contrib.rocks/image?repo=PlayVoice/so-vits-svc" />
 </a>
-
-## 学习交流群：非一键包
-<div align="center">
-
-![X·SING-QQ](https://github.com/PlayVoice/so-vits-svc-5.0/assets/16432329/dfbb4740-447e-40f0-9193-c974c4b6ceb0)
-
-</div>

hubert/inference.py

@@ -52,9 +52,8 @@ def pred_vec(model, wavPath, vecPath, device):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.description = 'please enter embed parameter ...'
-    parser.add_argument("-w", "--wav", help="wav", dest="wav")
-    parser.add_argument("-v", "--vec", help="vec", dest="vec")
+    parser.add_argument("-w", "--wav", help="wav", dest="wav", required=True)
+    parser.add_argument("-v", "--vec", help="vec", dest="vec", required=True)
     args = parser.parse_args()
     print(args.wav)
     print(args.vec)

pitch/debug.py

@@ -15,8 +15,7 @@ def save_csv_pitch(pitch, path):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.description = 'please enter embed parameter ...'
-    parser.add_argument("-p", "--pit", help="pit", dest="pit")  # pit for train
+    parser.add_argument("-p", "--pit", help="pit", dest="pit", required=True)  # pit for train
     args = parser.parse_args()
     print(args.pit)
 

pitch/inference.py

@@ -121,15 +121,14 @@ def load_csv_pitch(path):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.description = 'please enter embed parameter ...'
-    parser.add_argument("-w", "--wav", help="wav", dest="wav")
-    parser.add_argument("-p", "--pit", help="pit", dest="pit")  # csv for excel
+    parser.add_argument("-w", "--wav", help="wav", dest="wav", required=True)
+    parser.add_argument("-p", "--pit", help="pit", dest="pit", required=True)  # csv for excel
     args = parser.parse_args()
     print(args.wav)
     print(args.pit)
 
     device = "cuda" if torch.cuda.is_available() else "cpu"
     pitch = compute_f0_sing(args.wav, device)
     save_csv_pitch(pitch, args.pit)
-    #tmp = load_csv_pitch(args.pit)
-    #save_csv_pitch(tmp, "tmp.csv")
+    # tmp = load_csv_pitch(args.pit)
+    # save_csv_pitch(tmp, "tmp.csv")

prepare/preprocess_a.py

@@ -32,7 +32,6 @@ def process_files_with_thread_pool(wavPath, spks, outPath, sr, thread_num=None):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.description = 'please enter embed parameter ...'
     parser.add_argument("-w", "--wav", help="wav", dest="wav", required=True)
     parser.add_argument("-o", "--out", help="out", dest="out", required=True)
     parser.add_argument("-s", "--sr", help="sample rate", dest="sr", type=int, required=True)

prepare/preprocess_cdc.py

@@ -29,7 +29,6 @@ def cut_direct_content(iWave, oWave):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.description = 'please enter parameter ...'
     parser.add_argument("-i", help="input path", dest="inPath", required=True)
     parser.add_argument("-o", help="output path", dest="outPath", required=True)
 

prepare/preprocess_crepe.py

@@ -46,7 +46,6 @@ def compute_f0(filename, save, device):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.description = 'please enter embed parameter ...'
     parser.add_argument("-w", "--wav", help="wav", dest="wav", required=True)
     parser.add_argument("-p", "--pit", help="pit", dest="pit", required=True)
 

prepare/preprocess_f0.py

@@ -40,7 +40,6 @@ def process_files_with_process_pool(wavPath, spks, pitPath, process_num=None):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.description = 'please enter embed parameter ...'
     parser.add_argument("-w", "--wav", help="wav", dest="wav", required=True)
     parser.add_argument("-p", "--pit", help="pit", dest="pit", required=True)
     parser.add_argument("-t", "--thread_count", help="thread count to process, set 0 to use all cpu cores", dest="thread_count", type=int, default=1)

prepare/preprocess_f0_mouth.py

@@ -40,7 +40,6 @@ def process_files_with_process_pool(wavPath, spks, pitPath, process_num=None):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.description = 'please enter embed parameter ...'
     parser.add_argument("-w", "--wav", help="wav", dest="wav", required=True)
     parser.add_argument("-p", "--pit", help="pit", dest="pit", required=True)
     parser.add_argument("-t", "--thread_count", help="thread count to process, set 0 to use all cpu cores", dest="thread_count", type=int, default=1)

prepare/preprocess_hubert.py

@@ -34,7 +34,6 @@ def pred_vec(model, wavPath, vecPath, device):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.description = 'please enter embed parameter ...'
     parser.add_argument("-w", "--wav", help="wav", dest="wav", required=True)
     parser.add_argument("-v", "--vec", help="vec", dest="vec", required=True)
 

prepare/preprocess_ppg.py

@@ -41,7 +41,6 @@ def pred_ppg(whisper: Whisper, wavPath, ppgPath):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.description = 'please enter embed parameter ...'
     parser.add_argument("-w", "--wav", help="wav", dest="wav", required=True)
     parser.add_argument("-p", "--ppg", help="ppg", dest="ppg", required=True)
     args = parser.parse_args()

prepare/preprocess_speaker_ave.py

@@ -7,7 +7,6 @@
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.description = 'please enter embed parameter ...'
     parser.add_argument("dataset_speaker", type=str)
     parser.add_argument("dataset_singer", type=str)
 

prepare/preprocess_spec.py

@@ -39,7 +39,6 @@ def process_files_with_thread_pool(wavPath, spks, thread_num):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.description = 'please enter embed parameter ...'
     parser.add_argument("-w", "--wav", help="wav", dest="wav", required=True)
     parser.add_argument("-s", "--spe", help="spe", dest="spe", required=True)
     parser.add_argument("-t", "--thread_count", help="thread count to process, set 0 to use all cpu cores", dest="thread_count", type=int, default=1)

prepare/preprocess_trim.py

@@ -28,7 +28,6 @@ def trim_silence(iWave, oWave):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.description = 'please enter parameter ...'
     parser.add_argument("-i", help="input path", dest="inPath", required=True)
     parser.add_argument("-o", help="output path", dest="outPath", required=True)
 

whisper/inference.py

@@ -64,9 +64,8 @@ def pred_ppg(whisper: Whisper, wavPath, ppgPath, device):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.description = 'please enter embed parameter ...'
-    parser.add_argument("-w", "--wav", help="wav", dest="wav")
-    parser.add_argument("-p", "--ppg", help="ppg", dest="ppg")
+    parser.add_argument("-w", "--wav", help="wav", dest="wav", required=True)
+    parser.add_argument("-p", "--ppg", help="ppg", dest="ppg", required=True)
     args = parser.parse_args()
     print(args.wav)
     print(args.ppg)