Update preprocess_flist_config.py

preprocess_flist_config.py

@@ -7,7 +7,7 @@ from random import shuffle
 import json
 import wave
 
-config_template = json.load(open("configs_template/config_template.json"))
+config_template = json.load(open("configs/config.json"))
 
 pattern = re.compile(r'^[\.a-zA-Z0-9_\/]+$')
 
@@ -25,11 +25,13 @@ if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument("--train_list", type=str, default="./filelists/train.txt", help="path to train list")
     parser.add_argument("--val_list", type=str, default="./filelists/val.txt", help="path to val list")
+    parser.add_argument("--test_list", type=str, default="./filelists/test.txt", help="path to test list")
     parser.add_argument("--source_dir", type=str, default="./dataset/44k", help="path to source dir")
     args = parser.parse_args()
     
     train = []
     val = []
+    test = []
     idx = 0
     spk_dict = {}
     spk_id = 0
@@ -41,19 +43,21 @@ if __name__ == "__main__":
         for file in wavs:
             if not file.endswith("wav"):
                 continue
-            #if not pattern.match(file):
-            #    print(f"warning：文件名{file}中包含非字母数字下划线，可能会导致错误。（也可能不会）")
+            if not pattern.match(file):
+                print(f"warning：文件名{file}中包含非字母数字下划线，可能会导致错误。（也可能不会）")
             if get_wav_duration(file) < 0.3:
                 print("skip too short audio:", file)
                 continue
             new_wavs.append(file)
         wavs = new_wavs
         shuffle(wavs)
-        train += wavs[2:]
+        train += wavs[2:-2]
         val += wavs[:2]
+        test += wavs[-2:]
 
     shuffle(train)
     shuffle(val)
+    shuffle(test)
             
     print("Writing", args.train_list)
     with open(args.train_list, "w") as f:
@@ -66,10 +70,14 @@ if __name__ == "__main__":
         for fname in tqdm(val):
             wavpath = fname
             f.write(wavpath + "\n")
+            
+    print("Writing", args.test_list)
+    with open(args.test_list, "w") as f:
+        for fname in tqdm(test):
+            wavpath = fname
+            f.write(wavpath + "\n")
 
     config_template["spk"] = spk_dict
-    config_template["model"]["n_speakers"] = spk_id
-	
     print("Writing configs/config.json")
     with open("configs/config.json", "w") as f:
         json.dump(config_template, f, indent=2)