Update extract_feature_print.py

extract_feature_print.py

@@ -5,6 +5,32 @@ from torch import nn
 import torch
 
 import json
+os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"
+os.environ["PYTORCH_MPS_HIGH_WATERMARK_RATIO"] = "0.0"
+
+device=sys.argv[1]
+n_part = int(sys.argv[2])
+i_part = int(sys.argv[3])
+if len(sys.argv) == 6:
+    exp_dir = sys.argv[4]
+    version = sys.argv[5]
+else:
+    i_gpu = sys.argv[4]
+    exp_dir = sys.argv[5]
+    os.environ["CUDA_VISIBLE_DEVICES"] = str(i_gpu)
+    version = sys.argv[6]
+import torch
+import torch.nn.functional as F
+import soundfile as sf
+import numpy as np
+from fairseq import checkpoint_utils
+
+#device = "cpu"
+if torch.cuda.is_available():
+    device = "cuda"
+elif torch.backends.mps.is_available():
+    device = "mps"
+    
 version_config_paths = [
     os.path.join("/kaggle/working/Mangio-RVC-Fork/configs", "32k.json"),
     os.path.join("/kaggle/working/Mangio-RVC-Fork/configs", "40k.json"),
@@ -82,7 +108,7 @@ class Config:
         if not version_config_paths:
             raise FileNotFoundError("No configuration paths provided.")
 
-        full_config_path = os.path.join("rvc", "configs", version_config_paths[0])
+        full_config_path = os.path.join("/kaggle/working/Mangio-RVC-Fork/configs", version_config_paths[0])
         try:
             with open(full_config_path, "r") as f:
                 config = json.load(f)
@@ -137,32 +163,6 @@ class HubertModelWithFinalProj(HubertModel):
         super().__init__(config)
         self.final_proj = nn.Linear(config.hidden_size, config.classifier_proj_size)
 
-os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"
-os.environ["PYTORCH_MPS_HIGH_WATERMARK_RATIO"] = "0.0"
-
-device=sys.argv[1]
-n_part = int(sys.argv[2])
-i_part = int(sys.argv[3])
-if len(sys.argv) == 6:
-    exp_dir = sys.argv[4]
-    version = sys.argv[5]
-else:
-    i_gpu = sys.argv[4]
-    exp_dir = sys.argv[5]
-    os.environ["CUDA_VISIBLE_DEVICES"] = str(i_gpu)
-    version = sys.argv[6]
-import torch
-import torch.nn.functional as F
-import soundfile as sf
-import numpy as np
-from fairseq import checkpoint_utils
-
-#device = "cpu"
-if torch.cuda.is_available():
-    device = "cuda"
-elif torch.backends.mps.is_available():
-    device = "mps"
-
 f = open("%s/extract_f0_feature.log" % exp_dir, "a+")
 
 
@@ -216,13 +216,13 @@ models, saved_cfg, task = checkpoint_utils.load_model_ensemble_and_task(
 )
 if Custom_Embed == False:
     model = models[0]
+    if device not in ["mps", "cpu"]:
+        model = model.half()
 else:
     dtype = torch.float16 if config.is_half and "cuda" in device else torch.float32
     model = HubertModelWithFinalProj.from_pretrained("/kaggle/working/Mangio-RVC-Fork/Custom/").to(dtype).to(device)
 model = model.to(device)
 printt("move model to %s" % device)
-if device not in ["mps", "cpu"]:
-    model = model.half()
 model.eval()
 
 todo = sorted(list(os.listdir(wavPath)))[i_part::n_part]