From 28a19dbc4e85d3b8a4ec2ef7483bba64d422b43f Mon Sep 17 00:00:00 2001
From: aky15 <ankeyu.aky@11.17.44.249>
Date: 星期三, 12 四月 2023 18:03:06 +0800
Subject: [PATCH] Merge remote-tracking branch 'origin/main' into dev_aky

---
 funasr/tasks/diar.py |   23 +++++++++++++++++++----
 1 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/funasr/tasks/diar.py b/funasr/tasks/diar.py
index 6204cb7..096a5c8 100644
--- a/funasr/tasks/diar.py
+++ b/funasr/tasks/diar.py
@@ -507,7 +507,7 @@
             config_file: Union[Path, str] = None,
             model_file: Union[Path, str] = None,
             cmvn_file: Union[Path, str] = None,
-            device: str = "cpu",
+            device: Union[str, torch.device] = "cpu",
     ):
         """Build model from the files.
 
@@ -553,7 +553,7 @@
                 if ".bin" in model_name:
                     model_name_pth = os.path.join(model_dir, model_name.replace('.bin', '.pb'))
                 else:
-                    model_name_pth = os.path.join(model_dir, "{}.pth".format(model_name))
+                    model_name_pth = os.path.join(model_dir, "{}.pb".format(model_name))
                 if os.path.exists(model_name_pth):
                     logging.info("model_file is load from pth: {}".format(model_name_pth))
                     model_dict = torch.load(model_name_pth, map_location=device)
@@ -562,12 +562,27 @@
                 model.load_state_dict(model_dict)
             else:
                 model_dict = torch.load(model_file, map_location=device)
+        model_dict = cls.fileter_model_dict(model_dict, model.state_dict())
         model.load_state_dict(model_dict)
         if model_name_pth is not None and not os.path.exists(model_name_pth):
             torch.save(model_dict, model_name_pth)
             logging.info("model_file is saved to pth: {}".format(model_name_pth))
 
         return model, args
+
+    @classmethod
+    def fileter_model_dict(cls, src_dict: dict, dest_dict: dict):
+        from collections import OrderedDict
+        new_dict = OrderedDict()
+        for key, value in src_dict.items():
+            if key in dest_dict:
+                new_dict[key] = value
+            else:
+                logging.info("{} is no longer needed in this model.".format(key))
+        for key, value in dest_dict.items():
+            if key not in new_dict:
+                logging.warning("{} is missed in checkpoint.".format(key))
+        return new_dict
 
     @classmethod
     def convert_tf2torch(
@@ -787,10 +802,10 @@
             cls, train: bool = True, inference: bool = False
     ) -> Tuple[str, ...]:
         if not inference:
-            retval = ("speech", "profile", "binary_labels")
+            retval = ("speech", )
         else:
             # Recognition mode
-            retval = ("speech")
+            retval = ("speech", )
         return retval
 
     @classmethod

--
Gitblit v1.9.1