From 28ccfbfc51068a663a80764e14074df5edf2b5ba Mon Sep 17 00:00:00 2001
From: kongdeqiang <kongdeqiang960204@163.com>
Date: 星期五, 13 三月 2026 17:41:41 +0800
Subject: [PATCH] 提交

---
 funasr/train_utils/average_nbest_models.py |   51 ++++++++++++++++++++++++++++++++++-----------------
 1 files changed, 34 insertions(+), 17 deletions(-)

diff --git a/funasr/train_utils/average_nbest_models.py b/funasr/train_utils/average_nbest_models.py
index 013a719..873f419 100644
--- a/funasr/train_utils/average_nbest_models.py
+++ b/funasr/train_utils/average_nbest_models.py
@@ -16,51 +16,68 @@
 from functools import cmp_to_key
 
 
-
-def _get_checkpoint_paths(output_dir: str, last_n: int=5):
+def _get_checkpoint_paths(output_dir: str, last_n: int = 5, use_deepspeed=False, **kwargs):
     """
     Get the paths of the last 'last_n' checkpoints by parsing filenames
     in the output directory.
     """
     try:
-        checkpoint = torch.load(os.path.exists(os.path.join(output_dir, "model.pt")), map_location="cpu")
+        if not use_deepspeed:
+            checkpoint = torch.load(os.path.join(output_dir, "model.pt"), map_location="cpu")
+        else:
+            checkpoint = torch.load(
+                os.path.join(output_dir, "model.pt", "mp_rank_00_model_states.pt"),
+                map_location="cpu",
+            )
         avg_keep_nbest_models_type = checkpoint["avg_keep_nbest_models_type"]
-        val_step_or_eoch = checkpoint[f"val_{avg_keep_nbest_models_type}_step_or_eoch"]
-        sorted_items = sorted(saved_ckpts.items(), key=lambda x: x[1], reverse=True)
-        sorted_items = sorted_items[:last_n] if avg_keep_nbest_models_type == "acc" else sorted_items[-last_n:]
-        checkpoint_paths = [os.path.join(output_dir, key) for key, value in sorted_items[:last_n]]
+        val_step_or_epoch = checkpoint[f"val_{avg_keep_nbest_models_type}_step_or_epoch"]
+        sorted_items = sorted(val_step_or_epoch.items(), key=lambda x: x[1], reverse=True)
+        sorted_items = (
+            sorted_items[:last_n] if avg_keep_nbest_models_type == "acc" else sorted_items[-last_n:]
+        )
+        checkpoint_paths = []
+        for key, value in sorted_items[:last_n]:
+            if not use_deepspeed:
+                ckpt = os.path.join(output_dir, key)
+            else:
+                ckpt = os.path.join(output_dir, key, "mp_rank_00_model_states.pt")
+            checkpoint_paths.append(ckpt)
+
     except:
+        print(f"{checkpoint} does not exist, avg the lastet checkpoint.")
         # List all files in the output directory
         files = os.listdir(output_dir)
         # Filter out checkpoint files and extract epoch numbers
         checkpoint_files = [f for f in files if f.startswith("model.pt.e")]
         # Sort files by epoch number in descending order
-        checkpoint_files.sort(key=lambda x: int(re.search(r'(\d+)', x).group()), reverse=True)
+        checkpoint_files.sort(key=lambda x: int(re.search(r"(\d+)", x).group()), reverse=True)
         # Get the last 'last_n' checkpoint paths
         checkpoint_paths = [os.path.join(output_dir, f) for f in checkpoint_files[:last_n]]
+
     return checkpoint_paths
 
+
 @torch.no_grad()
-def average_checkpoints(output_dir: str, last_n: int=5, **kwargs):
+def average_checkpoints(output_dir: str, last_n: int = 5, **kwargs):
     """
     Average the last 'last_n' checkpoints' model state_dicts.
     If a tensor is of type torch.int, perform sum instead of average.
     """
-    checkpoint_paths = _get_checkpoint_paths(output_dir, last_n)
+    checkpoint_paths = _get_checkpoint_paths(output_dir, last_n, **kwargs)
     print(f"average_checkpoints: {checkpoint_paths}")
     state_dicts = []
 
     # Load state_dicts from checkpoints
     for path in checkpoint_paths:
         if os.path.isfile(path):
-            state_dicts.append(torch.load(path, map_location='cpu')['state_dict'])
+            state_dicts.append(torch.load(path, map_location="cpu")["state_dict"])
         else:
             print(f"Checkpoint file {path} not found.")
-            continue
 
     # Check if we have any state_dicts to average
-    if not state_dicts:
-        raise RuntimeError("No checkpoints found for averaging.")
+    if len(state_dicts) < 1:
+        print("No checkpoints found for averaging.")
+        return
 
     # Average or sum weights
     avg_state_dict = OrderedDict()
@@ -75,6 +92,6 @@
             # Perform average for other types of tensors
             stacked_tensors = torch.stack(tensors)
             avg_state_dict[key] = torch.mean(stacked_tensors, dim=0)
-    
-    torch.save({'state_dict': avg_state_dict}, os.path.join(output_dir, f"model.pt.avg{last_n}"))
-    return avg_state_dict
\ No newline at end of file
+    checkpoint_outpath = os.path.join(output_dir, f"model.pt.avg{last_n}")
+    torch.save({"state_dict": avg_state_dict}, checkpoint_outpath)
+    return checkpoint_outpath

--
Gitblit v1.9.1