From fc547e14e818772811c3dccd9bb09e45e35df168 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 25 九月 2024 15:26:14 +0800
Subject: [PATCH] bugfix memory leaky

---
 funasr/models/sense_voice/model.py |   16 +++++++++++-----
 1 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/funasr/models/sense_voice/model.py b/funasr/models/sense_voice/model.py
index 1311987..25e9faf 100644
--- a/funasr/models/sense_voice/model.py
+++ b/funasr/models/sense_voice/model.py
@@ -196,13 +196,13 @@
                 "inf"
             )  # float(numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min)
             scores = scores.masked_fill(mask, min_value)
-            self.attn = torch.softmax(scores, dim=-1).masked_fill(
+            attn = torch.softmax(scores, dim=-1).masked_fill(
                 mask, 0.0
             )  # (batch, head, time1, time2)
         else:
-            self.attn = torch.softmax(scores, dim=-1)  # (batch, head, time1, time2)
+            attn = torch.softmax(scores, dim=-1)  # (batch, head, time1, time2)
 
-        p_attn = self.dropout(self.attn)
+        p_attn = self.dropout(attn)
         x = torch.matmul(p_attn, value)  # (batch, head, time1, d_k)
         x = (
             x.transpose(1, 2).contiguous().view(n_batch, -1, self.h * self.d_k)
@@ -644,7 +644,13 @@
         self.embed = torch.nn.Embedding(
             7 + len(self.lid_dict) + len(self.textnorm_dict), input_size
         )
-        self.emo_dict = {"unk": 25009, "happy": 25001, "sad": 25002, "angry": 25003, "neutral": 25004}
+        self.emo_dict = {
+            "unk": 25009,
+            "happy": 25001,
+            "sad": 25002,
+            "angry": 25003,
+            "neutral": 25004,
+        }
 
         self.criterion_att = LabelSmoothingLoss(
             size=self.vocab_size,
@@ -874,7 +880,7 @@
         ctc_logits = self.ctc.log_softmax(encoder_out)
         if kwargs.get("ban_emo_unk", False):
             ctc_logits[:, :, self.emo_dict["unk"]] = -float("inf")
-            
+
         results = []
         b, n, d = encoder_out.size()
         if isinstance(key[0], (list, tuple)):

--
Gitblit v1.9.1