From 3d6347d9bc2bf5d4a98614cb9234d40ff13b8035 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 21 四月 2023 19:03:35 +0800
Subject: [PATCH] Merge pull request #395 from alibaba-damo-academy/dev_zly2
---
funasr/models/frontend/wav_frontend.py | 10 +++++-----
1 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/funasr/models/frontend/wav_frontend.py b/funasr/models/frontend/wav_frontend.py
index 203f00e..3661f6b 100644
--- a/funasr/models/frontend/wav_frontend.py
+++ b/funasr/models/frontend/wav_frontend.py
@@ -34,7 +34,7 @@
means = np.array(means_list).astype(np.float)
vars = np.array(vars_list).astype(np.float)
cmvn = np.array([means, vars])
- cmvn = torch.as_tensor(cmvn)
+ cmvn = torch.as_tensor(cmvn, dype=torch.float32)
return cmvn
@@ -47,10 +47,10 @@
dtype = inputs.dtype
frame, dim = inputs.shape
- means = np.tile(cmvn[0:1, :dim], (frame, 1))
- vars = np.tile(cmvn[1:2, :dim], (frame, 1))
- inputs += torch.from_numpy(means).type(dtype).to(device)
- inputs *= torch.from_numpy(vars).type(dtype).to(device)
+ means = cmvn[0:1, :dim]
+ vars = cmvn[1:2, :dim]
+ inputs += means.to(device)
+ inputs *= vars.to(device)
return inputs.type(torch.float32)
--
Gitblit v1.9.1