From 73959c6e8e80a6e735bbb7d63acf942a6e2f652d Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期四, 07 十二月 2023 14:54:25 +0800
Subject: [PATCH] Merge pull request #1157 from alibaba-damo-academy/dev_lhn
---
funasr/models/frontend/wav_frontend.py | 13 ++++++++-----
1 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/funasr/models/frontend/wav_frontend.py b/funasr/models/frontend/wav_frontend.py
index acab13b..f92f322 100644
--- a/funasr/models/frontend/wav_frontend.py
+++ b/funasr/models/frontend/wav_frontend.py
@@ -30,8 +30,8 @@
rescale_line = line_item[3:(len(line_item) - 1)]
vars_list = list(rescale_line)
continue
- means = np.array(means_list).astype(np.float)
- vars = np.array(vars_list).astype(np.float)
+ means = np.array(means_list).astype(np.float32)
+ vars = np.array(vars_list).astype(np.float32)
cmvn = np.array([means, vars])
cmvn = torch.as_tensor(cmvn, dtype=torch.float32)
return cmvn
@@ -145,9 +145,12 @@
feats_lens.append(feat_length)
feats_lens = torch.as_tensor(feats_lens)
- feats_pad = pad_sequence(feats,
- batch_first=True,
- padding_value=0.0)
+ if batch_size == 1:
+ feats_pad = feats[0][None, :, :]
+ else:
+ feats_pad = pad_sequence(feats,
+ batch_first=True,
+ padding_value=0.0)
return feats_pad, feats_lens
def forward_fbank(
--
Gitblit v1.9.1