From 7012ca2efc130103c4acd24e3678c7ae280f8db4 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 13 十二月 2023 20:08:55 +0800
Subject: [PATCH] funasr2 paraformer biciparaformer contextuaparaformer
---
funasr/models/frontend/wav_frontend.py | 15 +++++++++------
1 files changed, 9 insertions(+), 6 deletions(-)
diff --git a/funasr/models/frontend/wav_frontend.py b/funasr/models/frontend/wav_frontend.py
index acab13b..ac16065 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
@@ -116,7 +116,7 @@
def forward(
self,
input: torch.Tensor,
- input_lengths: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
+ input_lengths) -> Tuple[torch.Tensor, torch.Tensor]:
batch_size = input.size(0)
feats = []
feats_lens = []
@@ -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