From d80ac2fd2df4e7fb8a28acfa512bb11472b5cc99 Mon Sep 17 00:00:00 2001
From: liugz18 <57401541+liugz18@users.noreply.github.com>
Date: 星期四, 18 七月 2024 21:34:55 +0800
Subject: [PATCH] Rename 'res' in line 514 to avoid with naming conflict with line 365
---
funasr/utils/vad_utils.py | 23 ++++++++++++-----------
1 files changed, 12 insertions(+), 11 deletions(-)
diff --git a/funasr/utils/vad_utils.py b/funasr/utils/vad_utils.py
index 6d95e44..eba48a9 100644
--- a/funasr/utils/vad_utils.py
+++ b/funasr/utils/vad_utils.py
@@ -6,16 +6,17 @@
speech_list = []
speech_lengths_list = []
for i, segment in enumerate(vad_segments):
-
- bed_idx = int(segment[0][0]*16)
- end_idx = min(int(segment[0][1]*16), speech_lengths[0])
- speech_i = speech[0, bed_idx: end_idx]
- speech_lengths_i = end_idx-bed_idx
+
+ bed_idx = int(segment[0][0] * 16)
+ end_idx = min(int(segment[0][1] * 16), speech_lengths[0])
+ speech_i = speech[0, bed_idx:end_idx]
+ speech_lengths_i = end_idx - bed_idx
speech_list.append(speech_i)
speech_lengths_list.append(speech_lengths_i)
feats_pad = pad_sequence(speech_list, batch_first=True, padding_value=0.0)
speech_lengths_pad = torch.Tensor(speech_lengths_list).int()
return feats_pad, speech_lengths_pad
+
def slice_padding_audio_samples(speech, speech_lengths, vad_segments):
speech_list = []
@@ -23,12 +24,13 @@
for i, segment in enumerate(vad_segments):
bed_idx = int(segment[0][0] * 16)
end_idx = min(int(segment[0][1] * 16), speech_lengths)
- speech_i = speech[bed_idx: end_idx]
+ speech_i = speech[bed_idx:end_idx]
speech_lengths_i = end_idx - bed_idx
speech_list.append(speech_i)
speech_lengths_list.append(speech_lengths_i)
-
+
return speech_list, speech_lengths_list
+
def merge_vad(vad_result, max_length=15000):
new_result = []
@@ -37,9 +39,9 @@
if len(time_step) == 0:
return []
bg = 0
- for i in range(len(time_step)-1):
+ for i in range(len(time_step) - 1):
time = time_step[i]
- if time_step[i+1] - bg < max_length:
+ if time_step[i + 1] - bg < max_length:
continue
if time - bg < max_length * 1.5:
new_result.append([bg, time])
@@ -47,8 +49,7 @@
split_num = int(time - bg) // max_length + 1
spl_l = int(time - bg) // split_num
for j in range(split_num):
- new_result.append([bg + j*spl_l, bg + (j+1)*spl_l])
+ new_result.append([bg + j * spl_l, bg + (j + 1) * spl_l])
bg = time
new_result.append([bg, time_step[-1]])
return new_result
-
\ No newline at end of file
--
Gitblit v1.9.1