From 1028a8a036cabd6091fc1a040bbddd565fd3e911 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 10 一月 2024 17:42:53 +0800
Subject: [PATCH] funasr1.0 paraformer_streaming WavFrontendOnline

---
 funasr/utils/load_utils.py |    6 +++---
 1 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.py
index c82987f..39b708a 100644
--- a/funasr/utils/load_utils.py
+++ b/funasr/utils/load_utils.py
@@ -68,7 +68,7 @@
 	array = np.frombuffer((middle_data.astype(dtype) - offset) / abs_max, dtype=np.float32)
 	return array
 
-def extract_fbank(data, data_len = None, data_type: str="sound", frontend=None):
+def extract_fbank(data, data_len = None, data_type: str="sound", frontend=None, **kwargs):
 	# import pdb;
 	# pdb.set_trace()
 	if isinstance(data, np.ndarray):
@@ -83,7 +83,7 @@
 	elif isinstance(data, (list, tuple)):
 		data_list, data_len = [], []
 		for data_i in data:
-			if isinstance(data, np.ndarray):
+			if isinstance(data_i, np.ndarray):
 				data_i = torch.from_numpy(data_i)
 			data_list.append(data_i)
 			data_len.append(data_i.shape[0])
@@ -91,7 +91,7 @@
 	# import pdb;
 	# pdb.set_trace()
 	# if data_type == "sound":
-	data, data_len = frontend(data, data_len)
+	data, data_len = frontend(data, data_len, **kwargs)
 	
 	if isinstance(data_len, (list, tuple)):
 		data_len = torch.tensor([data_len])

--
Gitblit v1.9.1