From e30a17cf4e715b3d139fa1e0ba01cda1bcf0f884 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期三, 10 一月 2024 11:23:41 +0800
Subject: [PATCH] update funasr-onnx
---
funasr/models/fsmn_vad/model.py | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/funasr/models/fsmn_vad/model.py b/funasr/models/fsmn_vad/model.py
index ee19558..f6e0488 100644
--- a/funasr/models/fsmn_vad/model.py
+++ b/funasr/models/fsmn_vad/model.py
@@ -9,7 +9,7 @@
from typing import Optional
import time
from funasr.register import tables
-from funasr.utils.load_utils import load_audio_and_text_image_video,extract_fbank
+from funasr.utils.load_utils import load_audio_text_image_video,extract_fbank
from funasr.utils.datadir_writer import DatadirWriter
from torch.nn.utils.rnn import pad_sequence
@@ -544,7 +544,7 @@
else:
# extract fbank feats
time1 = time.perf_counter()
- audio_sample_list = load_audio_and_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000))
+ audio_sample_list = load_audio_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000))
time2 = time.perf_counter()
meta_data["load_data"] = f"{time2 - time1:0.3f}"
speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"),
--
Gitblit v1.9.1