From 81a5b29804800a4edd76c8dda2727d6fdf4b5643 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期四, 11 五月 2023 17:35:49 +0800
Subject: [PATCH] update repo
---
egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer_online.py | 12 ++++++++----
1 files changed, 8 insertions(+), 4 deletions(-)
diff --git a/egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer_online.py b/egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer_online.py
index 9d12b34..a8cc912 100644
--- a/egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer_online.py
+++ b/egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer_online.py
@@ -1,16 +1,20 @@
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
+from modelscope.utils.logger import get_logger
+import logging
+logger = get_logger(log_level=logging.CRITICAL)
+logger.setLevel(logging.CRITICAL)
import soundfile
-
if __name__ == '__main__':
output_dir = None
inference_pipline = pipeline(
task=Tasks.voice_activity_detection,
model="damo/speech_fsmn_vad_zh-cn-8k-common",
- model_revision='v1.1.9',
- output_dir='./output_dir',
+ model_revision='v1.2.0',
+ output_dir=output_dir,
batch_size=1,
+ mode='online',
)
speech, sample_rate = soundfile.read("./vad_example_8k.wav")
speech_length = speech.shape[0]
@@ -18,7 +22,7 @@
sample_offset = 0
step = 80 * 10
- param_dict = {'in_cache': dict()}
+ param_dict = {'in_cache': dict(), 'max_end_sil': 800}
for sample_offset in range(0, speech_length, min(step, speech_length - sample_offset)):
if sample_offset + step >= speech_length - 1:
step = speech_length - sample_offset
--
Gitblit v1.9.1