From 681868deae142875570d8efd6433a8b4e8227f6a Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 14 三月 2023 14:43:32 +0800
Subject: [PATCH] Merge pull request #225 from alibaba-damo-academy/dev_zly
---
egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer_online.py | 5 +++--
egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/infer.py | 2 +-
egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/infer_online.py | 5 +++--
egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer.py | 4 ++--
4 files changed, 9 insertions(+), 7 deletions(-)
diff --git a/egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/infer.py b/egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/infer.py
index c255474..2bf3251 100644
--- a/egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/infer.py
+++ b/egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/infer.py
@@ -7,7 +7,7 @@
inference_pipline = pipeline(
task=Tasks.voice_activity_detection,
model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
- model_revision=None,
+ model_revision='v1.2.0',
output_dir=output_dir,
batch_size=1,
)
diff --git a/egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/infer_online.py b/egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/infer_online.py
index bcf764b..66b8161 100644
--- a/egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/infer_online.py
+++ b/egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/infer_online.py
@@ -8,9 +8,10 @@
inference_pipline = pipeline(
task=Tasks.voice_activity_detection,
model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
- model_revision='v1.1.9',
- output_dir=None,
+ model_revision='v1.2.0',
+ output_dir=output_dir,
batch_size=1,
+ mode='online',
)
speech, sample_rate = soundfile.read("./vad_example_16k.wav")
speech_length = speech.shape[0]
diff --git a/egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer.py b/egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer.py
index 71af486..2e50275 100644
--- a/egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer.py
+++ b/egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/infer.py
@@ -7,8 +7,8 @@
inference_pipline = pipeline(
task=Tasks.voice_activity_detection,
model="damo/speech_fsmn_vad_zh-cn-8k-common",
- model_revision=None,
- output_dir='./output_dir',
+ model_revision='v1.2.0',
+ output_dir=output_dir,
batch_size=1,
)
segments_result = inference_pipline(audio_in=audio_in)
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..abf4ef5 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
@@ -8,9 +8,10 @@
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]
--
Gitblit v1.9.1