From 28ccfbfc51068a663a80764e14074df5edf2b5ba Mon Sep 17 00:00:00 2001
From: kongdeqiang <kongdeqiang960204@163.com>
Date: 星期五, 13 三月 2026 17:41:41 +0800
Subject: [PATCH] 提交
---
examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py | 44 +++++++++++++++++++++++++++++++++++++++++---
1 files changed, 41 insertions(+), 3 deletions(-)
diff --git a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
index 2a157ee..21ce0cb 100644
--- a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
+++ b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
@@ -5,7 +5,45 @@
from funasr import AutoModel
-model = AutoModel(model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch", model_revision="v2.0.0")
+wav_file = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav"
-res = model(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav")
-print(res)
\ No newline at end of file
+model = AutoModel(model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch")
+
+res = model.generate(input=wav_file)
+print(res)
+
+# [[beg1, end1], [beg2, end2], .., [begN, endN]]
+# beg/end: ms
+
+
+import soundfile
+import os
+
+wav_file = os.path.join(model.model_path, "example/vad_example.wav")
+speech, sample_rate = soundfile.read(wav_file)
+
+chunk_size = 200 # ms
+chunk_stride = int(chunk_size * sample_rate / 1000)
+
+cache = {}
+
+total_chunk_num = int(len((speech) - 1) / chunk_stride + 1)
+for i in range(total_chunk_num):
+ speech_chunk = speech[i * chunk_stride : (i + 1) * chunk_stride]
+ is_final = i == total_chunk_num - 1
+ res = model.generate(
+ input=speech_chunk,
+ cache=cache,
+ is_final=is_final,
+ chunk_size=chunk_size,
+ disable_pbar=True,
+ )
+ # print(res)
+ if len(res[0]["value"]):
+ print(res)
+
+
+# 1. [[beg1, end1], [beg2, end2], .., [begN, endN]]; [[beg, end]]; [[beg1, end1], [beg2, end2]]
+# 2. [[beg, -1]]
+# 3. [[-1, end]]
+# beg/end: ms
--
Gitblit v1.9.1