From 55c09aeaa25b4bb88a50e09ba68fa6ff00a6d676 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期一, 15 一月 2024 20:10:39 +0800
Subject: [PATCH] update readme, fix seaco bug
---
examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py | 16 ++++++++--------
1 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
index 6761a80..459dfff 100644
--- a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
+++ b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
@@ -7,11 +7,9 @@
wav_file = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav"
chunk_size = 60000 # ms
-model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/speech_fsmn_vad_zh-cn-16k-common-streaming", model_revision="v2.0.0")
+model = AutoModel(model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch", model_revision="v2.0.2")
-res = model(input=wav_file,
- chunk_size=chunk_size,
- )
+res = model(input=wav_file, chunk_size=chunk_size, )
print(res)
@@ -22,16 +20,18 @@
wav_file = os.path.join(model.model_path, "example/vad_example.wav")
speech, sample_rate = soundfile.read(wav_file)
-chunk_stride = int(chunk_size * 16000 / 1000)
+chunk_stride = int(chunk_size * sample_rate / 1000)
cache = {}
-for i in range(int(len((speech)-1)/chunk_stride+1)):
+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 == int(len((speech)-1)/chunk_stride+1) - 1
+ is_final = i == total_chunk_num - 1
res = model(input=speech_chunk,
cache=cache,
is_final=is_final,
chunk_size=chunk_size,
)
- print(res)
+ if len(res[0]["value"]):
+ print(res)
--
Gitblit v1.9.1