From 9b4e9cc8a0311e5243d69b73ed073e7ea441982e Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 27 三月 2024 16:05:29 +0800
Subject: [PATCH] train update
---
examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py | 18 ++++++++++++++----
1 files changed, 14 insertions(+), 4 deletions(-)
diff --git a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
index 459dfff..f131c8c 100644
--- a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
+++ b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
@@ -6,11 +6,12 @@
from funasr import AutoModel
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="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch", model_revision="v2.0.2")
+model = AutoModel(model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch")
-res = model(input=wav_file, chunk_size=chunk_size, )
+res = model.generate(input=wav_file)
print(res)
+# [[beg1, end1], [beg2, end2], .., [begN, endN]]
+# beg/end: ms
@@ -20,6 +21,7 @@
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 = {}
@@ -28,10 +30,18 @@
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(input=speech_chunk,
+ 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
\ No newline at end of file
--
Gitblit v1.9.1