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 | 63 ++++++++++++++++++-------------
1 files changed, 37 insertions(+), 26 deletions(-)
diff --git a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
index 01c6c39..f131c8c 100644
--- a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
+++ b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
@@ -4,33 +4,44 @@
# MIT License (https://opensource.org/licenses/MIT)
from funasr import AutoModel
-wav_file = "/Users/zhifu/funasr_github/test_local/asr_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")
+wav_file = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav"
-res = model(input=wav_file,
- chunk_size=chunk_size,
- )
+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_stride = int(chunk_size * 16000 / 1000)
-#
-# cache = {}
-#
-# for i in range(int(len((speech)-1)/chunk_stride+1)):
-# speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
-# is_final = i == int(len((speech)-1)/chunk_stride+1)
-# res = model(input=speech_chunk,
-# cache=cache,
-# is_final=is_final,
-# chunk_size=chunk_size,
-# )
-# print(res)
+
+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
\ No newline at end of file
--
Gitblit v1.9.1