From 40d1f80030d38b3377a95ead8837e82c67aa59f6 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 12 一月 2024 12:05:08 +0800
Subject: [PATCH] funasr1.0 streaming demo
---
examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py | 31 ++++++++++++++++++++++++++++---
1 files changed, 28 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..01c6c39 100644
--- a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
+++ b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
@@ -4,8 +4,33 @@
# 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")
-model = AutoModel(model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch", model_revision="v2.0.0")
+res = model(input=wav_file,
+ chunk_size=chunk_size,
+ )
+print(res)
-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
+
+#
+# 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)
--
Gitblit v1.9.1