From d3d2fe73c08ee51d3a44d7ffb7b31eff32b60404 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 18 三月 2024 20:46:23 +0800
Subject: [PATCH] wav fronend

---
 examples/industrial_data_pretraining/whisper/demo_from_openai.py |    7 +++++--
 1 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/examples/industrial_data_pretraining/whisper/demo_from_openai.py b/examples/industrial_data_pretraining/whisper/demo_from_openai.py
index 0b88a95..5cac06b 100644
--- a/examples/industrial_data_pretraining/whisper/demo_from_openai.py
+++ b/examples/industrial_data_pretraining/whisper/demo_from_openai.py
@@ -3,15 +3,18 @@
 # Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
 #  MIT License  (https://opensource.org/licenses/MIT)
 
+# To install requirements: pip3 install -U openai-whisper
+
 from funasr import AutoModel
 
 # model = AutoModel(model="Whisper-small", hub="openai")
 # model = AutoModel(model="Whisper-medium", hub="openai")
-model = AutoModel(model="Whisper-large-v2", hub="openai")
-# model = AutoModel(model="Whisper-large-v3", hub="openai")
+# model = AutoModel(model="Whisper-large-v2", hub="openai")
+model = AutoModel(model="Whisper-large-v3", hub="openai", vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",)
 
 res = model.generate(
 	language=None,
 	task="transcribe",
+	batch_size_s=0,
 	input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
 print(res)

--
Gitblit v1.9.1