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/whisper/demo_from_openai.py | 11 +++++++++--
1 files changed, 9 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..a257bc8 100644
--- a/examples/industrial_data_pretraining/whisper/demo_from_openai.py
+++ b/examples/industrial_data_pretraining/whisper/demo_from_openai.py
@@ -3,15 +3,22 @@
# 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",
+ vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
+ vad_kwargs={"max_single_segment_time": 30000},
+ hub="openai",
+ )
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