From e24dbdc496debec225414d4d2c760f5775e64f2a Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 26 三月 2025 13:44:41 +0800
Subject: [PATCH] 感觉应该从文件读取更合适，因为上面判断了文件存在，且可以读取，如果本身是文本的话，下面也会有逻辑进行处理 (#2452)
---
examples/industrial_data_pretraining/whisper/demo.py | 25 +++++++++++++++++++++----
1 files changed, 21 insertions(+), 4 deletions(-)
diff --git a/examples/industrial_data_pretraining/whisper/demo.py b/examples/industrial_data_pretraining/whisper/demo.py
index db8d92c..5665550 100644
--- a/examples/industrial_data_pretraining/whisper/demo.py
+++ b/examples/industrial_data_pretraining/whisper/demo.py
@@ -3,11 +3,28 @@
# 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="iic/Whisper-large-v3",
- model_revision="v2.0.4",
- )
+model = AutoModel(
+ model="Whisper-large-v3-turbo",
+ vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
+ vad_kwargs={"max_single_segment_time": 30000},
+)
-res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", language=None)
+DecodingOptions = {
+ "task": "transcribe",
+ "language": None,
+ "beam_size": None,
+ "fp16": True,
+ "without_timestamps": False,
+ "prompt": None,
+}
+res = model.generate(
+ DecodingOptions=DecodingOptions,
+ 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