From aa45aeeaa7e8abd11bc1be392b4547685645ca5e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=AF=AD=E5=B8=86?= Date: Mon, 4 Mar 2024 14:29:52 +0800 Subject: [PATCH] atsr --- .../lcbnet/demp.py | 35 +++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 examples/industrial_data_pretraining/lcbnet/demp.py diff --git a/examples/industrial_data_pretraining/lcbnet/demp.py b/examples/industrial_data_pretraining/lcbnet/demp.py new file mode 100644 index 000000000..cb08290b4 --- /dev/null +++ b/examples/industrial_data_pretraining/lcbnet/demp.py @@ -0,0 +1,35 @@ +#!/usr/bin/env python3 +# -*- encoding: utf-8 -*- +# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved. +# MIT License (https://opensource.org/licenses/MIT) + +from funasr import AutoModel + +model = AutoModel(model="iic/LCB-NET" + ) + + +# example1 +#res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", + ) +#print(res) + + +''' +# tensor or numpy as input +# example2 +import torchaudio +import os +wav_file = os.path.join(model.model_path, "example/asr_example.wav") +input_tensor, sample_rate = torchaudio.load(wav_file) +input_tensor = input_tensor.mean(0) +res = model.generate(input=[input_tensor], batch_size_s=300, is_final=True) + + +# example3 +import soundfile + +wav_file = os.path.join(model.model_path, "example/asr_example.wav") +speech, sample_rate = soundfile.read(wav_file) +res = model.generate(input=[speech], batch_size_s=300, is_final=True) +'''