42ff9460创建于 2022年12月8日历史提交

文件	最后提交记录	最后更新时间
conf	[audio] mv paddlespeech/audio to paddleaudio (#2706) * split paddlespeech/audio to paddleaudio. * add sox io ,sox effect, kaldi native fbank to paddleaudio.	3 年前
local	Update KWS example.	4 年前
README.md	Add KWS example.	4 年前
path.sh	Add KWS example.	4 年前
run.sh	Update KWS example.	4 年前

MDTC Keyword Spotting with HeySnips Dataset

Dataset

Before running scripts, you MUST follow this instruction to download the dataset: https://github.com/sonos/keyword-spotting-research-datasets

After you download and decompress the dataset archive, you should REPLACE the value of data_dir in conf/*.yaml to complete dataset config.

In this section, we will train the MDTC model and evaluate on "Hey Snips" dataset.

CUDA_VISIBLE_DEVICES=0,1 ./run.sh conf/mdtc.yaml

This script contains training and scoring steps. You can just set the CUDA_VISIBLE_DEVICES environment var to run on single gpu or multi-gpus.

The vars stage and stop_stage in ./run.sh controls the running steps:

stage 1: Training from scratch.
stage 2: Evaluating model on test dataset and computing detection error tradeoff(DET) of all trigger thresholds.
stage 3: Plotting the DET cruve for visualizaiton.