add dur utils

examples/librispeech/s1/README.md

@@ -1,5 +1,12 @@
 # LibriSpeech
 
+## Data
+
+| Data Subset | Duration in Seconds | 
+| data/manifest.train |  0.83s ~ 29.735s | 
+| data/manifest.dev | 1.065 ~ 35.155s |  
+| data/manifest.test-clean | 1.285s ~ 34.955s | 
+
 ## Conformer
 
 | Model | Params | Config | Augmentation| Test set | Decode method | Loss | WER |  

examples/librispeech/s1/path.sh

@@ -1,6 +1,6 @@
 export MAIN_ROOT=${PWD}/../../../
 
-export PATH=${MAIN_ROOT}:${MAIN_ROOT}/utils:${PATH}
+export PATH=${MAIN_ROOT}:${PWD}/utils:${PATH}
 export LC_ALL=C
 
 # Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C

examples/librispeech/s1/utils

@@ -0,0 +1 @@
+../../../utils

setup.sh

@@ -10,7 +10,7 @@ fi
 
 if [ -e /etc/lsb-release ];then
     #${SUDO} apt-get update
-    ${SUDO} apt-get install -y vim tig tree sox pkg-config libflac-dev libogg-dev libvorbis-dev libboost-dev swig python3-dev
+    ${SUDO} apt-get install -y jq vim tig tree sox pkg-config libflac-dev libogg-dev libvorbis-dev libboost-dev swig python3-dev
     if [ $? != 0 ]; then
         error_msg "Please using Ubuntu or install pkg-config libflac-dev libogg-dev libvorbis-dev libboost-dev swig python3-dev by user."
         exit -1

utils/duration_from_maniefst.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+if [ $# == 1 ];then
+    echo "usage: ${0} manifest_file"
+    exit -1
+fi
+
+manifest=$1
+
+jq -S '.feat_shape[0]' ${manifest} | sort -nu