From 33ffd88a3ffa9b31e1c5e171fb22ad16f13240e3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=BD=AD=E9=80=B8=E8=B1=AA?= Date: Thu, 9 Mar 2023 08:14:30 +0000 Subject: [PATCH] demos/TTSCppFrontend: add a script to download dictionary files --- demos/TTSCppFrontend/README.md | 8 ++++- demos/TTSCppFrontend/clean.sh | 1 + demos/TTSCppFrontend/download.sh | 62 ++++++++++++++++++++++++++++++++ 3 files changed, 70 insertions(+), 1 deletion(-) create mode 100755 demos/TTSCppFrontend/download.sh diff --git a/demos/TTSCppFrontend/README.md b/demos/TTSCppFrontend/README.md index a3adb6f36..592140ae1 100644 --- a/demos/TTSCppFrontend/README.md +++ b/demos/TTSCppFrontend/README.md @@ -31,6 +31,12 @@ Dependent libraries will be automatically downloaded to the `third-party/build` If the download speed is too slow, you can open [third-party/CMakeLists.txt](third-party/CMakeLists.txt) and modify `GIT_REPOSITORY` URLs. +## Download dictionary files + +``` +./download.sh +``` + ## Run ``` @@ -46,4 +52,4 @@ If the download speed is too slow, you can open [third-party/CMakeLists.txt](thi ./clean.sh ``` -The folders `build` and `third-party/build` will be deleted. +The folders `front_demo/dict`, `build` and `third-party/build` will be deleted. diff --git a/demos/TTSCppFrontend/clean.sh b/demos/TTSCppFrontend/clean.sh index d99761b0a..efbb28871 100755 --- a/demos/TTSCppFrontend/clean.sh +++ b/demos/TTSCppFrontend/clean.sh @@ -3,6 +3,7 @@ set -e set -x cd "$(dirname "$(realpath "$0")")" +rm -rf "./front_demo/dict" rm -rf "./build" rm -rf "./third-party/build" diff --git a/demos/TTSCppFrontend/download.sh b/demos/TTSCppFrontend/download.sh new file mode 100755 index 000000000..0953e3a59 --- /dev/null +++ b/demos/TTSCppFrontend/download.sh @@ -0,0 +1,62 @@ +#!/bin/bash +set -e + +cd "$(dirname "$(realpath "$0")")" + +download() { + file="$1" + url="$2" + md5="$3" + dir="$4" + + cd "$dir" + + if [ -f "$file" ] && [ "$(md5sum "$file" | awk '{ print $1 }')" = "$md5" ]; then + echo "File $file (MD5: $md5) has been downloaded." + else + echo "Downloading $file..." + wget -O "$file" "$url" + + # MD5 verify + fileMd5="$(md5sum "$file" | awk '{ print $1 }')" + if [ "$fileMd5" == "$md5" ]; then + echo "File $file (MD5: $md5) has been downloaded." + else + echo "MD5 mismatch, file may be corrupt" + echo "$file MD5: $fileMd5, it should be $md5" + fi + fi + + echo "Extracting $file..." + echo '-----------------------' + tar -vxf "$file" + echo '=======================' +} + +######################################## + +DIST_DIR="$PWD/front_demo/dict" + +mkdir -p "$DIST_DIR" + +download 'fastspeech2_nosil_baker_ckpt_0.4.tar.gz' \ + 'https://paddlespeech.bj.bcebos.com/t2s/text_frontend/fastspeech2_nosil_baker_ckpt_0.4.tar.gz' \ + '7bf1bab1737375fa123c413eb429c573' \ + "$DIST_DIR" + +download 'speedyspeech_nosil_baker_ckpt_0.5.tar.gz' \ + 'https://paddlespeech.bj.bcebos.com/t2s/text_frontend/speedyspeech_nosil_baker_ckpt_0.5.tar.gz' \ + '0b7754b21f324789aef469c61f4d5b8f' \ + "$DIST_DIR" + +download 'jieba.tar.gz' \ + 'https://paddlespeech.bj.bcebos.com/t2s/text_frontend/jieba.tar.gz' \ + '6d30f426bd8c0025110a483f051315ca' \ + "$DIST_DIR" + +download 'tranditional_to_simplified.tar.gz' \ + 'https://paddlespeech.bj.bcebos.com/t2s/text_frontend/tranditional_to_simplified.tar.gz' \ + '258f5b59d5ebfe96d02007ca1d274a7f' \ + "$DIST_DIR" + +echo "Done."