switch to makefile instead, reuse threads

This commit is contained in:
msqr1
2024-02-03 22:19:17 -08:00
parent 076e9f65a2
commit 70b7d2c21b
13 changed files with 167 additions and 155 deletions

View File

@@ -5,97 +5,95 @@
# #### # # ### #### # #### ##### #### # #### # # ####
# 1 hour build time
sudo apt install shtool libtool autogen autotools-dev pkg-config make &&
SHELL=/bin/bash
MAX_MEMORY?=300mb
MAX_THREADS?=2
EMSDK?=../emsdk
COMPILE_JOBS?:=$(nproc)
MAX_MEMORY?=300mb &&
MAX_THREADS?=2 &&
EMSDK?=$(realpath emsdk) &&
COMPILE_JOBS?=$(nproc) &&
SRC:=$(realpath src)
KALDI:=$(realpath kaldi)
VOSK:=$(realpath vosk-api)
OPENFST:=$(KALDI)/tools/openfst
LIBARCHIVE:=$(realpath libarchive)
ZSTD:=$(realpath zstd)
CLAPACK_WASM:=$(realpath clapack-wasm)
SRC=$(realpath src) &&
KALDI=$(realpath kaldi) &&
VOSK=$(realpath vosk-api) &&
OPENFST=$KALDI/tools/openfst &&
LIBARCHIVE=$(realpath libarchive) &&
ZSTD=$(realpath zstd) &&
CLAPACK_WASM=$(realpath clapack-wasm) &&
browser-recognizer: vosk libarchive
cd $(SRC) && \
em++ -O3 global.cc genericModel.cc model.cc spkModel.cc recognizer.cc bindings.cc -sWASMFS -sWASM_BIGINT -sSINGLE_FILE -sMODULARIZE -sTRUSTED_TYPES -sEMBIND_STD_STRING_IS_UTF8 -sPTHREAD_POOL_DELAY_LOAD -sTEXTDECODER=2 -sPTHREAD_POOL_SIZE_STRICT=2 -sINITIAL_MEMORY=$(MAX_MEMORY) -sPTHREAD_POOL_SIZE=$(MAX_THREADS) -sPOLYFILL=0 -sSUPPORT_LONGJMP=0 -sEXPORT_NAME=loadBR -sEXPORTED_RUNTIME_METHODS=UTF8ToString,stringToUTF8OnStack -sMALLOC=emmaloc -sEXPORTED_FUNCTIONS=_malloc,_main -sENVIRONMENT=web -I. -I$(LIBARCHIVE)/include -I$(VOSK)/src -L$(LIBARCHIVE)/lib -larchive -L$(ZSTD)/lib -lzstd -L$(KALDI)/src -l:online2/kaldi-online2.a -l:decoder/kaldi-decoder.a -l:ivector/kaldi-ivector.a -l:gmm/kaldi-gmm.a -l:tree/kaldi-tree.a -l:feat/kaldi-feat.a -l:cudamatrix/kaldi-cudamatrix.a -l:lat/kaldi-lat.a -l:lm/kaldi-lm.a -l:rnnlm/kaldi-rnnlm.a -l:hmm/kaldi-hmm.a -l:nnet3/kaldi-nnet3.a -l:transform/kaldi-transform.a -l:matrix/kaldi-matrix.a -l:fstext/kaldi-fstext.a -l:util/kaldi-util.a -l:base/kaldi-base.a -L$(OPENFST)/lib -l:libfst.a -l:libfstngram.a -L$(CLAPACK_WASM) -l:CBLAS/lib/cblas.a -l:CLAPACK-3.2.1/lapack.a -l:CLAPACK-3.2.1/libcblaswr.a -l:f2c_BLAS-3.8.0/blas.a -l:libf2c/libf2c.a -L$(VOSK)/src -l:vosk.a -lopfs.js -lembind -pthread -flto --pre-js pre.js ../BrowserRecognizer.js && \
cd .. && \
rm -f BrowserRecognizer.worker.js && \
sed -i 's/locateFile("BrowserRecognizer.worker.js")/pthreadUrl/g' BrowserRecognizer.js && \
sed -i 's/let root/var root/g' BrowserRecognizer.js
if [ ! -d $EMSDK_PATH ]; then
echo "Invalid EMSDK path" &&
exit 1
fi
if [ $MAX_THREAD -lt 2 ]; then
echo "MAX_THREADS must be greater than or equal to 2" &&
exit 1
fi
if [ $COMPILE_JOBS -lt 1 ]; then
echo "COMPILE_JOBS must be greater than or equal to 1" &&
exit 1
fi
if ! [[ $MAX_MEMORY =~ ^[0-9]+([kmgt]b)?$ ]]; then
echo "MAX_MEMORY valid suffixes are kb, mb, gb, tb, none (bytes)" &&
exit 1
fi
if [ $(realpath $EMSDK) == $(realpath emsdk) ]; then
echo "EMSDK is current directory, installing emsdk and Emscripten..." &&
git clone --depth=1 https://github.com/emscripten-core/emsdk.git &&
cd emsdk &&
./emsdk install 3.1.53 &&
./emsdk activate 3.1.53
fi
prepare:
sudo apt install shtool libtool autogen autotools-dev pkg-config make && \
[ $(EMSDK) != emsdk -a ! -d $(EMSDK) ] && \
echo "Invalid emsdk path"; \
exit 1; \
[ $(MAX_THREAD) -lt 2 ] && \
echo "MAX_THREADS must be greater than or equal to 2"; \
exit 1; \
[ $(COMPILE_JOBS) -lt 1 ] && \
echo "COMPILE_JOBS must be greater than or equal to 1"; \
exit 1; \
[[ ! $(MAX_MEMORY) =~ "$(^[0-9]+([kmgt]b)?$$)" ]] && \
echo "MAX_MEMORY valid suffixes are kb, mb, gb, tb, none (bytes)"; \
exit 1; \
[ $(EMSDK) = emsdk ] && \
echo "Installing emsdk + Emscripten..."; \
git clone --depth=1 https://github.com/emscripten-core/emsdk.git && \
cd emsdk && \
./emsdk install 3.1.53 && \
./emsdk activate 3.1.53; \
. $(EMSDK)/emsdk_env.sh && \
export PATH=:$$PATH:$(EMSDK)/upstream/bin
. $EMSDK/emsdk_env.sh &&
export PATH=:$PATH:$EMSDK/upstream/bin &&
zstd: prepare
rm -rf /tmp/zstd && \
git clone -b v1.5.5 --depth=1 https://github.com/facebook/zstd /tmp/zstd && \
cd /tmp/zstd && \
HAVE_THREAD=0 ZSTD_LEGACY_SUPPORT=0 HAVE_ZLIB=0 HAVE_LZMA=0 HAVE_LZ4=0 ZSTD_NOBENCH=1 ZSTD_NODICT=1 ZSTD_NOCOMPRESS=1 BACKTRACE=0 PREFIX=$(ZSTD) CPPFLAGS="-O3 -flto" LDFLAGS="-O3 -flto" emmake make -j$(COMPILE_JOBS) install && \
rm -rf /tmp/zstd
zstd:
rm -rf /tmp/zstd &&
git clone -b v1.5.5 --depth=1 https://github.com/facebook/zstd /tmp/zstd &&
cd /tmp/zstd &&
HAVE_THREAD=0 ZSTD_LEGACY_SUPPORT=0 HAVE_ZLIB=0 HAVE_LZMA=0 HAVE_LZ4=0 ZSTD_NOBENCH=1 ZSTD_NODICT=1 ZSTD_NOCOMPRESS=1 BACKTRACE=0 PREFIX=$ZSTD CPPFLAGS="-O3 -flto" LDFLAGS="-O3 -flto" emmake make -j$COMPILE_JOBS install &&
rm -rf /tmp/zstd &&
libarchive: zstd
rm -rf /tmp/libarchive && \
git clone -b v3.7.2 --depth=1 https://github.com/libarchive/libarchive /tmp/libarchive && \
cd /tmp/libarchive && \
build/autogen.sh && \
CPPFLAGS="-I$(ZSTD)/include -flto" LDFLAGS="-L$(ZSTD)/lib -flto" emconfigure ./configure --prefix=$(LIBARCHIVE) --without-lz4 --without-lzma --without-zlib --without-bz2lib --without-xml2 --without-expat --without-cng --without-openssl --without-libb2 --disable-bsdunzip --disable-xattr --disable-acl --disable-bsdcpio --disable-bsdcat --disable-rpath --disable-maintainer-mode --disable-dependency-tracking --enable-static --disable-shared && \
emmake make -j$(COMPILE_JOBS) install && \
rm -rf /tmp/libarchive
libarchive:
rm -rf /tmp/libarchive &&
git clone -b v3.7.2 --depth=1 https://github.com/libarchive/libarchive /tmp/libarchive &&
cd /tmp/libarchive &&
build/autogen.sh &&
CPPFLAGS="-I$ZSTD/include -flto" LDFLAGS="-L$ZSTD/lib -flto" emconfigure ./configure --prefix=$LIBARCHIVE --without-lz4 --without-lzma --without-zlib --without-bz2lib --without-xml2 --without-expat --without-cng --without-openssl --without-libb2 --disable-bsdunzip --disable-xattr --disable-acl --disable-bsdcpio --disable-bsdcat --disable-rpath --disable-maintainer-mode --disable-dependency-tracking --enable-static --disable-shared &&
emmake make -j$COMPILE_JOBS install &&
rm -rf /tmp/libarchive &&
clapack-wasm: prepare
git clone --depth=1 https://gitlab.inria.fr/multispeech/kaldi.web/clapack-wasm.git $(CLAPACK_WASM) && \
cd $(CLAPACK_WASM) && \
bash ./install_repo.sh emcc
clapack-wasm:
git clone --depth=1 https://gitlab.inria.fr/multispeech/kaldi.web/clapack-wasm.git $CLAPACK_WASM &&
cd $CLAPACK_WASM &&
bash ./install_repo.sh emcc &&
openfst:
rm -rf /tmp/openfst &&
git clone --depth=1 https://github.com/alphacep/openfst /tmp/openfst &&
cd /tmp/openfst &&
autoreconf -i &&
CXXFLAGS="-pthread -r -O3 -flto" LDFLAGS="-O3 -pthread -flto" emconfigure ./configure --prefix=$OPENFST --enable-static --disable-shared --enable-ngram-fsts --enable-lookahead-fsts --disable-bin --with-pic &&
emmake make -j$COMPILE_JOBS install &&
echo "PACKAGE_VERSION = 1.8.0" >> $OPENFST/Makefile &&
rm -rf /tmp/openfst &&
openfst: prepare
rm -rf /tmp/openfst && \
git clone --depth=1 https://github.com/alphacep/openfst /tmp/openfst && \
cd /tmp/openfst && \
autoreconf -i && \
CXXFLAGS="-pthread -r -O3 -flto" LDFLAGS="-O3 -pthread -flto" emconfigure ./configure --prefix=$(OPENFST) --enable-static --disable-shared --enable-ngram-fsts --enable-lookahead-fsts --disable-bin --with-pic && \
emmake make -j$(COMPILE_JOBS) install && \
echo "PACKAGE_VERSION = 1.8.0" >> $(OPENFST)/Makefile && \
rm -rf /tmp/openfst
kaldi:
git clone -b vosk --depth=1 https://github.com/alphacep/kaldi $KALDI &&
cd $KALDI/src &&
git apply $SRC/kaldi.patch &&
CXXFLAGS="-O3 -msimd128 -UHAVE_EXECINFO_H -pthread -flto" LDFLAGS="-O3 -sERROR_ON_UNDEFINED_SYMBOLS=0 -lembind -pthread -flto" emconfigure ./configure --use-cuda=no --with-cudadecoder=no --static --static-math=yes --static-fst=yes --debug-level=0 --double-precision=yes --clapack-root=$CLAPACK_WASM --host=WASM &&
emmake make -j$COMPILE_JOBS online2 lm rnnlm
kaldi: openfst clapack-wasm
git clone -b vosk --depth=1 https://github.com/alphacep/kaldi $(KALDI) && \
cd $(KALDI)/src && \
git apply $(SRC)/kaldi.patch && \
CXXFLAGS="-O3 -msimd128 -UHAVE_EXECINFO_H -pthread -flto" LDFLAGS="-O3 -sERROR_ON_UNDEFINED_SYMBOLS=0 -lembind -pthread -flto" emconfigure ./configure --use-cuda=no --with-cudadecoder=no --static --static-math=yes --static-fst=yes --debug-level=0 --double-precision=yes --clapack-root=$(CLAPACK_WASM) --host=WASM && \
emmake make -j$(COMPILE_JOBS) online2 lm rnnlm
vosk:
git clone -b go/v0.3.46 --depth=1 https://github.com/alphacep/vosk-api $VOSK &&
cd $VOSK/src &&
git apply $SRC/vosk.patch &&
VOSK_FILES="recognizer.cc language_model.cc model.cc spk_model.cc vosk_api.cc" &&
em++ -pthread -O3 -flto -Wno-deprecated -I. -I$KALDI/src -I$OPENFST/include $VOSK_FILES -c &&
emar -rcs vosk.a ${VOSK_FILES//.cc/.o}
vosk: kaldi
git clone -b go/v0.3.46 --depth=1 https://github.com/alphacep/vosk-api $(VOSK) && \
cd $(VOSK)/src && \
git apply $(SRC)/vosk.patch && \
VOSK_FILES="recognizer.cc language_model.cc model.cc spk_model.cc vosk_api.cc" && \
em++ -pthread -O3 -flto -Wno-deprecated -I. -I$(KALDI)/src -I$(OPENFST)/include $(VOSK_FILES) -c && \
emar -rcs vosk.a $(VOSK_FILES:.cc=.o)
browser-recognizer:
cd $SRC &&
em++ -O3 global.cc genericModel.cc model.cc spkModel.cc recognizer.cc bindings.cc -sWASMFS -sWASM_BIGINT -sSINGLE_FILE -sMODULARIZE -sTRUSTED_TYPES -sEMBIND_STD_STRING_IS_UTF8 -sPTHREAD_POOL_DELAY_LOAD -sALLOW_BLOCKING_ON_MAIN_THREAD -sINITIAL_MEMORY=$MAX_MEMORY -sPTHREAD_POOL_SIZE=$MAX_THREADS -sPOLYFILL=0 -sPTHREAD_POOL_SIZE_STRICT=0 -sSUPPORT_LONGJMP=0 -sEXPORTED_RUNTIME_METHODS=UTF8ToString,stringToUTF8OnStack -sEXPORTED_FUNCTIONS=_malloc,_main -sEXPORT_NAME=loadBR -sENVIRONMENT=web,worker -I. -I$LIBARCHIVE/include -I$VOSK/src -L$LIBARCHIVE/lib -larchive -L$ZSTD/lib -lzstd -L$KALDI/src -l:online2/kaldi-online2.a -l:decoder/kaldi-decoder.a -l:ivector/kaldi-ivector.a -l:gmm/kaldi-gmm.a -l:tree/kaldi-tree.a -l:feat/kaldi-feat.a -l:cudamatrix/kaldi-cudamatrix.a -l:lat/kaldi-lat.a -l:lm/kaldi-lm.a -l:rnnlm/kaldi-rnnlm.a -l:hmm/kaldi-hmm.a -l:nnet3/kaldi-nnet3.a -l:transform/kaldi-transform.a -l:matrix/kaldi-matrix.a -l:fstext/kaldi-fstext.a -l:util/kaldi-util.a -l:base/kaldi-base.a -L$OPENFST/lib -l:libfst.a -l:libfstngram.a -L$CLAPACK_WASM -l:CBLAS/lib/cblas.a -l:CLAPACK-3.2.1/lapack.a -l:CLAPACK-3.2.1/libcblaswr.a -l:f2c_BLAS-3.8.0/blas.a -l:libf2c/libf2c.a -L$VOSK/src -l:vosk.a -lopfs.js -lembind -pthread -flto --pre-js pre.js ../BrowserRecognizer.js &&
cd .. &&
rm -f BrowserRecognizer.worker.js &&
sed -i 's/locateFile("BrowserRecognizer.worker.js")/pthreadUrl/g' BrowserRecognizer.js
.PHONY: prepare