Remove libarchive, implement untar manually. Use vosk-browser models

This commit is contained in:
msqr1
2024-06-02 02:53:30 -07:00
parent 43048b0685
commit 410bff9be1
14 changed files with 122 additions and 98 deletions

View File

@@ -28,25 +28,15 @@ if [ $EMSDK = ../emsdk ] && [ ! -d $EMSDK ]; then
./emsdk activate 3.1.59
fi
. $(realpath $EMSDK)/emsdk_env.sh &&
export PATH=:$PATH:$(realpath $EMSDK)/upstream/bin
export PATH=:$PATH:$(realpath $EMSDK)/upstream/bin &&
cd ..
cd .. &&
SRC=$(realpath src)
KALDI=$(realpath kaldi)
VOSK=$(realpath vosk)
OPENFST=$(realpath openfst)
LIBARCHIVE=$(realpath libarchive)
CLAPACK_WASM=$(realpath clapack-wasm)
if [ ! -d $LIBARCHIVE ]; then
rm -rf /tmp/libarchive &&
git clone -b v3.7.4 --depth=1 https://github.com/libarchive/libarchive /tmp/libarchive &&
cd /tmp/libarchive &&
build/autogen.sh &&
CFLAGS="-O3 -flto -msimd128 -mreference-types -mnontrapping-fptoint -mextended-const -msign-ext -mmutable-globals" LDFLAGS="-O3 -flto" emconfigure ./configure --prefix=$LIBARCHIVE --without-lz4 --without-lzma --without-zlib --without-bz2lib --without-xml2 --without-expat --without-cng --without-openssl --without-libb2 --without-zstd --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$JOBS install
fi
if [ ! -d $OPENFST ]; then
rm -rf /tmp/openfst &&
git clone --depth=1 https://github.com/alphacep/openfst /tmp/openfst &&
@@ -82,13 +72,13 @@ if [ ! -d $VOSK ]; then
fi
cd $SRC &&
em++ link.cc genericModel.cc recognizer.cc bindings.cc -O3 -sWASMFS -sWASM_BIGINT -sSINGLE_FILE -sMODULARIZE -sEMBIND_STD_STRING_IS_UTF8 -sPTHREAD_POOL_DELAY_LOAD -sTEXTDECODER=2 -sPTHREAD_POOL_SIZE_STRICT=2 -sINITIAL_MEMORY=$MAX_MEMORY -sPTHREAD_POOL_SIZE=$MAX_THREADS -sPOLYFILL=0 -sEXIT_RUNTIME=0 -sINVOKE_RUN=0 -sSUPPORT_LONGJMP=0 -sEXPORTED_FUNCTIONS=_malloc -sEXPORT_NAME=loadVosklet -sMALLOC=emmalloc -sEXPORTED_RUNTIME_METHODS=UTF8ToString,stringToUTF8OnStack -sENVIRONMENT=web,worker -I. -I$LIBARCHIVE/include -I$VOSK/src -L$LIBARCHIVE/lib -larchive -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 -lembind -pthread -flto -msimd128 -mreference-types -mnontrapping-fptoint -mextended-const -msign-ext -mmutable-globals --pre-js wrapper.js -o ../Vosklet.js &&
em++ util.cc genericModel.cc recognizer.cc bindings.cc -O3 -sWASMFS -sWASM_BIGINT -sSINGLE_FILE -sMODULARIZE -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 -sEXIT_RUNTIME=0 -sINVOKE_RUN=0 -sSUPPORT_LONGJMP=0 -sEXPORTED_FUNCTIONS=_malloc -sEXPORT_NAME=loadVosklet -sMALLOC=emmalloc -sEXPORTED_RUNTIME_METHODS=UTF8ToString,stringToUTF8OnStack -sENVIRONMENT=web,worker -I. -I"$VOSK"/src -L$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 -lembind -pthread -flto -msimd128 -mreference-types -mnontrapping-fptoint -mextended-const -msign-ext -mmutable-globals --pre-js wrapper.js -o ../Vosklet.js &&
cd .. &&
rm -f Vosklet.worker.js
cp Vosklet.js examples/Vosklet.js &&
# Can't serve files from raw.githubusercontent with Content-Encoding: gzip header so the browser won't decompress automatically. Change to manually decompressing instead.
# Can't serve files from raw.githubusercontent with Content-Encoding: gzip header so the browser won't decompress automatically. Manually decompressing instead.
sed -i 's/res.body/new Response(res.body.pipeThrough(new DecompressionStream("gzip"))).body/' examples/Vosklet.js &&
rm -rf /tmp/libarchive