patrick/Vosklet
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Back to sh i guess

Browse Source
This commit is contained in:
msqr1
2024-03-31 19:44:22 -07:00
parent 59d7906590
commit 0cdc293bdd
4 changed files with 94 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
API.md
View File

@@ -46,15 +46,16 @@ Vosklet require SharedArrayBuffer to share threads' data, so these response head
If you can't set them, you may use a hacky workaround at *src/addCOI.js*. If you can't set them, you may use a hacky workaround at *src/addCOI.js*.
# Compilation # Compilation
Changing any option to non-default values requires recompilation - Changing any option to non-default values requires recompilation
- To re-make a specific target, erase its directory in the repo root and run ```./make``` again
``` ```
git clone --depth=1 https://github.com/msqr1/Vosklet && git clone --depth=1 https://github.com/msqr1/Vosklet &&
cd Vosklet/src && cd Vosklet/src &&
[Options] make [Options] ./make
``` ```
| Option | Description | Default value | | Option | Description | Default value |
|---|---|---| |---|---|---|
| MAX_MEMORY | Set max memory, valid suffixes: kb, mb, gb, tb or none (bytes) | ```375mb```, 300mb as [recommended](https://alphacephei.com/vosk/models) plus 75mb typical uncompressed model size (loaded to memory) | | MAX_MEMORY | Set max memory, valid suffixes: kb, mb, gb, tb or none (bytes) | ```375mb```, 300mb as [recommended](https://alphacephei.com/vosk/models) plus 75mb typical uncompressed model size (loaded to memory) |
| MAX_THREADS | Set the max number of threads (>=1), this should be equal to the number of model or speaker model that is used in the program | ```1``` (1 recognizer, 1 model, 0 speaker model) | | MAX_THREADS | Set the max number of threads (>=1), this should be equal to the number of model or speaker model that is used in the program | ```1``` (1 recognizer, 1 model, 0 speaker model) |
| COMPILE_JOBS | Set the number of jobs (threads) when building | ```$(nproc)``` | | JOBS | Set the number of jobs (threads) when building | ```$(nproc)``` |
| EMSDK | Set EMSDK's path (will install EMSDK in root folder if unset) | ```../emsdk``` | | EMSDK | Set EMSDK's path (will install EMSDK in root folder if unset) | ```../emsdk``` |

2
Vosklet.js
View File

File diff suppressed because one or more lines are too long

91
src/Makefile
View File

@@ -1,91 +0,0 @@
#### #### #### ### #### # # #### # #### #### #### #### ####
# # # # # # ## # # # # # # # # # # # # #
#### # # #### # # #### # # #### # # # #### #### #### ####
# # # # # # ## # # # # # # # # # # # #
# #### # # ### #### # #### ##### #### # #### # # ####
# 20 min build time
SHELL=/bin/bash
MAX_MEMORY?=300mb
MAX_THREADS?=2
EMSDK?=../emsdk
COMPILE_JOBS?:=$(nproc)
SRC:=$(realpath src)
KALDI:=$(realpath kaldi)
VOSK:=$(realpath vosk)
OPENFST:=$(realpath openfst)
LIBARCHIVE:=$(realpath libarchive)
CLAPACK_WASM:=$(realpath clapack-wasm)
Vosklet.js: | vosk libarchive
cd $(SRC) && \
em++ -O3 link.cc genericModel.cc recognizer.cc bindings.cc -sWASMFS -sWASM_BIGINT -sSINGLE_FILE -sMODULARIZE -sEMBIND_STD_STRING_IS_UTF8 -sPTHREAD_POOL_DELAY_LOAD -sTEXTDECODER=2 -sPTHREAD_POOL_SIZE_STRICT=2 -sINITIAL_MEMORY=$(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 --pre-js pre.js -o ../Vosklet.js && \
cd .. && \
rm -f Vosklet.worker.js && \
prepare:
sudo apt install shtool libtool autogen autotools-dev pkg-config make && \
[ $(EMSDK) != ../emsdk ! -d $(EMSDK) ] && \
echo "Invalid emsdk path"; \
exit 1; \
[ $(MAX_THREADS) -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)?$$)" ]] && \
echo "MAX_MEMORY valid suffixes are kb, mb, gb, tb, none (bytes)"; \
exit 1; \
[ $(EMSDK) = ../emsdk ] && \
echo "Installing emsdk + Emscripten..."; \
git clone --depth=1 https://github.com/emscripten-core/emsdk.git ../emsdk && \
cd ../emsdk &&
./emsdk install 3.1.56 && \
./emsdk activate 3.1.56; \
. ./emsdk_env.sh && \
export PATH=:$$PATH:$(realpath $(EMSDK))/upstream/bin && \
cd ../src
libarchive: prepare
rm -rf /tmp/libarchive && \
git clone -b v3.7.2 --depth=1 https://github.com/libarchive/libarchive /tmp/libarchive && \
cd /tmp/libarchive && \
build/autogen.sh && \
CPPFLAGS="-O3 -flto -msimd128" LDFLAGS="-O3 -flto" emconfigure ./configure --prefix=$(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$(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) && \
git apply $(SRC)/clapack-wasm.patch &&
bash install_repo.sh emcc
openfst: prepare
rm -rf /tmp/openfst && \
git clone --depth=1 https://github.com/alphacep/openfst /tmp/openfst && \
cd /tmp/openfst && \
autoreconf -i && \
CXXFLAGS="-r -O3 -flto -msimd128" LDFLAGS="-O3 -flto" emconfigure ./configure --prefix=$(OPENFST) --enable-static --disable-shared --enable-lookahead-fsts --enable-ngram-fsts --disable-bin && \
emmake make -j$(COMPILE_JOBS) install && \
echo "PACKAGE_VERSION = 1.8.0" >> $(OPENFST)/Makefile && \
rm -rf /tmp/openfst
kaldi: | openfst clapack-wasm
git clone -b vosk --depth=1 https://github.com/alphacep/kaldi && \
cd $(KALDI)/src && \
git apply $(SRC)/kaldi.patch && \
CXXFLAGS="-O3 -UHAVE_EXECINFO_H -flto -msimd128 -Wno-unused-variable -Wno-unused-but-set-variable -g0" LDFLAGS="-O3 -lembind -flto -g0" emconfigure ./configure --use-cuda=no --with-cudadecoder=no --static --static-math=yes --static-fst=yes --debug-level=0 --fst-root=$(OPENFST) --clapack-root=$(CLAPACK_WASM) --host=WASM && \
emmake make -j$(COMPILE_JOBS) online2 rnnlm
vosk: | kaldi
git clone -b go/v0.3.46 --depth=1 https://github.com/alphacep/vosk-api $(VOSK) && \
cd $(VOSK)/src && \
git apply $(SRC)/vosk.patch && \
VOSK_FILES="recognizer.cc language_model.cc model.cc spk_model.cc vosk_api.cc" && \
em++ -O3 -flto -msimd128 -Wno-deprecated -I. -I$(KALDI)/src -I$(OPENFST)/include $(VOSK_FILES) -c && \
emar -rcs vosk.a $(VOSK_FILES:.cc=.o)
.PHONY: prepare

89
src/make Executable file
View File

@@ -0,0 +1,89 @@
#!/bin/bash
MAX_MEMORY=${MAX_MEMORY:-300mb}
MAX_THREADS=${MAX_THREADS:-1}
EMSDK=${EMSDK:-../emsdk}
JOBS=${JOBS:-$(nproc)}
sudo apt install shtool libtool autogen autotools-dev pkg-config make &&
if [ $EMSDK != ../emsdk && ! -d $EMSDK ]; then
echo "Invalid emsdk path"
exit 1
fi
if [ $MAX_THREADS -lt 1 ]; then
echo "MAX_THREADS must be greater than or equal to 1"
exit 1
fi
if [ $JOBS -lt 1 ]; then
echo "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 [ $EMSDK = ../emsdk ]; then
echo "Installing emsdk + Emscripten..."
git clone --depth=1 https://github.com/emscripten-core/emsdk.git ../emsdk &&
cd ../emsdk &&
./emsdk install 3.1.56 &&
./emsdk activate 3.1.56
fi
. $(realpath $EMSDK)/emsdk_env.sh &&
export PATH=:$PATH:$(realpath $EMSDK)/upstream/bin
cd ..
SRC=$(realpath src)
KALDI=$(realpath kaldi)
VOSK=$(realpath vosk)
OPENFST=$(realpath openfst)
LIBARCHIVE=$(realpath libarchive)
CLAPACK_WASM=$(realpath clapack-wasm)
if [ ! -d $LIBARCHIVE ]; then
rm -rf /tmp/libarchive &&
git clone -b v3.7.2 --depth=1 https://github.com/libarchive/libarchive /tmp/libarchive &&
cd /tmp/libarchive &&
build/autogen.sh &&
CFLAGS="-O3 -flto -msimd128" LDFLAGS="-O3 -flto" emconfigure ./configure --prefix=$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 $OPENFST ]; then
rm -rf /tmp/openfst &&
git clone --depth=1 https://github.com/alphacep/openfst /tmp/openfst &&
cd /tmp/openfst &&
autoreconf -is &&
CXXFLAGS="-r -O3 -flto -msimd128" LDFLAGS="-O3 -flto" emconfigure ./configure --prefix=$OPENFST --enable-static --disable-shared --enable-lookahead-fsts --enable-ngram-fsts --disable-bin &&
emmake make -j$JOBS install &&
echo "PACKAGE_VERSION = 1.8.0" >> $OPENFST/Makefile
fi
if [ ! -d $CLAPACK_WASM ]; then
git clone --depth=1 https://gitlab.inria.fr/multispeech/kaldi.web/clapack-wasm.git $CLAPACK_WASM &&
cd $CLAPACK_WASM &&
git apply $SRC/clapack-wasm.patch &&
bash install_repo.sh emcc
fi
if [ ! -d $KALDI ]; then
git clone -b vosk --depth=1 https://github.com/alphacep/kaldi $KALDI &&
cd $KALDI/src &&
git apply $SRC/kaldi.patch &&
CXXFLAGS="-O3 -UHAVE_EXECINFO_H -flto -msimd128 -Wno-unused-variable -Wno-unused-but-set-variable -g0" LDFLAGS="-O3 -lembind -flto -g0" emconfigure ./configure --use-cuda=no --with-cudadecoder=no --static --static-math=yes --static-fst=yes --debug-level=0 --fst-root=$OPENFST --clapack-root=$CLAPACK_WASM --host=WASM &&
emmake make -j$JOBS online2 rnnlm
fi
if [ ! -d $VOSK ]; then
git clone -b go/v0.3.46 --depth=1 https://github.com/alphacep/vosk-api $VOSK &&
cd $VOSK/src &&
git apply $SRC/vosk.patch &&
VOSK_FILES="recognizer.cc language_model.cc model.cc spk_model.cc vosk_api.cc" &&
em++ -O3 -flto -msimd128 -Wno-deprecated -I. -I$KALDI/src -I$OPENFST/include $VOSK_FILES -c &&
emar -rcs vosk.a ${VOSK_FILES//.cc/.o}
fi
cd $SRC &&
em++ -O3 link.cc genericModel.cc recognizer.cc bindings.cc -sWASMFS -sWASM_BIGINT -sSINGLE_FILE -sMODULARIZE -sEMBIND_STD_STRING_IS_UTF8 -sPTHREAD_POOL_DELAY_LOAD -sTEXTDECODER=2 -sPTHREAD_POOL_SIZE_STRICT=2 -sINITIAL_MEMORY=$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 --pre-js pre.js -o ../Vosklet.js &&
rm -f ../Vosklet.worker.js &&
rm -rf /tmp/libarchive &&
rm -rf /tmp/openfst