Great progress
This commit is contained in:
msqr1
@@ -9,7 +9,7 @@
|
||||
- Download multiple models
|
||||
- Model storage path management (for multiple models)
|
||||
- Model ID management (for model updates)
|
||||
- Massively smaller JS size (>5.7MB vs 1.7MB)
|
||||
- Smaller JS size (>3.1MB vs 1.7MB)
|
||||
- All related files (worker.js, worklet processors,...) are bundled
|
||||
- Shorter from-scratch build time
|
||||
|
||||
|
||||
1
devel/Vosklet.d.ts
vendored
1
devel/Vosklet.d.ts
vendored
@@ -15,7 +15,6 @@ interface WasmModule {
|
||||
export interface genericModel {
|
||||
check(): void;
|
||||
afterFetch(): void;
|
||||
load(): void;
|
||||
delete(): void;
|
||||
}
|
||||
|
||||
|
||||
311
devel/Vosklet.js
311
devel/Vosklet.js
File diff suppressed because one or more lines are too long
17546
devel/Vosklet.js.symbols
17546
devel/Vosklet.js.symbols
File diff suppressed because it is too large
Load Diff
@@ -9,7 +9,7 @@ LIBARCHIVE=$(realpath libarchive) &&
|
||||
CLAPACK_WASM=$(realpath clapack-wasm) &&
|
||||
|
||||
MAX_MEMORY=${MAX_MEMORY:-300mb} &&
|
||||
MAX_THREADS=${MAX_THREADS:-2} &&
|
||||
MAX_THREADS=${MAX_THREADS:-5} &&
|
||||
EMSDK=${EMSDK:-$(realpath emsdk)} &&
|
||||
|
||||
if [ ! -d $EMSDK ]; then
|
||||
@@ -28,12 +28,12 @@ fi
|
||||
. $EMSDK/emsdk_env.sh &&
|
||||
|
||||
cd $SRC &&
|
||||
MODE=2 && # 0: Ultra debug info, 1: Extremely optimized release, else custom
|
||||
MODE=0 && # 0: Ultra debug info, 1: Extremely optimized release, else custom
|
||||
echo "Mode = $MODE" &&
|
||||
if [ $MODE = 0 ]; then
|
||||
em++ -O0 global.cc genericModel.cc recognizer.cc bindings.cc -sWASMFS -sWASM_BIGINT -sSINGLE_FILE -sGZIP_EMBEDDINGS -sMODULARIZE -sEMBIND_STD_STRING_IS_UTF8 -sPTHREAD_POOL_DELAY_LOAD -sRUNTIME_DEBUG -sSTACK_OVERFLOW_CHECK=2 -sTEXTDECODER=2 -sPTHREAD_POOL_SIZE_STRICT=2 -sASSERTIONS=2 -sINITIAL_MEMORY=$MAX_MEMORY -sPTHREAD_POOL_SIZE=$MAX_THREADS -sDISABLE_EXCEPTION_CATCHING=0 -sINVOKE_RUN=0 -sPOLYFILL=0 -sEXPORTED_FUNCTIONS=_malloc -sEXPORT_NAME=loadVosklet -sMALLOC=emmalloc -sEXPORTED_RUNTIME_METHODS=UTF8ToString,stringToUTF8OnStack -sENVIRONMENT=web,worker -I. -I$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 -lopfs.js -lembind -pthread -flto -msimd128 --emit-symbol-map --embind-emit-tsd Vosklet.d.ts -fsanitize=undefined -fsanitize=address -fsanitize=leak -g3 --pre-js pre.js -o ../devel/Vosklet.js
|
||||
em++ -O0 global.cc genericModel.cc recognizer.cc bindings.cc -sWASMFS -sWASM_BIGINT -sSINGLE_FILE -sGZIP_EMBEDDINGS -sMODULARIZE -sEMBIND_STD_STRING_IS_UTF8 -sPTHREAD_POOL_DELAY_LOAD -sRUNTIME_DEBUG -sSTACK_OVERFLOW_CHECK=2 -sTEXTDECODER=2 -sPTHREAD_POOL_SIZE_STRICT=2 -sASSERTIONS=2 -sINITIAL_MEMORY=$MAX_MEMORY -sPTHREAD_POOL_SIZE=$MAX_THREADS -sDISABLE_EXCEPTION_CATCHING=0 -sEXIT_RUNTIME=0 -sINVOKE_RUN=0 -sPOLYFILL=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 -lopfs.js -lembind -pthread -flto -msimd128 --embind-emit-tsd Vosklet.d.ts -fsanitize=undefined -fsanitize=address -fsanitize=leak -g3 --pre-js pre.js -o ../devel/Vosklet.js
|
||||
elif [ $MODE = 1 ]; then
|
||||
em++ -O3 global.cc genericModel.cc recognizer.cc bindings.cc -sWASMFS -sWASM_BIGINT -sSINGLE_FILE -sGZIP_EMBEDDINGS -sMODULARIZE -sEMBIND_STD_STRING_IS_UTF8 -sPTHREAD_POOL_DELAY_LOAD -sTEXTDECODER=2 -sPTHREAD_POOL_SIZE_STRICT=2 -sINITIAL_MEMORY=$MAX_MEMORY -sPTHREAD_POOL_SIZE=$MAX_THREADS -sPOLYFILL=0 -sINVOKE_RUN=0 -sSUPPORT_LONGJMP=0 -sEXPORTED_FUNCTIONS=_malloc -sEXPORT_NAME=loadVosklet -sMALLOC=emmalloc -sEXPORTED_RUNTIME_METHODS=UTF8ToString,stringToUTF8OnStack -sENVIRONMENT=web,worker -I. -I$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 -lopfs.js -lembind -pthread -flto -msimd128 --pre-js pre.js -o ../devel/Vosklet.js
|
||||
em++ -O3 global.cc genericModel.cc recognizer.cc bindings.cc -sWASMFS -sWASM_BIGINT -sSINGLE_FILE -sGZIP_EMBEDDINGS -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$VOSK/src -l:vosk.a -lopfs.js -lembind -pthread -flto -msimd128 --pre-js pre.js -o ../devel/Vosklet.js
|
||||
else
|
||||
em++ -O0 global.cc genericModel.cc recognizer.cc bindings.cc -sWASMFS -sWASM_BIGINT -sSINGLE_FILE -sGZIP_EMBEDDINGS -sMODULARIZE -sEMBIND_STD_STRING_IS_UTF8 -sPTHREAD_POOL_DELAY_LOAD -sRUNTIME_DEBUG -sSTACK_OVERFLOW_CHECK=2 -sTEXTDECODER=2 -sPTHREAD_POOL_SIZE_STRICT=2 -sASSERTIONS=2 -sINITIAL_MEMORY=$MAX_MEMORY -sPTHREAD_POOL_SIZE=$MAX_THREADS -sDISABLE_EXCEPTION_CATCHING=0 -sEXIT_RUNTIME=0 -sPOLYFILL=0 -sEXPORTED_FUNCTIONS=_malloc -sEXPORT_NAME=loadVosklet -sMALLOC=emmalloc -sEXPORTED_RUNTIME_METHODS=UTF8ToString,stringToUTF8OnStack -sENVIRONMENT=web,worker -I. -I$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 -lopfs.js -lembind -pthread -flto -msimd128 --emit-symbol-map --embind-emit-tsd Vosklet.d.ts -fsanitize=undefined -fsanitize=address -fsanitize=leak -g3 --pre-js pre.js -o ../devel/Vosklet.js
|
||||
em++ -O0 global.cc genericModel.cc recognizer.cc bindings.cc -sWASMFS -sWASM_BIGINT -sSINGLE_FILE -sGZIP_EMBEDDINGS -sMODULARIZE -sEMBIND_STD_STRING_IS_UTF8 -sPTHREAD_POOL_DELAY_LOAD -sRUNTIME_DEBUG -sSTACK_OVERFLOW_CHECK=2 -sTEXTDECODER=2 -sPTHREAD_POOL_SIZE_STRICT=2 -sASSERTIONS=2 -sINITIAL_MEMORY=$MAX_MEMORY -sPTHREAD_POOL_SIZE=$MAX_THREADS -sDISABLE_EXCEPTION_CATCHING=0 -sEXIT_RUNTIME=0 -sINVOKE_RUN=0 -sPOLYFILL=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 -lopfs.js -lembind -pthread -flto -msimd128 --embind-emit-tsd Vosklet.d.ts -fsanitize=undefined -fsanitize=address -fsanitize=leak -g3 --pre-js pre.js -o ../devel/Vosklet.js
|
||||
fi
|
||||
|
||||
@@ -9,8 +9,7 @@ EMSCRIPTEN_BINDINGS() {
|
||||
class_<genericModel>("genericModel")
|
||||
.constructor<std::string, std::string, int, bool>(allow_raw_pointers())
|
||||
.function("check", &genericModel::check, allow_raw_pointers())
|
||||
.function("afterFetch", &genericModel::afterFetch, allow_raw_pointers())
|
||||
.function("load", &genericModel::load, allow_raw_pointers());
|
||||
.function("afterFetch", &genericModel::afterFetch, allow_raw_pointers());
|
||||
|
||||
class_<recognizer>("recognizer")
|
||||
.constructor<genericModel*, float, int>(allow_raw_pointers())
|
||||
|
||||
@@ -52,7 +52,7 @@ void genericModel::check() {
|
||||
thrd.addTask([this](){
|
||||
if(OPFSTried && !OPFSOk) {
|
||||
emscripten_console_log("OPFS isn't available");
|
||||
fireEv("_checkMdl", "OPFS isn't available", index);
|
||||
fireEv("_continue", "OPFS isn't available", index);
|
||||
return;
|
||||
}
|
||||
if(!OPFSTried){
|
||||
@@ -63,7 +63,7 @@ void genericModel::check() {
|
||||
emscripten_console_log("Initializing OPFS");
|
||||
if(!OPFSOk) {
|
||||
emscripten_console_log("OPFS initialization failed");
|
||||
fireEv("_checkMdl", "OPFS initialization failed", index);
|
||||
fireEv("_continue", "OPFS initialization failed", index);
|
||||
return;
|
||||
}
|
||||
fs::current_path("/opfs", tank);
|
||||
@@ -84,41 +84,24 @@ void genericModel::check() {
|
||||
}
|
||||
if(!checkFiles() && !fs::exists("id", tank)) {
|
||||
emscripten_console_log("Model is not available, fetching...");
|
||||
fireEv("_checkMdl", "fetch", index);
|
||||
fireEv("_continue", "1", index);
|
||||
return;
|
||||
}
|
||||
emscripten_console_log("Model is available, verifying ID");
|
||||
FILE* idFile {fopen("id", "r")};
|
||||
if(idFile == nullptr) {
|
||||
emscripten_console_log("Couldn't open id file");
|
||||
fireEv("_checkMdl", "Couldn't open id file", index);
|
||||
return;
|
||||
}
|
||||
if(fseek(idFile, 0, SEEK_END) != 0) {
|
||||
emscripten_console_log("Id file end seeking fail");
|
||||
fireEv("_checkMdl", "Id file end seeking fail", index);
|
||||
fclose(idFile);
|
||||
return;
|
||||
};
|
||||
long long oldsize{ftell(idFile)};
|
||||
char* oldid {new char[oldsize]};
|
||||
if(fseek(idFile, 0L, SEEK_SET) != 0) {
|
||||
emscripten_console_log("Id file start seeking fail");
|
||||
fireEv("_checkMdl", "Id file start seeking fail", index);
|
||||
fclose(idFile);
|
||||
return;
|
||||
};
|
||||
fread(oldid, 1, oldsize, idFile);
|
||||
fclose(idFile);
|
||||
if(strcmp(oldid, id.c_str()) != 0) {
|
||||
std::ifstream idFile("id");
|
||||
idFile.seekg(0, std::ios::end);
|
||||
size_t oldSize = idFile.tellg();
|
||||
std::string oldID(oldSize, ' ');
|
||||
idFile.seekg(0);
|
||||
idFile.read(&oldID[0], oldSize);
|
||||
if(id.compare(oldID.c_str()) != 0) {
|
||||
emscripten_console_log("ID doesn't match, fetching...");
|
||||
fireEv("_checkMdl", "fetch", index);
|
||||
fireEv("_continue", "1", index);
|
||||
}
|
||||
else {
|
||||
emscripten_console_log("ID match, returning instance");
|
||||
fireEv("_checkMdl", nullptr, index);
|
||||
emscripten_console_log("ID matches, loading...");
|
||||
//load();
|
||||
}
|
||||
delete[] oldid;
|
||||
emscripten_console_log("Success! Model is ready!");
|
||||
});
|
||||
}
|
||||
@@ -126,9 +109,9 @@ void genericModel::afterFetch() {
|
||||
thrd.addTask([this](){
|
||||
emscripten_console_log("Trying to extract...");
|
||||
if(!extract()) {
|
||||
fs::remove("/opfs/m0dEl.tar",tank);
|
||||
//fs::remove("/opfs/m0dEl.tar",tank);
|
||||
fs::current_path("/opfs", tank);
|
||||
fs::remove_all(storepath, tank);
|
||||
//fs::remove_all(storepath, tank);
|
||||
emscripten_console_log("Unable to extract model");
|
||||
fireEv("_continue", "Unable to extract model", index);
|
||||
return;
|
||||
@@ -167,13 +150,25 @@ void genericModel::afterFetch() {
|
||||
bool genericModel::extract() {
|
||||
static fs::path path{};
|
||||
static int fd{};
|
||||
static archive_entry* entry{archive_entry_new()};
|
||||
archive_entry* entry{archive_entry_new()};
|
||||
archive* src {archive_read_new()};
|
||||
auto cleanup {[&](){
|
||||
archive_entry_free(entry);
|
||||
archive_read_free(src);
|
||||
}};
|
||||
archive_read_support_format_tar(src);
|
||||
archive_read_open_filename(src, "/opfs/m0dEl.tar", 10240);
|
||||
if(archive_errno(src) != 0) return false;
|
||||
if(archive_errno(src) != 0) {
|
||||
cleanup();
|
||||
emscripten_console_log(archive_error_string(src));
|
||||
return false;
|
||||
}
|
||||
while(archive_read_next_header2(src, entry) == ARCHIVE_OK) {
|
||||
if(archive_errno(src) != 0) return false;
|
||||
if(archive_errno(src) != 0) {
|
||||
cleanup();
|
||||
emscripten_console_log(archive_error_string(src));
|
||||
return false;
|
||||
}
|
||||
path = archive_entry_pathname(entry);
|
||||
// Strip 1st component, keep relative path
|
||||
path = "." + path.generic_string().substr(path.generic_string().find("/"));
|
||||
@@ -183,16 +178,20 @@ bool genericModel::extract() {
|
||||
continue;
|
||||
}
|
||||
fd = creat(path.c_str(),0777);
|
||||
if(fd == -1) return false;
|
||||
if(fd == -1) {
|
||||
cleanup();
|
||||
return false;
|
||||
}
|
||||
archive_read_data_into_fd(src, fd);
|
||||
close(fd);
|
||||
if(archive_errno(src) != 0) {
|
||||
cleanup();
|
||||
emscripten_console_log(archive_error_string(src));
|
||||
return false;
|
||||
}
|
||||
}
|
||||
fs::remove("README",tank);
|
||||
fs::remove("/opfs/m0dEl.tar",tank);
|
||||
archive_read_free(src);
|
||||
cleanup();
|
||||
return true;
|
||||
}
|
||||
@@ -3,7 +3,7 @@
|
||||
|
||||
#include <string>
|
||||
#include <filesystem>
|
||||
#include <cstring>
|
||||
#include <fstream>
|
||||
#include <fcntl.h>
|
||||
#include <variant>
|
||||
|
||||
@@ -13,14 +13,14 @@
|
||||
namespace fs = std::filesystem;
|
||||
|
||||
struct genericModel {
|
||||
bool normalMdl{};
|
||||
bool recognizerUsedThrd{};
|
||||
int index{};
|
||||
bool normalMdl;
|
||||
bool recognizerUsedThrd;
|
||||
int index;
|
||||
std::string storepath;
|
||||
std::string id;
|
||||
std::variant<VoskModel*, VoskSpkModel*> mdl{};
|
||||
reusableThrd thrd{};
|
||||
static bool extract();
|
||||
std::variant<VoskModel*, VoskSpkModel*> mdl;
|
||||
reusableThrd thrd;
|
||||
bool extract();
|
||||
void load();
|
||||
void check();
|
||||
bool checkFiles();
|
||||
|
||||
@@ -20,7 +20,6 @@ reusableThrd::reusableThrd() {
|
||||
blocker.wait(done.test(std::memory_order_relaxed) || queue.empty(), std::memory_order_relaxed);
|
||||
blocker.clear(std::memory_order_relaxed);
|
||||
while(!queue.empty()) {
|
||||
emscripten_console_log("Executing task...");
|
||||
queue.front()();
|
||||
queue.pop();
|
||||
}
|
||||
|
||||
264
src/pre.js
264
src/pre.js
@@ -1,5 +1,4 @@
|
||||
let objs = []
|
||||
let dStream = new DecompressionStream("gzip")
|
||||
Module.cleanUp = () => {
|
||||
objs.forEach(obj => obj.delete())
|
||||
URL.revokeObjectURL(pthreadUrl)
|
||||
@@ -9,33 +8,31 @@ Module.locateFile = (path, scriptDir) => {
|
||||
if(path === "Vosklet.js") return pthreadUrl
|
||||
return scriptDir+path
|
||||
}
|
||||
|
||||
class genericModel extends EventTarget {
|
||||
constructor() {
|
||||
constructor(url, storepath, id, normalMdl) {
|
||||
super()
|
||||
objs.push(this)
|
||||
this.url = url
|
||||
this.storepath = storepath
|
||||
this.id = id
|
||||
this.normalMdl = normalMdl
|
||||
}
|
||||
static async _init(url, storepath, id, normalMdl) {
|
||||
let mdl = new genericModel()
|
||||
return new Promise((resolve, reject) => {
|
||||
mdl.addEventListener("_continue", (ev) => {
|
||||
if(ev.detail === "0") {
|
||||
return resolve(mdl)
|
||||
}
|
||||
mdl.delete()
|
||||
reject(ev.detail)
|
||||
}, {once : true})
|
||||
mdl.addEventListener("_checkMdl", async (ev) => {
|
||||
let mdl = new genericModel(url, storepath, id, normalMdl)
|
||||
mdl.addEventListener("_continue", async function listener(ev) {
|
||||
switch(ev.detail) {
|
||||
case "0":
|
||||
mdl.load(true);
|
||||
break;
|
||||
case "fetch":
|
||||
mdl.removeEventListener("_continue", listener)
|
||||
return resolve(mdl)
|
||||
case "1":
|
||||
let res = await fetch(url)
|
||||
if(!res.ok) {
|
||||
return reject("Unable to download model")
|
||||
}
|
||||
let wStream = await (await (await navigator.storage.getDirectory()).getFileHandle("m0dEl.tar", {create : true})).createWritable()
|
||||
let tarReader = res.body.pipeThrough(dStream).getReader()
|
||||
let tarReader = res.body.pipeThrough(new DecompressionStream("gzip")).getReader()
|
||||
while(true) {
|
||||
let readRes = await tarReader.read()
|
||||
if(!readRes.done) await wStream.write(readRes.value)
|
||||
@@ -46,9 +43,11 @@ class genericModel extends EventTarget {
|
||||
mdl.obj.afterFetch()
|
||||
break;
|
||||
default:
|
||||
mdl.delete()
|
||||
mdl.removeEventListener("_continue", listener)
|
||||
reject(ev.detail)
|
||||
}
|
||||
}, {once : true})
|
||||
})
|
||||
mdl.obj = new Module.genericModel(storepath, id, objs.length-1, normalMdl)
|
||||
mdl.obj.check()
|
||||
})
|
||||
@@ -58,9 +57,17 @@ class genericModel extends EventTarget {
|
||||
}
|
||||
}
|
||||
Module.makeModel = async (url, storepath, id) => {
|
||||
return genericModel._init(url, storepath, id, true)
|
||||
for (obj in objs) {
|
||||
if (typeof obj.normalMdl !== "undefined" && obj.normalMdl && obj.url === url && obj.storepath === storepath && obj.id === id) return obj;
|
||||
}
|
||||
return genericModel._init(url, storepath, id, true);
|
||||
}
|
||||
Module.makeSpkModel = async (url, storepath, id) => {
|
||||
for(obj in objs) {
|
||||
if(typeof obj.normalMdl !== "undefined" && !obj.normalMdl && obj.url === url && obj.storepath === storepath && obj.id === id) {
|
||||
return obj;
|
||||
}
|
||||
}
|
||||
return genericModel._init(url, storepath, id, false)
|
||||
}
|
||||
class Recognizer extends EventTarget {
|
||||
@@ -68,48 +75,29 @@ class Recognizer extends EventTarget {
|
||||
super()
|
||||
objs.push(this)
|
||||
}
|
||||
static async _init1(model, sampleRate) {
|
||||
let rec = new Recognizer()
|
||||
static async _init(model, sampleRate, mode, grammar, spkModel) {
|
||||
return new Promise((resolve, reject) => {
|
||||
let rec = new Recognizer()
|
||||
rec.addEventListener("_continue", (ev) => {
|
||||
if(ev.detail == "0") {
|
||||
if(ev.detail === "0") {
|
||||
rec.ptr = Module._malloc(512)
|
||||
return resolve(rec)
|
||||
}
|
||||
rec.delete()
|
||||
reject(ev.detail)
|
||||
}, {once : true})
|
||||
rec.obj = new Module.recognizer(model, sampleRate, objs.length-1)
|
||||
switch(mode) {
|
||||
case 1:
|
||||
rec.obj = new Module.recognizer(model, sampleRate, objs.length-1)
|
||||
break
|
||||
case 2:
|
||||
rec.obj = new Module.recognizer(model, spkModel, sampleRate, objs.length-1)
|
||||
break
|
||||
default:
|
||||
rec.obj = new Module.recognizer(model, grammar, sampleRate, objs.length-1, 0)
|
||||
}
|
||||
})
|
||||
}
|
||||
static async _init2(model, spkModel, sampleRate) {
|
||||
let rec = new Recognizer()
|
||||
return new Promise((resolve, reject) => {
|
||||
rec.addEventListener("_continue", (ev) => {
|
||||
if(ev.detail == "0") {
|
||||
rec.ptr = Module._malloc(512)
|
||||
return resolve(rec)
|
||||
}
|
||||
rec.delete()
|
||||
reject(ev.detail)
|
||||
}, {once : true})
|
||||
rec.obj = new Module.recognizer(model, spkModel, sampleRate, objs.length-1)
|
||||
})
|
||||
}
|
||||
static async _init3(model, grammar, sampleRate) {
|
||||
let rec = new Recognizer()
|
||||
return new Promise((resolve, reject) => {
|
||||
rec.addEventListener("_continue", (ev) => {
|
||||
if(ev.detail == "0") {
|
||||
rec.ptr = Module._malloc(512)
|
||||
return resolve(rec)
|
||||
}
|
||||
rec.delete()
|
||||
reject(ev.detail)
|
||||
}, {once : true})
|
||||
rec.obj = new Module.recognizer(model, grammar, sampleRate, objs.length-1, 0)
|
||||
})
|
||||
}
|
||||
}
|
||||
async getNode(ctx, channelIndex = 0) {
|
||||
if(typeof this.node === "undefined") {
|
||||
let msgChannel = new MessageChannel()
|
||||
@@ -149,13 +137,13 @@ class Recognizer extends EventTarget {
|
||||
}
|
||||
}
|
||||
Module.makeRecognizer = (model, sampleRate) => {
|
||||
return Recognizer._init(model.obj, sampleRate)
|
||||
return Recognizer._init(model.obj, sampleRate, 1)
|
||||
}
|
||||
Module.makeRecognizerWithSpkModel = (model, spkModel, sampleRate) => {
|
||||
return Recognizer._init2(model.obj, spkModel.obj, sampleRate)
|
||||
Module.makeRecognizerWithSpkModel = (model, sampleRate, spkModel) => {
|
||||
return Recognizer._init(model.obj, sampleRate, 2, null, spkModel)
|
||||
}
|
||||
Module.makeRecognizerWithGrm = (model, grammar, sampleRate) => {
|
||||
return Recognizer._init3(model.obj, grammar, sampleRate)
|
||||
Module.makeRecognizerWithGrm = (model, sampleRate, grammar) => {
|
||||
return Recognizer._init(model.obj, sampleRate, 3, grammar, null)
|
||||
}
|
||||
let processorUrl = URL.createObjectURL(new Blob(['(',
|
||||
(() => {
|
||||
@@ -177,168 +165,10 @@ let processorUrl = URL.createObjectURL(new Blob(['(',
|
||||
})
|
||||
}).toString()
|
||||
, ')()'], {type : "text/javascript"}))
|
||||
/*
|
||||
let pthreadUrl = URL.createObjectURL(new Blob(['(',
|
||||
(() => {
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2015 The Emscripten Authors
|
||||
* SPDX-License-Identifier: MIT
|
||||
*/
|
||||
|
||||
// Pthread Web Worker startup routine:
|
||||
// This is the entry point file that is loaded first by each Web Worker
|
||||
// that executes pthreads on the Emscripten application.
|
||||
|
||||
'use strict';
|
||||
|
||||
var Module = {};
|
||||
|
||||
// Thread-local guard variable for one-time init of the JS state
|
||||
var initializedJS = false;
|
||||
|
||||
function assert(condition, text) {
|
||||
if (!condition) abort('Assertion failed: ' + text);
|
||||
}
|
||||
|
||||
function threadPrintErr(...args) {
|
||||
var text = args.join(' ');
|
||||
console.error(text);
|
||||
}
|
||||
function threadAlert(...args) {
|
||||
var text = args.join(' ');
|
||||
postMessage({cmd: 'alert', text, threadId: Module['_pthread_self']()});
|
||||
}
|
||||
// We don't need out() for now, but may need to add it if we want to use it
|
||||
// here. Or, if this code all moves into the main JS, that problem will go
|
||||
// away. (For now, adding it here increases code size for no benefit.)
|
||||
var out = () => { throw 'out() is not defined in worker.js.'; }
|
||||
var err = threadPrintErr;
|
||||
self.alert = threadAlert;
|
||||
var dbg = threadPrintErr;
|
||||
|
||||
Module['instantiateWasm'] = (info, receiveInstance) => {
|
||||
// Instantiate from the module posted from the main thread.
|
||||
// We can just use sync instantiation in the worker.
|
||||
var module = Module['wasmModule'];
|
||||
// We don't need the module anymore; new threads will be spawned from the main thread.
|
||||
Module['wasmModule'] = null;
|
||||
var instance = new WebAssembly.Instance(module, info);
|
||||
// TODO: Due to Closure regression https://github.com/google/closure-compiler/issues/3193,
|
||||
// the above line no longer optimizes out down to the following line.
|
||||
// When the regression is fixed, we can remove this if/else.
|
||||
return receiveInstance(instance);
|
||||
}
|
||||
|
||||
// Turn unhandled rejected promises into errors so that the main thread will be
|
||||
// notified about them.
|
||||
self.onunhandledrejection = (e) => {
|
||||
throw e.reason || e;
|
||||
};
|
||||
|
||||
function handleMessage(e) {
|
||||
try {
|
||||
if (e.data.cmd === 'load') { // Preload command that is called once per worker to parse and load the Emscripten code.
|
||||
|
||||
// Until we initialize the runtime, queue up any further incoming messages.
|
||||
let messageQueue = [];
|
||||
self.onmessage = (e) => messageQueue.push(e);
|
||||
|
||||
// And add a callback for when the runtime is initialized.
|
||||
self.startWorker = (instance) => {
|
||||
Module = instance;
|
||||
// Notify the main thread that this thread has loaded.
|
||||
postMessage({ 'cmd': 'loaded' });
|
||||
// Process any messages that were queued before the thread was ready.
|
||||
for (let msg of messageQueue) {
|
||||
handleMessage(msg);
|
||||
}
|
||||
// Restore the real message handler.
|
||||
self.onmessage = handleMessage;
|
||||
};
|
||||
|
||||
// Module and memory were sent from main thread
|
||||
Module['wasmModule'] = e.data.wasmModule;
|
||||
|
||||
// Use `const` here to ensure that the variable is scoped only to
|
||||
// that iteration, allowing safe reference from a closure.
|
||||
for (const handler of e.data.handlers) {
|
||||
Module[handler] = (...args) => {
|
||||
postMessage({ cmd: 'callHandler', handler, args: args });
|
||||
}
|
||||
}
|
||||
|
||||
Module['wasmMemory'] = e.data.wasmMemory;
|
||||
|
||||
Module['buffer'] = Module['wasmMemory'].buffer;
|
||||
|
||||
Module['workerID'] = e.data.workerID;
|
||||
|
||||
Module['ENVIRONMENT_IS_PTHREAD'] = true;
|
||||
|
||||
if (typeof e.data.urlOrBlob == 'string') {
|
||||
importScripts(e.data.urlOrBlob);
|
||||
} else {
|
||||
var objectUrl = URL.createObjectURL(e.data.urlOrBlob);
|
||||
importScripts(objectUrl);
|
||||
URL.revokeObjectURL(objectUrl);
|
||||
}
|
||||
loadBR(Module);
|
||||
} else if (e.data.cmd === 'run') {
|
||||
// Pass the thread address to wasm to store it for fast access.
|
||||
Module['__emscripten_thread_init'](e.data.pthread_ptr, /*is_main=*/0, /*is_runtime=*/0, /*can_block=*/1);
|
||||
|
||||
// Await mailbox notifications with `Atomics.waitAsync` so we can start
|
||||
// using the fast `Atomics.notify` notification path.
|
||||
Module['__emscripten_thread_mailbox_await'](e.data.pthread_ptr);
|
||||
|
||||
assert(e.data.pthread_ptr);
|
||||
// Also call inside JS module to set up the stack frame for this pthread in JS module scope
|
||||
Module['establishStackSpace']();
|
||||
Module['PThread'].receiveObjectTransfer(e.data);
|
||||
Module['PThread'].threadInitTLS();
|
||||
|
||||
if (!initializedJS) {
|
||||
// Embind must initialize itself on all threads, as it generates support JS.
|
||||
// We only do this once per worker since they get reused
|
||||
Module['__embind_initialize_bindings']();
|
||||
initializedJS = true;
|
||||
}
|
||||
|
||||
try {
|
||||
Module['invokeEntryPoint'](e.data.start_routine, e.data.arg);
|
||||
} catch(ex) {
|
||||
if (ex != 'unwind') {
|
||||
// The pthread "crashed". Do not call `_emscripten_thread_exit` (which
|
||||
// would make this thread joinable). Instead, re-throw the exception
|
||||
// and let the top level handler propagate it back to the main thread.
|
||||
throw ex;
|
||||
}
|
||||
}
|
||||
} else if (e.data.cmd === 'cancel') { // Main thread is asking for a pthread_cancel() on this thread.
|
||||
if (Module['_pthread_self']()) {
|
||||
Module['__emscripten_thread_exit'](-1);
|
||||
}
|
||||
} else if (e.data.target === 'setimmediate') {
|
||||
// no-op
|
||||
} else if (e.data.cmd === 'checkMailbox') {
|
||||
if (initializedJS) {
|
||||
Module['checkMailbox']();
|
||||
}
|
||||
} else if (e.data.cmd) {
|
||||
// The received message looks like something that should be handled by this message
|
||||
// handler, (since there is a e.data.cmd field present), but is not one of the
|
||||
// recognized commands:
|
||||
err(`worker.js received unknown command ${e.data.cmd}`);
|
||||
err(e.data);
|
||||
}
|
||||
} catch(ex) {
|
||||
err(`worker.js onmessage() captured an uncaught exception: ${ex}`);
|
||||
if (ex?.stack) err(ex.stack);
|
||||
Module['__emscripten_thread_crashed']?.();
|
||||
throw ex;
|
||||
}
|
||||
};
|
||||
|
||||
self.onmessage = handleMessage;
|
||||
|
||||
}).toString()
|
||||
, ')()'], {type : "text/javascript"}))
|
||||
, ')()'], {type : "text/javascript"}))
|
||||
*/
|
||||
@@ -5,9 +5,9 @@
|
||||
struct recognizer {
|
||||
std::atomic_flag done{};
|
||||
std::atomic_flag controller{};
|
||||
float* dataPtr{};
|
||||
int index{};
|
||||
VoskRecognizer* rec{};
|
||||
float* dataPtr;
|
||||
int index;
|
||||
VoskRecognizer* rec;
|
||||
recognizer(genericModel* model, float sampleRate, int index);
|
||||
recognizer(genericModel* model, genericModel* spkModel, float sampleRate, int index);
|
||||
recognizer(genericModel* model, const std::string& grm, float sampleRate, int index, int dummy);
|
||||
|
||||
@@ -12,7 +12,7 @@
|
||||
## ```Module``` object
|
||||
| Function signature | Description |
|
||||
|---|---|
|
||||
| ```Promise<Model> makeModel(path: string, url: string, id: string)```<br><br>```Promise<SpkModel> makeSpkModel(path: string, url: string, id: string)``` | Make a ```Model``` or ```SpkModel```, model files must be directly under the model root, and compressed model must be in .tgz format. If:<br>- **path** contains valid model files and **id** is the same, there will not be a fetch from **url**.<br>- **path** doesn't contain valid model files, or if it contains valid model files but **id** is different, there will be a fetch from **url**, and the model is stored with **id**. |
|
||||
| ```Promise<Model> makeModel(path: string, url: string, id: string)```<br><br>```Promise<SpkModel> makeSpkModel(path: string, url: string, id: string)``` | Make a ```Model``` or ```SpkModel```, model files must be directly under the model root, and compressed model must be in .tgz format. If:<br>- **path** contains valid model files and **id** is the same, there will not be a fetch from **url**.<br>- **path** doesn't contain valid model files, or if it contains valid model files but **id** is different, there will be a fetch from **url**, and the model is stored with **id**. Creating models with the same parameters will return a reference to the first one created. |
|
||||
| ```Promise<Recognizer> makeRecognizer(model: Model, sampleRate: float)```<br><br>```Promise<Recognizer> makeRecognizerWithSpkModel(model: Model, spkModel: spkModel, sampleRate: float)```<br><br>```Promise<Recognizer> makeRecognizerWithGrm(model: Model, grammar: string, sampleRate: float)``` | Make a ```Recognizer```, it will use **model**'s thread if it's the first user of **model**, else it will use a new thread. |
|
||||
| ```setLogLevel(lvl: int)``` | Set Vosk's log level (default: ```0```: Info) <br>```-2```: Error<br>```-1```: Warning<br>```1```: Verbose<br>```2```: More verbose<br>```3```: Debug |
|
||||
| ```cleanUp()``` | A convenience function that call ```delete()``` on all objects and revoke all URLs. **Put this at the end of your code!** |
|
||||
@@ -43,9 +43,9 @@ Vosklet require SharedArrayBuffer to share thread's data, so these response head
|
||||
If you can't set them, you may use a HACKY workaround at *src/addCOI.js*.
|
||||
|
||||
## Origin Private Filesystem (OPFS)
|
||||
Vosklet needs the Emscripten WASMFS' OPFS to store its model, IDBFS was considered, but dropped because there is no direct way to read from IDBFS to C++ without copying to MEMFS (basically RAM). For safety with this, always:
|
||||
- Try catch ```window.loadBR()``` to to check for OPFS availability.
|
||||
- Check if there is enough space via ```navigator.storage.estimate()``` for TWICE THE MODEL SIZE before calling Module.makeModel
|
||||
Vosklet needs the Emscripten WASMFS' OPFS to store its model, IDBFS was considered, but dropped because there is no direct way to read from IDBFS to C++ without copying to MEMFS (RAM). For safety with this, always:
|
||||
- Try catch ```window.loadVosklet()``` to to check for OPFS availability.
|
||||
- Check if there is enough space via ```navigator.storage.estimate()``` for TWICE THE MODEL SIZE before calling ```Module.makeModel```
|
||||
|
||||
# Compilation
|
||||
Changing any option to non-default values requires recompilation
|
||||
@@ -58,5 +58,5 @@ cd Vosklet/src &&
|
||||
|---|---|---|
|
||||
| MAX_MEMORY | Set max memory, valid suffixes: kb, mb, gb, tb or none (bytes) | ```300mb```, as [recommended](https://alphacephei.com/vosk/models) |
|
||||
| MAX_THREADS | Set the max number of thread (2 min) | ```2``` (1 OPFS thread + 1 model/recognizer thread) |
|
||||
| COMPILE_JOBS | Set the number of jobs (threads) when compiling | ```$(nproc)``` |
|
||||
| COMPILE_JOBS | Set the number of jobs (threads) when building | ```$(nproc)``` |
|
||||
| EMSDK | Set EMSDK's path (will install EMSDK in root folder if unset) | ```../emsdk``` |
|
||||
|
||||
Reference in New Issue
Block a user