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

Hardcode event type since it is always "0", except for recognizer.

Browse Source
This commit is contained in:
msqr1
2024-03-16 17:25:58 -07:00
parent 39e08f3f48
commit 9c261cb5eb
11 changed files with 78 additions and 5924 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@@ -9,11 +9,10 @@
- Download multiple models
- Model storage path management (for multiple models)
- Model ID management (for model updates)
- Smaller JS size (>3.1MB vs 1.7MB)
- Smaller JS size (>3.1MB vs 1.4MB)
- All related files (pthread worker, worklet processor,...) are merged
- Shorter from-scratch build time
# Basic usage
- Use the prebuilt binary through JsDelivr.

5643
devel/Vosklet.js
View File

File diff suppressed because one or more lines are too long

166
devel/Vosklet.worker.js
View File

@@ -1,165 +1 @@
/**
* @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) => {
dbg(`calling handler on main thread: ${handler}`);
postMessage({ cmd: 'callHandler', handler, args: args });
}
}
Module['wasmMemory'] = e.data.wasmMemory;
Module['wasmOffsetData'] = e.data.wasmOffsetConverter;
Module['buffer'] = Module['wasmMemory'].buffer;
Module['workerID'] = e.data.workerID;
Module['ENVIRONMENT_IS_PTHREAD'] = true;
if (typeof e.data.urlOrBlob == 'string') {
importScripts(e.data.urlOrBlob);
} else {
var objectUrl = URL.createObjectURL(e.data.urlOrBlob);
importScripts(objectUrl);
URL.revokeObjectURL(objectUrl);
}
loadVosklet(Module);
} else if (e.data.cmd === 'run') {
// Pass the thread address to wasm to store it for fast access.
Module['__emscripten_thread_init'](e.data.pthread_ptr, /*is_main=*/0, /*is_runtime=*/0, /*can_block=*/1);
// Await mailbox notifications with `Atomics.waitAsync` so we can start
// using the fast `Atomics.notify` notification path.
Module['__emscripten_thread_mailbox_await'](e.data.pthread_ptr);
assert(e.data.pthread_ptr);
// Also call inside JS module to set up the stack frame for this pthread in JS module scope
Module['establishStackSpace']();
Module['PThread'].receiveObjectTransfer(e.data);
Module['PThread'].threadInitTLS();
if (!initializedJS) {
// Embind must initialize itself on all threads, as it generates support JS.
// We only do this once per worker since they get reused
Module['__embind_initialize_bindings']();
initializedJS = true;
}
try {
Module['invokeEntryPoint'](e.data.start_routine, e.data.arg);
} catch(ex) {
if (ex != 'unwind') {
// The pthread "crashed". Do not call `_emscripten_thread_exit` (which
// would make this thread joinable). Instead, re-throw the exception
// and let the top level handler propagate it back to the main thread.
throw ex;
}
dbg(`Pthread 0x${Module['_pthread_self']().toString(16)} completed its main entry point with an 'unwind', keeping the worker alive for asynchronous operation.`);
}
} 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;
"use strict";var Module={};var initializedJS=false;function threadPrintErr(...args){var text=args.join(" ");console.error(text)}function threadAlert(...args){var text=args.join(" ");postMessage({cmd:"alert",text:text,threadId:Module["_pthread_self"]()})}var err=threadPrintErr;self.alert=threadAlert;Module["instantiateWasm"]=(info,receiveInstance)=>{var module=Module["wasmModule"];Module["wasmModule"]=null;var instance=new WebAssembly.Instance(module,info);return receiveInstance(instance)};self.onunhandledrejection=e=>{throw e.reason||e};function handleMessage(e){try{if(e.data.cmd==="load"){let messageQueue=[];self.onmessage=e=>messageQueue.push(e);self.startWorker=instance=>{Module=instance;postMessage({"cmd":"loaded"});for(let msg of messageQueue){handleMessage(msg)}self.onmessage=handleMessage};Module["wasmModule"]=e.data.wasmModule;for(const handler of e.data.handlers){Module[handler]=(...args)=>{postMessage({cmd:"callHandler",handler:handler,args:args})}}Module["wasmMemory"]=e.data.wasmMemory;Module["buffer"]=Module["wasmMemory"].buffer;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)}loadVosklet(Module)}else if(e.data.cmd==="run"){Module["__emscripten_thread_init"](e.data.pthread_ptr,0,0,1);Module["__emscripten_thread_mailbox_await"](e.data.pthread_ptr);Module["establishStackSpace"]();Module["PThread"].receiveObjectTransfer(e.data);Module["PThread"].threadInitTLS();if(!initializedJS){Module["__embind_initialize_bindings"]();initializedJS=true}try{Module["invokeEntryPoint"](e.data.start_routine,e.data.arg)}catch(ex){if(ex!="unwind"){throw ex}}}else if(e.data.cmd==="cancel"){if(Module["_pthread_self"]()){Module["__emscripten_thread_exit"](-1)}}else if(e.data.target==="setimmediate"){}else if(e.data.cmd==="checkMailbox"){if(initializedJS){Module["checkMailbox"]()}}else if(e.data.cmd){err(`worker.js received unknown command ${e.data.cmd}`);err(e.data)}}catch(ex){Module["__emscripten_thread_crashed"]?.();throw ex}}self.onmessage=handleMessage;

4
devel/index.html
View File

@@ -4,7 +4,9 @@
<script src="Vosklet.js"></script>
<script>
window.onload = async () => {
window.module = await loadVosklet();
const module = await loadVosklet();
const model = await module.makeModel("../usage/en-model.tgz","model","ID");
const recognizer = await module.makeRecognizer()
}
</script>
</head>

6
devel/test.sh
View File

@@ -9,7 +9,7 @@ LIBARCHIVE=$(realpath libarchive) &&
CLAPACK_WASM=$(realpath clapack-wasm) &&
MAX_MEMORY=${MAX_MEMORY:-300mb} &&
MAX_THREADS=${MAX_THREADS:-5} &&
MAX_THREADS=${MAX_THREADS:-2} &&
EMSDK=${EMSDK:-$(realpath emsdk)} &&
if [ ! -d $EMSDK ]; then
@@ -28,7 +28,7 @@ fi
. $EMSDK/emsdk_env.sh &&
cd $SRC &&
MODE=0 && # 0: Ultra debug info, 1: Extremely optimized release, else custom
MODE=1 && # 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=$MAX_THREADS -sDISABLE_EXCEPTION_CATCHING=0 -sEXIT_RUNTIME=0 -sINVOKE_RUN=0 -sPOLYFILL=0 -sEXPORTED_FUNCTIONS=_malloc -sEXPORT_NAME=loadVosklet -sMALLOC=emmalloc -sEXPORTED_RUNTIME_METHODS=UTF8ToString,stringToUTF8OnStack -sENVIRONMENT=web,worker -I. -I$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
@@ -36,4 +36,4 @@ 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=$MAX_THREADS -sPOLYFILL=0 -sEXIT_RUNTIME=0 -sINVOKE_RUN=0 -sSUPPORT_LONGJMP=0 -sEXPORTED_FUNCTIONS=_malloc -sEXPORT_NAME=loadVosklet -sMALLOC=emmalloc -sEXPORTED_RUNTIME_METHODS=UTF8ToString,stringToUTF8OnStack -sENVIRONMENT=web,worker -I. -I$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 -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
fi

126
src/genericModel.cc
View File

@@ -1,48 +1,34 @@
#include "genericModel.h"
genericModel::genericModel(std::string storepath, std::string id, int index, bool normalMdl) : index(index), normalMdl(normalMdl), storepath(std::move(storepath)), id(std::move(id)), entry(archive_entry_new()) {}
genericModel::genericModel(std::string storepath, std::string id, int index, bool normalMdl) : index(index), normalMdl(normalMdl), storepath("/opfs/" + std::move(storepath)), id(std::move(id)), entry(archive_entry_new()) {}
void genericModel::load() {
auto main{[this](){
if(normalMdl) {
VoskModel* temp {vosk_model_new(".")};
if(temp == nullptr) {
fireEv("_continue", "Unable to load model for recognition", index);
return;
}
mdl = temp;
}
else {
VoskSpkModel* temp {vosk_spk_model_new(".")};
if(temp == nullptr) {
fireEv("_continue", "Unable to load model for recognition", index);
return;
}
mdl = temp;
}
fireEv("_continue", nullptr, index);
}};
thrd.addTask(main);
thrd.addTask([this](){
if(normalMdl) mdl = vosk_model_new(storepath.c_str());
else vosk_spk_model_new(storepath.c_str());
if(normalMdl && std::get<0>(mdl) == nullptr || std::get<1>(mdl) == nullptr) fireEv(index, "Unable to load model for recognition");
else fireEv(index, nullptr);
});
}
bool genericModel::checkFiles() {
if(normalMdl) {
return fs::exists("am/final.mdl", tank) &&
fs::exists("conf/mfcc.conf", tank) &&
fs::exists("conf/model.conf", tank) &&
fs::exists("graph/phones/word_boundary.int", tank) &&
fs::exists("graph/Gr.fst", tank) &&
fs::exists("graph/HCLr.fst", tank) &&
fs::exists("graph/disambig_tid.int", tank) &&
fs::exists("ivector/final.dubm", tank) &&
fs::exists("ivector/final.ie", tank) &&
fs::exists("ivector/final.mat", tank) &&
fs::exists("ivector/global_cmvn.stats", tank) &&
fs::exists("ivector/online_cmvn.conf", tank) &&
fs::exists("ivector/splice.conf", tank);
return fs::exists(storepath + "/am/final.mdl", tank) &&
fs::exists(storepath + "/conf/mfcc.conf", tank) &&
fs::exists(storepath + "/conf/model.conf", tank) &&
fs::exists(storepath + "/graph/phones/word_boundary.int", tank) &&
fs::exists(storepath + "/graph/Gr.fst", tank) &&
fs::exists(storepath + "/graph/HCLr.fst", tank) &&
fs::exists(storepath + "/graph/disambig_tid.int", tank) &&
fs::exists(storepath + "/ivector/final.dubm", tank) &&
fs::exists(storepath + "/ivector/final.ie", tank) &&
fs::exists(storepath + "/ivector/final.mat", tank) &&
fs::exists(storepath + "/ivector/global_cmvn.stats", tank) &&
fs::exists(storepath + "/ivector/online_cmvn.conf", tank) &&
fs::exists(storepath + "/ivector/splice.conf", tank);
}
return fs::exists("mfcc.conf", tank) &&
fs::exists("final.ext.raw", tank) &&
fs::exists("mean.vec", tank) &&
fs::exists("transform.mat", tank);
return fs::exists(storepath + "/mfcc.conf", tank) &&
fs::exists(storepath + "/final.ext.raw", tank) &&
fs::exists(storepath + "/mean.vec", tank) &&
fs::exists(storepath + "/transform.mat", tank);
}
genericModel::~genericModel() {
archive_entry_free(entry);
@@ -53,7 +39,7 @@ void genericModel::check() {
thrd.addTask([this](){
if(OPFSTried && !OPFSOk) {
emscripten_console_log("OPFS isn't available");
fireEv("_continue", "OPFS isn't available", index);
fireEv(index, "OPFS isn't available");
return;
}
if(!OPFSTried){
@@ -64,32 +50,16 @@ void genericModel::check() {
emscripten_console_log("Initializing OPFS");
if(!OPFSOk) {
emscripten_console_log("OPFS initialization failed");
fireEv("_continue", "OPFS initialization failed", index);
fireEv(index, "OPFS initialization failed");
return;
}
fs::current_path("/opfs", tank);
if(tank.value() != 0) {
emscripten_console_log("Unable to cd OPFS root");
fireEv("_continue","Unable to cd OPFS root", index);
return;
}
fs::create_directories(storepath, tank);
if(tank.value() != 0) {
emscripten_console_log("Unable to create storepath");
fireEv("_continue","Unable to create storepath", index);
}
fs::current_path(storepath, tank);
if(tank.value() != 0) {
emscripten_console_log("Unable to cd storepath");
fireEv("_continue", "Unable to cd storepath", index);
}
if(!checkFiles() && !fs::exists("id", tank)) {
if(!checkFiles() && !fs::exists(storepath + "/id", tank)) {
emscripten_console_log("Model is not available, fetching...");
fireEv("_continue", "1", index);
fireEv(index, "1");
return;
}
emscripten_console_log("Model is available, verifying ID");
std::ifstream idFile("id");
std::ifstream idFile(storepath + "/id");
idFile.seekg(0, std::ios::end);
size_t oldSize = idFile.tellg();
std::string oldID(oldSize, ' ');
@@ -97,11 +67,11 @@ void genericModel::check() {
idFile.read(&oldID[0], oldSize);
if(id.compare(oldID.c_str()) != 0) {
emscripten_console_log("ID doesn't match, fetching...");
fireEv("_continue", "1", index);
fireEv(index, "1");
}
else {
emscripten_console_log("ID matches, loading...");
//load();
load();
}
emscripten_console_log("Success! Model is ready!");
});
@@ -110,35 +80,32 @@ void genericModel::afterFetch() {
thrd.addTask([this](){
emscripten_console_log("Trying to extract...");
if(!extract()) {
//fs::remove("/opfs/m0dEl.tar",tank);
fs::current_path("/opfs", tank);
//fs::remove_all(storepath, tank);
fs::remove(storepath + ".tar",tank);
fs::remove_all(storepath, tank);
emscripten_console_log("Unable to extract model");
fireEv("_continue", "Unable to extract model", index);
fireEv(index, "Unable to extract model");
return;
}
emscripten_console_log("Extract done, checking files...");
if(!checkFiles()) {
emscripten_console_log("URL points to invalid model files");
fireEv("_continue", "URL points to invalid model files", index);
fireEv(index, "URL points to invalid model files");
return;
}
emscripten_console_log("Creating ID file...");
int idFd {creat("id",0777)};
int idFd {creat((storepath + "/id").c_str(),0777)};
if(idFd == -1) {
emscripten_console_log("Unable to create ID file");
fireEv("_continue", "Unable to create ID file", index);
fs::remove("/opfs/m0dEl.tar",tank);
fs::current_path("/opfs", tank);
fireEv(index, "Unable to create ID file");
fs::remove(storepath + ".tar",tank);
fs::remove_all(storepath, tank);
return;
}
emscripten_console_log("Writing ID...");
if(write(idFd, id.c_str(), id.size()) == -1) {
if(write(idFd,id.data(), id.size()) == -1) {
emscripten_console_log("Unable to write new ID");
fireEv("_continue", "Unable to write new ID", index);
fs::remove("/opfs/m0dEl.tar",tank);
fs::current_path("/opfs", tank);
fireEv(index, "Unable to write new ID");
fs::remove(storepath + ".tar",tank);
fs::remove_all(storepath, tank);
close(idFd);
return;
@@ -146,14 +113,14 @@ void genericModel::afterFetch() {
close(idFd);
emscripten_console_log("Success! Model is ready!");
});
//load();
load();
}
bool genericModel::extract() {
static fs::path path{};
static int fd{};
archive* src {archive_read_new()};
archive_read_support_format_tar(src);
archive_read_open_filename(src, "/opfs/m0dEl.tar", 10240);
archive_read_open_filename(src, (storepath + ".tar").c_str(), 10240);
if(archive_errno(src) != 0) {
emscripten_console_log(archive_error_string(src));
return false;
@@ -164,8 +131,7 @@ bool genericModel::extract() {
return false;
}
path = archive_entry_pathname(entry);
// Strip 1st component, keep relative path
path = "." + path.generic_string().substr(path.generic_string().find("/"));
path = storepath + path.generic_string().substr(path.generic_string().find("/"));
emscripten_console_logf("Creating file/dir %s", path.c_str());
if(!path.has_extension()) {
fs::create_directory(path);
@@ -182,8 +148,8 @@ bool genericModel::extract() {
return false;
}
}
fs::remove("README",tank);
fs::remove("/opfs/m0dEl.tar",tank);
fs::remove(storepath + "/README",tank);
fs::remove(storepath + ".tar" ,tank);
archive_read_free(src);
return true;
}

10
src/global.cc
View File

@@ -5,11 +5,13 @@ std::error_code tank{};
bool OPFSOk{};
bool OPFSTried{};
ProxyingQueue glbQ{};
void fireEv(const char *type, const char *content, int index) {
auto proxy{[index, type, content](){
void fireEv(int index, const char* content, const char* type) {
auto proxy{[index, content, type](){
emscripten_console_logf("Firing event, index: %d, content: %s, type: %s", index, content, type);
EM_ASM({
objs[$0].dispatchEvent(new CustomEvent(UTF8ToString($1), {"detail" : UTF8ToString($2)}));
},index, type, content);
console.log(objs[$0]);
objs[$0].dispatchEvent(new CustomEvent($2 === 0 ? "0" : UTF8ToString($2), {"detail" : UTF8ToString($1)}));
}, index, content, type);
}};
if(dstThrd == pthread_self()) proxy();
else glbQ.proxySync(dstThrd, proxy);

2
src/global.h
View File

@@ -15,7 +15,7 @@ extern std::error_code tank;
extern pthread_t dstThrd;
extern ProxyingQueue glbQ;
void fireEv(const char *type, const char *content, int index);
void fireEv(int index, const char* content, const char* type = nullptr);
struct reusableThrd {
std::queue<std::function<void()>> queue{};
std::atomic_flag blocker{};

32
src/pre.js
View File

@@ -8,7 +8,6 @@ Module.locateFile = (path, scriptDir) => {
if(path === "Vosklet.js") return pthreadUrl
return scriptDir+path
}
class genericModel extends EventTarget {
constructor(url, storepath, id, normalMdl) {
super()
@@ -21,17 +20,17 @@ class genericModel extends EventTarget {
static async _init(url, storepath, id, normalMdl) {
return new Promise((resolve, reject) => {
let mdl = new genericModel(url, storepath, id, normalMdl)
mdl.addEventListener("_continue", async function listener(ev) {
mdl.addEventListener("0", async function listener(ev) {
switch(ev.detail) {
case "0":
mdl.removeEventListener("_continue", listener)
mdl.removeEventListener("0", 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 wStream = await (await (await navigator.storage.getDirectory()).getFileHandle(storepath + ".tar", {create : true})).createWritable()
let tarReader = res.body.pipeThrough(new DecompressionStream("gzip")).getReader()
while(true) {
let readRes = await tarReader.read()
@@ -40,11 +39,12 @@ class genericModel extends EventTarget {
}
tarReader.releaseLock()
await wStream.close()
console.log("Fetching and writing tar done!")
mdl.obj.afterFetch()
break;
break
default:
mdl.delete()
mdl.removeEventListener("_continue", listener)
mdl.removeEventListener("0", listener)
reject(ev.detail)
}
})
@@ -57,17 +57,9 @@ class genericModel extends EventTarget {
}
}
Module.makeModel = async (url, storepath, id) => {
for (let 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);
return genericModel._init(url, storepath, id, true)
}
Module.makeSpkModel = async (url, storepath, id) => {
for(let 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 {
@@ -78,7 +70,7 @@ class Recognizer extends EventTarget {
static async _init(model, sampleRate, mode, grammar, spkModel) {
return new Promise((resolve, reject) => {
let rec = new Recognizer()
rec.addEventListener("_continue", (ev) => {
rec.addEventListener("0", (ev) => {
if(ev.detail === "0") {
rec.ptr = Module._malloc(512)
return resolve(rec)
@@ -165,10 +157,8 @@ let processorUrl = URL.createObjectURL(new Blob(['(',
})
}).toString()
, ')()'], {type : "text/javascript"}))
/*
let pthreadUrl = URL.createObjectURL(new Blob(['(',
/*let pthreadUrl = URL.createObjectURL(new Blob(['(',
(() => {
{ PTHREAD_SCRIPT }
}).toString()
, ')()'], {type : "text/javascript"}))
*/
, ')()'], {type : "text/javascript"})) */

8
src/recognizer.cc
View File

@@ -22,21 +22,21 @@ recognizer::~recognizer() {
}
void recognizer::finishConstruction(genericModel* model, genericModel* spkModel) {
if(rec == nullptr) {
fireEv("_continue", "Unable to initialize recognizer", this->index);
fireEv(index, "Unable to initialize recognizer");
return;
}
auto main {[this](){
fireEv("_continue", nullptr, index);
fireEv(index, "0");
while(!done.test(std::memory_order_relaxed)) {
controller.wait(!done.test(std::memory_order_relaxed), std::memory_order_relaxed);
controller.clear(std::memory_order_relaxed);
if(done.test(std::memory_order_relaxed)) continue;
switch(vosk_recognizer_accept_waveform_f(rec, dataPtr, 512)) {
case 0:
fireEv("result", vosk_recognizer_result(rec), index);
fireEv(index, vosk_recognizer_result(rec), "result");
break;
case 1:
fireEv("partialResult", vosk_recognizer_partial_result(rec), index);
fireEv(index, vosk_recognizer_partial_result(rec), "partialResult");
}
}
}};

2
usage/README.md
View File

@@ -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**. Creating models with the same parameters will return a reference to the first one created. |
| ```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**. Models are thread-safe, reuse them as much as possible! |
| ```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!** |