addon.node : using whisper as a Node.js addon (#443)

* addon: implement node addon call whisper through cpp

* addon: modify the license to MIT

* addon: remove iostream

* addon: rename dir

* addon: fix typo

* addon: configure cmake to build when cmake-js is used

examples/CMakeLists.txt

@@ -24,6 +24,8 @@ if (EMSCRIPTEN)
     add_subdirectory(command.wasm)
     add_subdirectory(talk.wasm)
     add_subdirectory(bench.wasm)
+elseif(CMAKE_JS_VERSION)
+    add_subdirectory(addon.node)
 else()
     add_subdirectory(main)
     add_subdirectory(stream)

examples/addon.node/.gitignore

@@ -0,0 +1,3 @@
+.idea
+node_modules
+build

examples/addon.node/CMakeLists.txt

@@ -0,0 +1,26 @@
+set(TARGET whisper-addon)
+
+# Base settings
+#==================================================================
+# env var supported by cmake-js
+add_definitions(-DNAPI_VERSION=4)
+include_directories(${CMAKE_JS_INC})
+#==================================================================
+
+add_library(${TARGET} SHARED ${CMAKE_JS_SRC} addon.cpp)
+set_target_properties(${TARGET} PROPERTIES PREFIX "" SUFFIX ".node")
+
+include(DefaultTargetOptions)
+
+# Include N-API wrappers
+#==================================================================
+execute_process(COMMAND node -p "require('node-addon-api').include"
+        WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
+        OUTPUT_VARIABLE NODE_ADDON_API_DIR
+        )
+string(REPLACE "\n" "" NODE_ADDON_API_DIR ${NODE_ADDON_API_DIR})
+string(REPLACE "\"" "" NODE_ADDON_API_DIR ${NODE_ADDON_API_DIR})
+target_include_directories(${TARGET} PRIVATE ${NODE_ADDON_API_DIR})
+#==================================================================
+
+target_link_libraries(${TARGET} ${CMAKE_JS_LIB} whisper ${CMAKE_THREAD_LIBS_INIT})

examples/addon.node/README.md

@@ -0,0 +1,37 @@
+# addon
+
+This is an addon demo that can **perform whisper model reasoning in `node` and `electron` environments**, based on [cmake-js](https://github.com/cmake-js/cmake-js).
+It can be used as a reference for using the whisper.cpp project in other node projects.
+
+## Install
+
+```shell
+npm install
+```
+
+## Compile
+
+Make sure it is in the project root directory and compiled with make-js.
+
+```shell
+npx cmake-js compile -T whisper-addon
+```
+
+For Electron addon and cmake-js options, you can see [cmake-js](https://github.com/cmake-js/cmake-js) and make very few configuration changes.
+
+> Such as appointing special cmake path:
+> ```shell
+> npx cmake-js compile -c 'xxx/cmake' -T whisper-addon
+> ```
+
+## Run
+
+```shell
+cd examples/addon.node
+
+node index.js --language='language' --model='model-path' --fname_inp='file-path'
+```
+
+Because this is a simple Demo, only the above parameters are set in the node environment.
+
+Other parameters can also be specified in the node environment.

examples/addon.node/addon.cpp

@@ -0,0 +1,421 @@
+#include <string>
+#include <thread>
+#include <vector>
+#include <cmath>
+
+#include "napi.h"
+
+#define DR_WAV_IMPLEMENTATION
+#include "dr_wav.h"
+
+#include "whisper.h"
+
+struct whisper_params {
+    int32_t n_threads    = std::min(4, (int32_t) std::thread::hardware_concurrency());
+    int32_t n_processors = 1;
+    int32_t offset_t_ms  = 0;
+    int32_t offset_n     = 0;
+    int32_t duration_ms  = 0;
+    int32_t max_context  = -1;
+    int32_t max_len      = 0;
+    int32_t best_of      = 5;
+    int32_t beam_size    = -1;
+
+    float word_thold    = 0.01f;
+    float entropy_thold = 2.4f;
+    float logprob_thold = -1.0f;
+
+    bool speed_up       = false;
+    bool translate      = false;
+    bool diarize        = false;
+    bool output_txt     = false;
+    bool output_vtt     = false;
+    bool output_srt     = false;
+    bool output_wts     = false;
+    bool output_csv     = false;
+    bool print_special  = false;
+    bool print_colors   = false;
+    bool print_progress = false;
+    bool no_timestamps  = false;
+
+    std::string language = "en";
+    std::string prompt;
+    std::string model    = "../../ggml-large.bin";
+
+    std::vector<std::string> fname_inp = {};
+    std::vector<std::string> fname_outp = {};
+};
+
+struct whisper_print_user_data {
+    const whisper_params * params;
+
+    const std::vector<std::vector<float>> * pcmf32s;
+};
+
+//  500 -> 00:05.000
+// 6000 -> 01:00.000
+std::string to_timestamp(int64_t t, bool comma = false) {
+    int64_t msec = t * 10;
+    int64_t hr = msec / (1000 * 60 * 60);
+    msec = msec - hr * (1000 * 60 * 60);
+    int64_t min = msec / (1000 * 60);
+    msec = msec - min * (1000 * 60);
+    int64_t sec = msec / 1000;
+    msec = msec - sec * 1000;
+
+    char buf[32];
+    snprintf(buf, sizeof(buf), "%02d:%02d:%02d%s%03d", (int) hr, (int) min, (int) sec, comma ? "," : ".", (int) msec);
+
+    return std::string(buf);
+}
+
+int timestamp_to_sample(int64_t t, int n_samples) {
+    return std::max(0, std::min((int) n_samples - 1, (int) ((t*WHISPER_SAMPLE_RATE)/100)));
+}
+
+void whisper_print_segment_callback(struct whisper_context * ctx, int n_new, void * user_data) {
+    const auto & params  = *((whisper_print_user_data *) user_data)->params;
+    const auto & pcmf32s = *((whisper_print_user_data *) user_data)->pcmf32s;
+
+    const int n_segments = whisper_full_n_segments(ctx);
+
+    std::string speaker = "";
+
+    int64_t t0;
+    int64_t t1;
+
+    // print the last n_new segments
+    const int s0 = n_segments - n_new;
+
+    if (s0 == 0) {
+        printf("\n");
+    }
+
+    for (int i = s0; i < n_segments; i++) {
+        if (!params.no_timestamps || params.diarize) {
+            t0 = whisper_full_get_segment_t0(ctx, i);
+            t1 = whisper_full_get_segment_t1(ctx, i);
+        }
+
+        if (!params.no_timestamps) {
+            printf("[%s --> %s]  ", to_timestamp(t0).c_str(), to_timestamp(t1).c_str());
+        }
+
+        if (params.diarize && pcmf32s.size() == 2) {
+            const int64_t n_samples = pcmf32s[0].size();
+
+            const int64_t is0 = timestamp_to_sample(t0, n_samples);
+            const int64_t is1 = timestamp_to_sample(t1, n_samples);
+
+            double energy0 = 0.0f;
+            double energy1 = 0.0f;
+
+            for (int64_t j = is0; j < is1; j++) {
+                energy0 += fabs(pcmf32s[0][j]);
+                energy1 += fabs(pcmf32s[1][j]);
+            }
+
+            if (energy0 > 1.1*energy1) {
+                speaker = "(speaker 0)";
+            } else if (energy1 > 1.1*energy0) {
+                speaker = "(speaker 1)";
+            } else {
+                speaker = "(speaker ?)";
+            }
+
+            //printf("is0 = %lld, is1 = %lld, energy0 = %f, energy1 = %f, %s\n", is0, is1, energy0, energy1, speaker.c_str());
+        }
+
+        // colorful print bug
+        //
+        const char * text = whisper_full_get_segment_text(ctx, i);
+        printf("%s%s", speaker.c_str(), text);
+
+
+        // with timestamps or speakers: each segment on new line
+        if (!params.no_timestamps || params.diarize) {
+            printf("\n");
+        }
+
+        fflush(stdout);
+    }
+}
+
+int run(whisper_params &params, std::vector<std::vector<std::string>> &result) {
+
+    if (params.fname_inp.empty()) {
+        fprintf(stderr, "error: no input files specified\n");
+        return 2;
+    }
+
+    if (params.language != "auto" && whisper_lang_id(params.language.c_str()) == -1) {
+        fprintf(stderr, "error: unknown language '%s'\n", params.language.c_str());
+        exit(0);
+    }
+
+    // whisper init
+
+    struct whisper_context * ctx = whisper_init_from_file(params.model.c_str());
+
+    if (ctx == nullptr) {
+        fprintf(stderr, "error: failed to initialize whisper context\n");
+        return 3;
+    }
+
+    // initial prompt
+    std::vector<whisper_token> prompt_tokens;
+
+    if (!params.prompt.empty()) {
+        prompt_tokens.resize(1024);
+        prompt_tokens.resize(whisper_tokenize(ctx, params.prompt.c_str(), prompt_tokens.data(), prompt_tokens.size()));
+
+        fprintf(stderr, "\n");
+        fprintf(stderr, "initial prompt: '%s'\n", params.prompt.c_str());
+        fprintf(stderr, "initial tokens: [ ");
+        for (int i = 0; i < (int) prompt_tokens.size(); ++i) {
+            fprintf(stderr, "%d ", prompt_tokens[i]);
+        }
+        fprintf(stderr, "]\n");
+    }
+
+    for (int f = 0; f < (int) params.fname_inp.size(); ++f) {
+        const auto fname_inp = params.fname_inp[f];
+        const auto fname_outp = f < (int)params.fname_outp.size() && !params.fname_outp[f].empty() ? params.fname_outp[f] : params.fname_inp[f];
+
+        std::vector<float> pcmf32; // mono-channel F32 PCM
+        std::vector<std::vector<float>> pcmf32s; // stereo-channel F32 PCM
+
+        // WAV input
+        {
+            drwav wav;
+            std::vector<uint8_t> wav_data; // used for pipe input from stdin
+
+            if (fname_inp == "-") {
+                {
+                    uint8_t buf[1024];
+                    while (true)
+                    {
+                        const size_t n = fread(buf, 1, sizeof(buf), stdin);
+                        if (n == 0) {
+                            break;
+                        }
+                        wav_data.insert(wav_data.end(), buf, buf + n);
+                    }
+                }
+
+                if (drwav_init_memory(&wav, wav_data.data(), wav_data.size(), nullptr) == false) {
+                    fprintf(stderr, "error: failed to open WAV file from stdin\n");
+                    return 4;
+                }
+
+                fprintf(stderr, "%s: read %zu bytes from stdin\n", __func__, wav_data.size());
+            }
+            else if (drwav_init_file(&wav, fname_inp.c_str(), nullptr) == false) {
+                fprintf(stderr, "error: failed to open '%s' as WAV file\n", fname_inp.c_str());
+                return 5;
+            }
+
+           if (wav.channels != 1 && wav.channels != 2) {
+               fprintf(stderr, "error: WAV file '%s' must be mono or stereo\n", fname_inp.c_str());
+               return 6;
+           }
+
+           if (params.diarize && wav.channels != 2 && params.no_timestamps == false) {
+               fprintf(stderr, "error: WAV file '%s' must be stereo for diarization and timestamps have to be enabled\n", fname_inp.c_str());
+               return 6;
+           }
+
+           if (wav.sampleRate != WHISPER_SAMPLE_RATE) {
+               fprintf(stderr, "error: WAV file '%s' must be %i kHz\n", fname_inp.c_str(), WHISPER_SAMPLE_RATE/1000);
+               return 8;
+           }
+
+           if (wav.bitsPerSample != 16) {
+               fprintf(stderr, "error: WAV file '%s' must be 16-bit\n", fname_inp.c_str());
+               return 9;
+           }
+
+            const uint64_t n = wav_data.empty() ? wav.totalPCMFrameCount : wav_data.size()/(wav.channels*wav.bitsPerSample/8);
+
+            std::vector<int16_t> pcm16;
+            pcm16.resize(n*wav.channels);
+            drwav_read_pcm_frames_s16(&wav, n, pcm16.data());
+            drwav_uninit(&wav);
+
+            // convert to mono, float
+            pcmf32.resize(n);
+            if (wav.channels == 1) {
+                for (uint64_t i = 0; i < n; i++) {
+                    pcmf32[i] = float(pcm16[i])/32768.0f;
+                }
+            } else {
+                for (uint64_t i = 0; i < n; i++) {
+                    pcmf32[i] = float(pcm16[2*i] + pcm16[2*i + 1])/65536.0f;
+                }
+            }
+
+            if (params.diarize) {
+                // convert to stereo, float
+                pcmf32s.resize(2);
+
+                pcmf32s[0].resize(n);
+                pcmf32s[1].resize(n);
+                for (uint64_t i = 0; i < n; i++) {
+                    pcmf32s[0][i] = float(pcm16[2*i])/32768.0f;
+                    pcmf32s[1][i] = float(pcm16[2*i + 1])/32768.0f;
+                }
+            }
+        }
+
+        // print system information
+        {
+            fprintf(stderr, "\n");
+            fprintf(stderr, "system_info: n_threads = %d / %d | %s\n",
+                    params.n_threads*params.n_processors, std::thread::hardware_concurrency(), whisper_print_system_info());
+        }
+
+        // print some info about the processing
+        {
+            fprintf(stderr, "\n");
+            if (!whisper_is_multilingual(ctx)) {
+                if (params.language != "en" || params.translate) {
+                    params.language = "en";
+                    params.translate = false;
+                    fprintf(stderr, "%s: WARNING: model is not multilingual, ignoring language and translation options\n", __func__);
+                }
+            }
+            fprintf(stderr, "%s: processing '%s' (%d samples, %.1f sec), %d threads, %d processors, lang = %s, task = %s, timestamps = %d ...\n",
+                    __func__, fname_inp.c_str(), int(pcmf32.size()), float(pcmf32.size())/WHISPER_SAMPLE_RATE,
+                    params.n_threads, params.n_processors,
+                    params.language.c_str(),
+                    params.translate ? "translate" : "transcribe",
+                    params.no_timestamps ? 0 : 1);
+
+            fprintf(stderr, "\n");
+        }
+
+        // run the inference
+        {
+            whisper_full_params wparams = whisper_full_default_params(WHISPER_SAMPLING_GREEDY);
+
+            wparams.strategy = params.beam_size > 1 ? WHISPER_SAMPLING_BEAM_SEARCH : WHISPER_SAMPLING_GREEDY;
+
+            wparams.print_realtime   = false;
+            wparams.print_progress   = params.print_progress;
+            wparams.print_timestamps = !params.no_timestamps;
+            wparams.print_special    = params.print_special;
+            wparams.translate        = params.translate;
+            wparams.language         = params.language.c_str();
+            wparams.n_threads        = params.n_threads;
+            wparams.n_max_text_ctx   = params.max_context >= 0 ? params.max_context : wparams.n_max_text_ctx;
+            wparams.offset_ms        = params.offset_t_ms;
+            wparams.duration_ms      = params.duration_ms;
+
+            wparams.token_timestamps = params.output_wts || params.max_len > 0;
+            wparams.thold_pt         = params.word_thold;
+            wparams.entropy_thold    = params.entropy_thold;
+            wparams.logprob_thold    = params.logprob_thold;
+            wparams.max_len          = params.output_wts && params.max_len == 0 ? 60 : params.max_len;
+
+            wparams.speed_up         = params.speed_up;
+
+            wparams.greedy.best_of        = params.best_of;
+            wparams.beam_search.beam_size = params.beam_size;
+
+            wparams.prompt_tokens     = prompt_tokens.empty() ? nullptr : prompt_tokens.data();
+            wparams.prompt_n_tokens   = prompt_tokens.empty() ? 0       : prompt_tokens.size();
+
+            whisper_print_user_data user_data = { &params, &pcmf32s };
+
+            // this callback is called on each new segment
+            if (!wparams.print_realtime) {
+                wparams.new_segment_callback           = whisper_print_segment_callback;
+                wparams.new_segment_callback_user_data = &user_data;
+            }
+
+            // example for abort mechanism
+            // in this example, we do not abort the processing, but we could if the flag is set to true
+            // the callback is called before every encoder run - if it returns false, the processing is aborted
+            {
+                static bool is_aborted = false; // NOTE: this should be atomic to avoid data race
+
+                wparams.encoder_begin_callback = [](struct whisper_context * /*ctx*/, void * user_data) {
+                    bool is_aborted = *(bool*)user_data;
+                    return !is_aborted;
+                };
+                wparams.encoder_begin_callback_user_data = &is_aborted;
+            }
+
+            if (whisper_full_parallel(ctx, wparams, pcmf32.data(), pcmf32.size(), params.n_processors) != 0) {
+                fprintf(stderr, "failed to process audio\n");
+                return 10;
+            }
+        }
+    }
+
+    const int n_segments = whisper_full_n_segments(ctx);
+    result.resize(n_segments);
+    for (int i = 0; i < n_segments; ++i) {
+        const char * text = whisper_full_get_segment_text(ctx, i);
+        const int64_t t0 = whisper_full_get_segment_t0(ctx, i);
+        const int64_t t1 = whisper_full_get_segment_t1(ctx, i);
+
+        result[i].emplace_back(to_timestamp(t0, true));
+        result[i].emplace_back(to_timestamp(t1, true));
+        result[i].emplace_back(text);
+    }
+
+    whisper_print_timings(ctx);
+    whisper_free(ctx);
+
+    return 0;
+}
+
+Napi::Object whisper(const Napi::CallbackInfo& info) {
+    Napi::Env env = info.Env();
+    if (info.Length() <= 0 || !info[0].IsObject()) {
+        Napi::TypeError::New(env, "object expected").ThrowAsJavaScriptException();
+    }
+    whisper_params params;
+    std::vector<std::vector<std::string>> result;
+
+    Napi::Object whisper_params = info[0].As<Napi::Object>();
+    std::string language = whisper_params.Get("language").As<Napi::String>();
+    std::string model = whisper_params.Get("model").As<Napi::String>();
+    std::string input = whisper_params.Get("fname_inp").As<Napi::String>();
+
+    params.language = language;
+    params.model = model;
+    params.fname_inp.emplace_back(input);
+
+    // run model
+    run(params, result);
+
+    fprintf(stderr, "RESULT:\n");
+    for (auto sentence:result) {
+        fprintf(stderr, "t0: %s, t1: %s, content: %s \n",
+                sentence[0].c_str(), sentence[1].c_str(), sentence[2].c_str());
+    }
+
+    Napi::Object res = Napi::Array::New(env, result.size());
+    for (u_int32_t i = 0; i < result.size(); ++i) {
+        Napi::Object tmp = Napi::Array::New(env, 3);
+        for (u_int32_t j = 0; j < 3; ++j) {
+            tmp[j] = Napi::String::New(env, result[i][j]);
+        }
+        res[i] = tmp;
+    }
+
+    return res;
+}
+
+
+Napi::Object Init(Napi::Env env, Napi::Object exports) {
+    exports.Set(
+            Napi::String::New(env, "whisper"),
+            Napi::Function::New(env, whisper)
+    );
+    return exports;
+}
+
+NODE_API_MODULE(whisper, Init);

examples/addon.node/index.js

@@ -0,0 +1,27 @@
+const path = require('path');
+const { whisper } = require(path.join(__dirname, '../../build/Release/whisper-addon'));
+
+const whisperParams = {
+    language: 'en',
+    model: path.join(__dirname, '../../models/ggml-base.en.bin'),
+    fname_inp: '',
+};
+
+const arguments = process.argv.slice(2);
+const params = Object.fromEntries(
+    arguments.reduce((pre, item) => {
+        if (item.startsWith("--")) {
+            return [...pre, item.slice(2).split("=")];
+        }
+        return pre;
+    }, []),
+);
+
+for (const key in params) {
+    if (whisperParams.hasOwnProperty(key)) {
+        whisperParams[key] = params[key];
+    }
+}
+
+console.log('whisperParams =', whisperParams);
+console.log(whisper(whisperParams));

examples/addon.node/package.json

@@ -0,0 +1,12 @@
+{
+  "name": "whisper-addon",
+  "version": "0.0.0",
+  "description": "",
+  "main": "index.js",
+  "author": "Qanhe Chen",
+  "license": "MIT",
+  "devDependencies": {
+    "cmake-js": "^7.1.1",
+    "node-addon-api": "^5.0.0"
+  }
+}