examples : clean up common code (#1871)

move some utility functions into common.h

examples/CMakeLists.txt

@@ -54,6 +54,9 @@ if (WHISPER_SDL2)
     set_target_properties(${TARGET} PROPERTIES POSITION_INDEPENDENT_CODE ON)
 endif()
 
+# add json lib
+add_library(json_cpp INTERFACE json.hpp)
+
 # examples
 
 include_directories(${CMAKE_CURRENT_SOURCE_DIR})

examples/addon.node/addon.cpp

@@ -52,27 +52,6 @@ struct whisper_print_user_data {
     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, struct whisper_state * state, 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;
@@ -104,8 +83,8 @@ void whisper_print_segment_callback(struct whisper_context * ctx, struct whisper
         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);
+            const int64_t is0 = timestamp_to_sample(t0, n_samples, WHISPER_SAMPLE_RATE);
+            const int64_t is1 = timestamp_to_sample(t1, n_samples, WHISPER_SAMPLE_RATE);
 
             double energy0 = 0.0f;
             double energy1 = 0.0f;

examples/command/command.cpp

@@ -22,11 +22,6 @@
 #include <vector>
 #include <map>
 
-bool file_exists(const std::string & fname) {
-    std::ifstream f(fname.c_str());
-    return f.good();
-}
-
 // command-line parameters
 struct whisper_params {
     int32_t n_threads  = std::min(4, (int32_t) std::thread::hardware_concurrency());
@@ -736,7 +731,7 @@ int main(int argc, char ** argv) {
 
     if (!params.grammar.empty()) {
         auto & grammar = params.grammar_parsed;
-        if (file_exists(params.grammar.c_str())) {
+        if (is_file_exist(params.grammar.c_str())) {
             // read grammar from file
             std::ifstream ifs(params.grammar.c_str());
             const std::string txt = std::string((std::istreambuf_iterator<char>(ifs)), std::istreambuf_iterator<char>());

examples/common.cpp

@@ -836,3 +836,30 @@ void sam_print_usage(int /*argc*/, char ** argv, const sam_params & params) {
     fprintf(stderr, "                        output file (default: %s)\n", params.fname_out.c_str());
     fprintf(stderr, "\n");
 }
+
+//  500 -> 00:05.000
+// 6000 -> 01:00.000
+std::string to_timestamp(int64_t t, bool comma) {
+    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, int whisper_sample_rate) {
+    return std::max(0, std::min((int) n_samples - 1, (int) ((t*whisper_sample_rate)/100)));
+}
+
+bool is_file_exist(const char *fileName)
+{
+    std::ifstream infile(fileName);
+    return infile.good();
+}

examples/common.h

@@ -281,3 +281,28 @@ struct sam_params {
 bool sam_params_parse(int argc, char ** argv, sam_params & params);
 
 void sam_print_usage(int argc, char ** argv, const sam_params & params);
+
+//
+// Terminal utils
+//
+
+
+// Terminal color map. 10 colors grouped in ranges [0.0, 0.1, ..., 0.9]
+// Lowest is red, middle is yellow, highest is green.
+const std::vector<std::string> k_colors = {
+    "\033[38;5;196m", "\033[38;5;202m", "\033[38;5;208m", "\033[38;5;214m", "\033[38;5;220m",
+    "\033[38;5;226m", "\033[38;5;190m", "\033[38;5;154m", "\033[38;5;118m", "\033[38;5;82m",
+};
+
+//
+// Other utils
+//
+
+// convert timestamp to string, 6000 -> 01:00.000
+std::string to_timestamp(int64_t t, bool comma = false);
+
+// given a timestamp get the sample
+int timestamp_to_sample(int64_t t, int n_samples, int whisper_sample_rate);
+
+// check if file exists using ifstream
+bool is_file_exist(const char *fileName);

examples/lsp/CMakeLists.txt

@@ -5,5 +5,5 @@ if (WHISPER_SDL2)
 
     include(DefaultTargetOptions)
 
-    target_link_libraries(${TARGET} PRIVATE common common-sdl whisper ${CMAKE_THREAD_LIBS_INIT})
+    target_link_libraries(${TARGET} PRIVATE common json_cpp common-sdl whisper ${CMAKE_THREAD_LIBS_INIT})
 endif ()

examples/main/main.cpp

@@ -14,34 +14,6 @@
 #pragma warning(disable: 4244 4267) // possible loss of data
 #endif
 
-// Terminal color map. 10 colors grouped in ranges [0.0, 0.1, ..., 0.9]
-// Lowest is red, middle is yellow, highest is green.
-const std::vector<std::string> k_colors = {
-    "\033[38;5;196m", "\033[38;5;202m", "\033[38;5;208m", "\033[38;5;214m", "\033[38;5;220m",
-    "\033[38;5;226m", "\033[38;5;190m", "\033[38;5;154m", "\033[38;5;118m", "\033[38;5;82m",
-};
-
-//  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)));
-}
-
 // helper function to replace substrings
 void replace_all(std::string & s, const std::string & search, const std::string & replace) {
     for (size_t pos = 0; ; pos += replace.length()) {
@@ -244,8 +216,8 @@ std::string estimate_diarization_speaker(std::vector<std::vector<float>> pcmf32s
     std::string speaker = "";
     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);
+    const int64_t is0 = timestamp_to_sample(t0, n_samples, WHISPER_SAMPLE_RATE);
+    const int64_t is1 = timestamp_to_sample(t1, n_samples, WHISPER_SAMPLE_RATE);
 
     double energy0 = 0.0f;
     double energy1 = 0.0f;

examples/server/CMakeLists.txt

@@ -1,9 +1,9 @@
 set(TARGET server)
-add_executable(${TARGET} server.cpp httplib.h json.hpp)
+add_executable(${TARGET} server.cpp httplib.h)
 
 include(DefaultTargetOptions)
 
-target_link_libraries(${TARGET} PRIVATE common whisper ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE common json_cpp whisper ${CMAKE_THREAD_LIBS_INIT})
 
 if (WIN32)
     target_link_libraries(${TARGET} PRIVATE ws2_32)

examples/server/server.cpp

@@ -22,13 +22,6 @@ using json = nlohmann::ordered_json;
 
 namespace {
 
-// Terminal color map. 10 colors grouped in ranges [0.0, 0.1, ..., 0.9]
-// Lowest is red, middle is yellow, highest is green.
-const std::vector<std::string> k_colors = {
-    "\033[38;5;196m", "\033[38;5;202m", "\033[38;5;208m", "\033[38;5;214m", "\033[38;5;220m",
-    "\033[38;5;226m", "\033[38;5;190m", "\033[38;5;154m", "\033[38;5;118m", "\033[38;5;82m",
-};
-
 // output formats
 const std::string json_format   = "json";
 const std::string text_format   = "text";
@@ -96,33 +89,6 @@ struct whisper_params {
     std::string openvino_encode_device = "CPU";
 };
 
-//  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)));
-}
-
-bool is_file_exist(const char *fileName)
-{
-    std::ifstream infile(fileName);
-    return infile.good();
-}
-
 void whisper_print_usage(int /*argc*/, char ** argv, const whisper_params & params, const server_params& sparams) {
     fprintf(stderr, "\n");
     fprintf(stderr, "usage: %s [options] \n", argv[0]);
@@ -274,8 +240,8 @@ std::string estimate_diarization_speaker(std::vector<std::vector<float>> pcmf32s
     std::string speaker = "";
     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);
+    const int64_t is0 = timestamp_to_sample(t0, n_samples, WHISPER_SAMPLE_RATE);
+    const int64_t is1 = timestamp_to_sample(t1, n_samples, WHISPER_SAMPLE_RATE);
 
     double energy0 = 0.0f;
     double energy1 = 0.0f;
@@ -629,7 +595,7 @@ int main(int argc, char ** argv) {
         return false;
     });
 
-    svr.Options(sparams.request_path + "/inference", [&](const Request &req, Response &res){
+    svr.Options(sparams.request_path + "/inference", [&](const Request &, Response &){
     });
 
     svr.Post(sparams.request_path + "/inference", [&](const Request &req, Response &res){

examples/stream/stream.cpp

@@ -14,20 +14,6 @@
 #include <fstream>
 
 
-//  500 -> 00:05.000
-// 6000 -> 01:00.000
-std::string to_timestamp(int64_t t) {
-    int64_t sec = t/100;
-    int64_t msec = t - sec*100;
-    int64_t min = sec/60;
-    sec = sec - min*60;
-
-    char buf[32];
-    snprintf(buf, sizeof(buf), "%02d:%02d.%03d", (int) min, (int) sec, (int) msec);
-
-    return std::string(buf);
-}
-
 // command-line parameters
 struct whisper_params {
     int32_t n_threads  = std::min(4, (int32_t) std::thread::hardware_concurrency());
@@ -372,7 +358,7 @@ int main(int argc, char ** argv) {
                         const int64_t t0 = whisper_full_get_segment_t0(ctx, i);
                         const int64_t t1 = whisper_full_get_segment_t1(ctx, i);
 
-                        std::string output = "[" + to_timestamp(t0) + " --> " + to_timestamp(t1) + "]  " + text;
+                        std::string output = "[" + to_timestamp(t0, false) + " --> " + to_timestamp(t1, false) + "]  " + text;
 
                         if (whisper_full_get_segment_speaker_turn_next(ctx, i)) {
                             output += " [SPEAKER_TURN]";

examples/talk.wasm/emscripten.cpp

@@ -29,18 +29,6 @@ std::string g_status_forced = "";
 
 std::vector<float> g_pcmf32;
 
-std::string to_timestamp(int64_t t) {
-    int64_t sec = t/100;
-    int64_t msec = t - sec*100;
-    int64_t min = sec/60;
-    sec = sec - min*60;
-
-    char buf[32];
-    snprintf(buf, sizeof(buf), "%02d:%02d.%03d", (int) min, (int) sec, (int) msec);
-
-    return std::string(buf);
-}
-
 void talk_set_status(const std::string & status) {
     std::lock_guard<std::mutex> lock(g_mutex);
     g_status = status;