From: Felix <redacted>
Date: Mon, 19 Feb 2024 08:50:15 +0000 (+0100)
Subject: examples : clean up common code (whisper/1871)
X-Git-Tag: upstream/0.0.1642~936
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=390cdf8fdf232a59516cf99b86018ccf686b49d9;p=pkg%2Fggml%2Fsources%2Fggml

examples : clean up common code (whisper/1871)

move some utility functions into common.h
---

diff --git a/examples/common.cpp b/examples/common.cpp
index f71c5912..99efd18d 100644
--- a/examples/common.cpp
+++ b/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();
+}
diff --git a/examples/common.h b/examples/common.h
index 09094a1b..0529a057 100644
--- a/examples/common.h
+++ b/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);
diff --git a/examples/whisper/main.cpp b/examples/whisper/main.cpp
index 9230ab60..8abb27fc 100644
--- a/examples/whisper/main.cpp
+++ b/examples/whisper/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;