Win Dictation Dev
82 lines
3.0 KiB
C++
82 lines
3.0 KiB
C++
#include "transcriber.h"
|
|
#include "text_util.h"
|
|
#include <cstdio>
|
|
#include <cstdint>
|
|
#include <fstream>
|
|
#include <vector>
|
|
#include <string>
|
|
#include <cctype>
|
|
|
|
static int g_fail = 0;
|
|
#define CHECK(cond, msg) do { if (!(cond)) { printf(" FAIL: %s\n", msg); ++g_fail; } \
|
|
else printf(" ok: %s\n", msg); } while(0)
|
|
|
|
static bool load_wav(const std::string& path, std::vector<float>& out) {
|
|
std::ifstream f(path, std::ios::binary);
|
|
if (!f) return false;
|
|
char hdr[44];
|
|
f.read(hdr, 44);
|
|
if (std::string(hdr, 4) != "RIFF") return false;
|
|
std::vector<int16_t> pcm((std::istreambuf_iterator<char>(f)), {});
|
|
out.clear(); out.reserve(pcm.size());
|
|
for (int16_t s : pcm) out.push_back(s / 32768.0f);
|
|
return !out.empty();
|
|
}
|
|
|
|
static std::string lower(std::string s) { for (char& c : s) c = (char)tolower((unsigned char)c); return s; }
|
|
|
|
int main(int argc, char** argv) {
|
|
std::string model = (argc > 1) ? argv[1] : "models/ggml-tiny.en.bin";
|
|
std::string wav = (argc > 2) ? argv[2] : "samples/jfk.wav";
|
|
|
|
CHECK(append_transcript(L"", L"hello") == L"hello", "append: empty + a");
|
|
CHECK(append_transcript(L"hello", L"world") == L"hello world", "append: a + b spaced");
|
|
CHECK(append_transcript(L"hello", L"") == L"hello", "append: a + empty");
|
|
|
|
{
|
|
Transcriber t; WhisperConfig bad; bad.model_path = "models\\does-not-exist.bin";
|
|
bool ok = t.preload(bad);
|
|
CHECK(!ok, "bad model path: preload returns false");
|
|
std::vector<float> a(16000, 0.0f);
|
|
std::string r = t.transcribe_sync(a);
|
|
CHECK(r.empty(), "bad model path: transcribe_sync returns empty, no crash");
|
|
}
|
|
|
|
{
|
|
Transcriber t; WhisperConfig cfg; cfg.model_path = model; cfg.n_threads = 4;
|
|
bool ok = t.preload(cfg);
|
|
CHECK(ok, "model loads");
|
|
if (ok) {
|
|
int last = -1, maxp = 0; bool monotonic = true;
|
|
t.set_progress_callback([&](int p) {
|
|
if (p < last) monotonic = false;
|
|
last = p; if (p > maxp) maxp = p;
|
|
});
|
|
|
|
std::vector<float> audio;
|
|
bool loaded = load_wav(wav, audio);
|
|
CHECK(loaded, "wav loads");
|
|
if (loaded) {
|
|
std::string text = lower(t.transcribe_sync(audio));
|
|
CHECK(!text.empty(), "transcription is non-empty");
|
|
CHECK(text.find("country") != std::string::npos, "transcription contains 'country'");
|
|
CHECK(monotonic, "progress is non-decreasing");
|
|
CHECK(maxp >= 95, "progress reaches ~100%");
|
|
}
|
|
}
|
|
}
|
|
|
|
{
|
|
Transcriber t; WhisperConfig cfg; cfg.model_path = model;
|
|
if (t.preload(cfg)) {
|
|
std::vector<float> tiny(100, 0.1f);
|
|
std::string r = t.transcribe_sync(tiny);
|
|
CHECK(true, "short audio did not crash");
|
|
}
|
|
}
|
|
|
|
printf("\n%s (%d failure%s)\n", g_fail ? "TESTS FAILED" : "ALL TESTS PASSED",
|
|
g_fail, g_fail == 1 ? "" : "s");
|
|
return g_fail ? 1 : 0;
|
|
}
|