/home/pdd/le/whisper.cpp-1.5.0/cmake-build-debug/bin/main
options:
-h, --help [default] show this help message and exit
-t N, --threads N [4 ] number of threads to use during computation
-p N, --processors N [1 ] number of processors to use during computation
-ot N, --offset-t N [0 ] time offset in milliseconds
-on N, --offset-n N [0 ] segment index offset
-d N, --duration N [0 ] duration of audio to process in milliseconds
-mc N, --max-context N [-1 ] maximum number of text context tokens to store
-ml N, --max-len N [0 ] maximum segment length in characters
-sow, --split-on-word [false ] split on word rather than on token
-bo N, --best-of N [5 ] number of best candidates to keep
-bs N, --beam-size N [5 ] beam size for beam search
-wt N, --word-thold N [0.01 ] word timestamp probability threshold
-et N, --entropy-thold N [2.40 ] entropy threshold for decoder fail
-lpt N, --logprob-thold N [-1.00 ] log probability threshold for decoder fail
-debug, --debug-mode [false ] enable debug mode (eg. dump log_mel)
-tr, --translate [false ] translate from source language to english
-di, --diarize [false ] stereo audio diarization
-tdrz, --tinydiarize [false ] enable tinydiarize (requires a tdrz model)
-nf, --no-fallback [false ] do not use temperature fallback while decoding
-otxt, --output-txt [false ] output result in a text file
-ovtt, --output-vtt [false ] output result in a vtt file
-osrt, --output-srt [false ] output result in a srt file
-olrc, --output-lrc [false ] output result in a lrc file
-owts, --output-words [false ] output script for generating karaoke video
-fp, --font-path [/System/Library/Fonts/Supplemental/Courier New Bold.ttf] path to a monospace font for karaoke video
-ocsv, --output-csv [false ] output result in a CSV file
-oj, --output-json [false ] output result in a JSON file
-ojf, --output-json-full [false ] include more information in the JSON file
-of FNAME, --output-file FNAME [ ] output file path (without file extension)
-ps, --print-special [false ] print special tokens
-pc, --print-colors [false ] print colors
-pp, --print-progress [false ] print progress
-nt, --no-timestamps [false ] do not print timestamps
-l LANG, --language LANG [en ] spoken language ('auto' for auto-detect)
-dl, --detect-language [false ] exit after automatically detecting language
--prompt PROMPT [ ] initial prompt
-m FNAME, --model FNAME [models/ggml-base.en.bin] model path
-f FNAME, --file FNAME [ ] input WAV file path
-oved D, --ov-e-device DNAME [CPU ] the OpenVINO device used for encode inference
-ls, --log-score [false ] log best decoder scores of tokens
-ng, --no-gpu [false ] disable GPU
调试设置
项目依赖和CmakeLists.txt
set(TARGET main)
add_executable(${TARGET} main.cpp)
include(DefaultTargetOptions)
target_link_libraries(${TARGET} PRIVATE common whisper ${CMAKE_THREAD_LIBS_INIT})
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;
const int n_segments = whisper_full_n_segments(ctx);
std::string speaker = "";
int64_t t0 = 0;
int64_t t1 = 0;
// 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) {
speaker = estimate_diarization_speaker(pcmf32s, t0, t1);
}
if (params.print_colors) {
for (int j = 0; j < whisper_full_n_tokens(ctx, i); ++j) {
if (params.print_special == false) {
const whisper_token id = whisper_full_get_token_id(ctx, i, j);
if (id >= whisper_token_eot(ctx)) {
continue;
}
}
const char * text = whisper_full_get_token_text(ctx, i, j);
const float p = whisper_full_get_token_p (ctx, i, j);
const int col = std::max(0, std::min((int) k_colors.size() - 1, (int) (std::pow(p, 3)*float(k_colors.size()))));
printf("%s%s%s%s", speaker.c_str(), k_colors[col].c_str(), text, "\033[0m");
}
} else {
const char * text = whisper_full_get_segment_text(ctx, i);
printf("%s%s", speaker.c_str(), text);
}
if (params.tinydiarize) {
if (whisper_full_get_segment_speaker_turn_next(ctx, i)) {
printf("%s", params.tdrz_speaker_turn.c_str());
}
}
// with timestamps or speakers: each segment on new line
if (!params.no_timestamps || params.diarize) {
printf("\n");
}
fflush(stdout);
}
}
3.4.2解析参数
// examples for abort mechanism
// in examples below, 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*/, struct whisper_state * /*state*/, void * user_data) {
bool is_aborted = *(bool*)user_data;
return !is_aborted;
};
wparams.encoder_begin_callback_user_data = &is_aborted;
}
// the callback is called before every computation - if it returns true, the computation is aborted
{
static bool is_aborted = false; // NOTE: this should be atomic to avoid data race
wparams.abort_callback = [](void * user_data) {
bool is_aborted = *(bool*)user_data;
return is_aborted;
};
wparams.abort_callback_user_data = &is_aborted;
}
3.4.3 process whisper_full_parallel
if (whisper_full_parallel(ctx, wparams, pcmf32.data(), pcmf32.size(), params.n_processors) != 0) {
fprintf(stderr, "%s: failed to process audio\n", argv[0]);
return 10;
}
whisper_full_parallel
int whisper_full_parallel(
struct whisper_context * ctx,
struct whisper_full_params params,
const float * samples,
int n_samples,
int n_processors) {
if (n_processors == 1) {
return whisper_full(ctx, params, samples, n_samples);
}
// 略
}
whisper_full
int whisper_full(
struct whisper_context * ctx,
struct whisper_full_params params,
const float * samples,
int n_samples) {
return whisper_full_with_state(ctx, ctx-&g