haraldwolff
/
whisper.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

examples : added audio_ctx argument to main and server (#1857) 

* added audio_ctx argument to main and server examples

* Better default value

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* better default value (again)

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
pull/1261/merge
dscripka 2024-02-12 02:19:07 -05:00 committed by GitHub
parent 163e74b6c3
commit a6fb6ab597
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
examples/main/main.cpp
View File

@ -64,6 +64,7 @@ struct whisper_params {
int32_t max_len = 0;
int32_t best_of = whisper_full_default_params(WHISPER_SAMPLING_GREEDY).greedy.best_of;
int32_t beam_size = whisper_full_default_params(WHISPER_SAMPLING_BEAM_SEARCH).beam_search.beam_size;
int32_t audio_ctx = 0;
float word_thold = 0.01f;
float entropy_thold = 2.40f;
@ -136,6 +137,7 @@ bool whisper_params_parse(int argc, char ** argv, whisper_params & params) {
else if (arg == "-ml" || arg == "--max-len") { params.max_len = std::stoi(argv[++i]); }
else if (arg == "-bo" || arg == "--best-of") { params.best_of = std::stoi(argv[++i]); }
else if (arg == "-bs" || arg == "--beam-size") { params.beam_size = std::stoi(argv[++i]); }
else if (arg == "-ac" || arg == "--audio-context") { params.audio_ctx = std::stoi(argv[++i]); }
else if (arg == "-wt" || arg == "--word-thold") { params.word_thold = std::stof(argv[++i]); }
else if (arg == "-et" || arg == "--entropy-thold") { params.entropy_thold = std::stof(argv[++i]); }
else if (arg == "-lpt" || arg == "--logprob-thold") { params.logprob_thold = std::stof(argv[++i]); }
@ -195,6 +197,7 @@ void whisper_print_usage(int /*argc*/, char ** argv, const whisper_params & para
fprintf(stderr, " -sow, --split-on-word [%-7s] split on word rather than on token\n", params.split_on_word ? "true" : "false");
fprintf(stderr, " -bo N, --best-of N [%-7d] number of best candidates to keep\n", params.best_of);
fprintf(stderr, " -bs N, --beam-size N [%-7d] beam size for beam search\n", params.beam_size);
fprintf(stderr, " -ac N, --audio-ctx N [%-7d] audio context size (0 - all)\n", params.audio_ctx);
fprintf(stderr, " -wt N, --word-thold N [%-7.2f] word timestamp probability threshold\n", params.word_thold);
fprintf(stderr, " -et N, --entropy-thold N [%-7.2f] entropy threshold for decoder fail\n", params.entropy_thold);
fprintf(stderr, " -lpt N, --logprob-thold N [%-7.2f] log probability threshold for decoder fail\n", params.logprob_thold);
@ -967,6 +970,7 @@ int main(int argc, char ** argv) {
wparams.thold_pt = params.word_thold;
wparams.max_len = params.output_wts && params.max_len == 0 ? 60 : params.max_len;
wparams.split_on_word = params.split_on_word;
wparams.audio_ctx = params.audio_ctx;
wparams.speed_up = params.speed_up;
wparams.debug_mode = params.debug_mode;

8
examples/server/server.cpp
View File

@ -60,6 +60,7 @@ struct whisper_params {
int32_t max_len = 0;
int32_t best_of = 2;
int32_t beam_size = -1;
int32_t audio_ctx = 0;
float word_thold = 0.01f;
float entropy_thold = 2.40f;
@ -138,6 +139,7 @@ void whisper_print_usage(int /*argc*/, char ** argv, const whisper_params & para
fprintf(stderr, " -sow, --split-on-word [%-7s] split on word rather than on token\n", params.split_on_word ? "true" : "false");
fprintf(stderr, " -bo N, --best-of N [%-7d] number of best candidates to keep\n", params.best_of);
fprintf(stderr, " -bs N, --beam-size N [%-7d] beam size for beam search\n", params.beam_size);
fprintf(stderr, " -ac N, --audio-ctx N [%-7d] audio context size (0 - all)\n", params.audio_ctx);
fprintf(stderr, " -wt N, --word-thold N [%-7.2f] word timestamp probability threshold\n", params.word_thold);
fprintf(stderr, " -et N, --entropy-thold N [%-7.2f] entropy threshold for decoder fail\n", params.entropy_thold);
fprintf(stderr, " -lpt N, --logprob-thold N [%-7.2f] log probability threshold for decoder fail\n", params.logprob_thold);
@ -183,6 +185,7 @@ bool whisper_params_parse(int argc, char ** argv, whisper_params & params, serve
else if (arg == "-ml" || arg == "--max-len") { params.max_len = std::stoi(argv[++i]); }
else if (arg == "-bo" || arg == "--best-of") { params.best_of = std::stoi(argv[++i]); }
else if (arg == "-bs" || arg == "--beam-size") { params.beam_size = std::stoi(argv[++i]); }
else if (arg == "-ac" || arg == "--audio-context") { params.audio_ctx = std::stoi(argv[++i]); }
else if (arg == "-wt" || arg == "--word-thold") { params.word_thold = std::stof(argv[++i]); }
else if (arg == "-et" || arg == "--entropy-thold") { params.entropy_thold = std::stof(argv[++i]); }
else if (arg == "-lpt" || arg == "--logprob-thold") { params.logprob_thold = std::stof(argv[++i]); }
@ -433,6 +436,10 @@ void get_req_parameters(const Request & req, whisper_params & params)
{
params.beam_size = std::stoi(req.get_file_value("beam_size").content);
}
if (req.has_file("audio_ctx"))
{
params.audio_ctx = std::stof(req.get_file_value("audio_ctx").content);
}
if (req.has_file("word_thold"))
{
params.word_thold = std::stof(req.get_file_value("word_thold").content);
@ -741,6 +748,7 @@ int main(int argc, char ** argv) {
wparams.thold_pt = params.word_thold;
wparams.max_len = params.max_len == 0 ? 60 : params.max_len;
wparams.split_on_word = params.split_on_word;
wparams.audio_ctx = params.audio_ctx;
wparams.speed_up = params.speed_up;
wparams.debug_mode = params.debug_mode;