ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-12 20:18:08 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

whisper : add "split_on_word" flag when using using "max_len" option (#455)

Browse Source 
* Update whisper.cpp

* fix: trim function

* feat: added flag to split on word

* fix: arguments for main
This commit is contained in:
Matija Pevec
2023-02-05 13:44:23 +01:00
committed by GitHub
parent b2083c5d02
commit d012b5c7e4
3 changed files with 39 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/main/main.cpp
View File

@ -69,6 +69,7 @@ struct whisper_params {
bool speed_up = false;
bool translate = false;
bool diarize = false;
bool split_on_word = false;
bool no_fallback = false;
bool output_txt = false;
bool output_vtt = false;
@ -118,6 +119,7 @@ bool whisper_params_parse(int argc, char ** argv, whisper_params & params) {
else if (arg == "-su" || arg == "--speed-up") { params.speed_up = true; }
else if (arg == "-tr" || arg == "--translate") { params.translate = true; }
else if (arg == "-di" || arg == "--diarize") { params.diarize = true; }
else if (arg == "-sow" || arg == "--split-on-word") { params.split_on_word = true; }
else if (arg == "-nf" || arg == "--no-fallback") { params.no_fallback = true; }
else if (arg == "-otxt" || arg == "--output-txt") { params.output_txt = true; }
else if (arg == "-ovtt" || arg == "--output-vtt") { params.output_vtt = true; }
@ -156,6 +158,7 @@ void whisper_print_usage(int /*argc*/, char ** argv, const whisper_params & para
fprintf(stderr, " -d N, --duration N [%-7d] duration of audio to process in milliseconds\n", params.duration_ms);
fprintf(stderr, " -mc N, --max-context N [%-7d] maximum number of text context tokens to store\n", params.max_context);
fprintf(stderr, " -ml N, --max-len N [%-7d] maximum segment length in characters\n", params.max_len);
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, " -wt N, --word-thold N [%-7.2f] word timestamp probability threshold\n", params.word_thold);
@ -651,6 +654,7 @@ int main(int argc, char ** argv) {
wparams.token_timestamps = params.output_wts || params.max_len > 0;
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.speed_up = params.speed_up;