Skip to content

token: Add interfaces for getting start and end time of specified tok… #3462

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

token: Add interfaces for getting start and end time of specified tok… #3462

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions include/whisper.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -670,6 +670,13 @@ extern "C" {
WHISPER_API float whisper_full_get_token_p (struct whisper_context * ctx, int i_segment, int i_token);
WHISPER_API float whisper_full_get_token_p_from_state(struct whisper_state * state, int i_segment, int i_token);

// Get the start and end time of the specified token
WHISPER_API int64_t whisper_full_get_token_t0(struct whisper_context* ctx, int i_segment, int i_token);
WHISPER_API int64_t whisper_full_get_token_t0_from_state(struct whisper_state* state, struct whisper_token_data* token);

WHISPER_API int64_t whisper_full_get_token_t1(struct whisper_context* ctx, int i_segment, int i_token);
WHISPER_API int64_t whisper_full_get_token_t1_from_state(struct whisper_state* state, struct whisper_token_data* token);

//
// Voice Activity Detection (VAD)
//
Expand Down
39 changes: 39 additions & 0 deletions src/whisper.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8001,6 +8001,45 @@ float whisper_full_get_token_p(struct whisper_context * ctx, int i_segment, int
return ctx->state->result_all[i_segment].tokens[i_token].p;
}

int64_t whisper_full_get_token_t0_from_state(struct whisper_state* state, struct whisper_token_data* token)
{
if (!state->has_vad_segments || state->vad_mapping_table.empty()) {
return token->t0;
}
return map_processed_to_original_time(token->t0, state->vad_mapping_table);
}
int64_t whisper_full_get_token_t1_from_state(struct whisper_state* state, struct whisper_token_data* token)
{
if (!state->has_vad_segments || state->vad_mapping_table.empty()) {
return token->t1;
}

int64_t t1 = token->t1;

int64_t orig_t1 = map_processed_to_original_time(t1, state->vad_mapping_table);

int64_t orig_t0 = whisper_full_get_token_t0_from_state(state, token);

// Ensure minimum duration to prevent zero-length token
const int64_t min_duration = 10; // 10ms minimum
if (orig_t1 - orig_t0 < min_duration) {
orig_t1 = orig_t0 + min_duration;
}
return orig_t1;
}

int64_t whisper_full_get_token_t0(struct whisper_context* ctx, int i_segment, int i_token)
{
whisper_token_data token = whisper_full_get_token_data(ctx, i_segment, i_token);
return whisper_full_get_token_t0_from_state(ctx->state, &token);
}
int64_t whisper_full_get_token_t1(struct whisper_context* ctx, int i_segment, int i_token)
{
whisper_token_data token = whisper_full_get_token_data(ctx, i_segment, i_token);
return whisper_full_get_token_t1_from_state(ctx->state, &token);
}


float whisper_full_get_segment_no_speech_prob(struct whisper_context * ctx, int i_segment) {
return ctx->state->result_all[i_segment].no_speech_prob;
}
Expand Down
Loading