ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2024-12-19 04:37:51 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

whisper : add initial_prompt param (#645)

Browse Source
This commit is contained in:
Jhen-Jie Hong 2023-03-30 04:23:23 +08:00 committed by GitHub
parent aac1710afb
commit eefed45e37
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 13 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
examples/addon.node/addon.cpp
View File

@ -160,22 +160,6 @@ int run(whisper_params &params, std::vector<std::vector<std::string>> &result) {
return 3;
}
// initial prompt
std::vector<whisper_token> prompt_tokens;
if (!params.prompt.empty()) {
prompt_tokens.resize(1024);
prompt_tokens.resize(whisper_tokenize(ctx, params.prompt.c_str(), prompt_tokens.data(), prompt_tokens.size()));
fprintf(stderr, "\n");
fprintf(stderr, "initial prompt: '%s'\n", params.prompt.c_str());
fprintf(stderr, "initial tokens: [ ");
for (int i = 0; i < (int) prompt_tokens.size(); ++i) {
fprintf(stderr, "%d ", prompt_tokens[i]);
}
fprintf(stderr, "]\n");
}
for (int f = 0; f < (int) params.fname_inp.size(); ++f) {
const auto fname_inp = params.fname_inp[f];
const auto fname_out = f < (int)params.fname_out.size() && !params.fname_out[f].empty() ? params.fname_out[f] : params.fname_inp[f];
@ -243,8 +227,7 @@ int run(whisper_params &params, std::vector<std::vector<std::string>> &result) {
wparams.greedy.best_of = params.best_of;
wparams.beam_search.beam_size = params.beam_size;
wparams.prompt_tokens = prompt_tokens.empty() ? nullptr : prompt_tokens.data();
wparams.prompt_n_tokens = prompt_tokens.empty() ? 0 : prompt_tokens.size();
wparams.initial_prompt = params.prompt.c_str();
whisper_print_user_data user_data = { &params, &pcmf32s };

19
examples/main/main.cpp
View File

@ -639,22 +639,6 @@ int main(int argc, char ** argv) {
return 3;
}
// initial prompt
std::vector<whisper_token> prompt_tokens;
if (!params.prompt.empty()) {
prompt_tokens.resize(1024);
prompt_tokens.resize(whisper_tokenize(ctx, params.prompt.c_str(), prompt_tokens.data(), prompt_tokens.size()));
fprintf(stderr, "\n");
fprintf(stderr, "initial prompt: '%s'\n", params.prompt.c_str());
fprintf(stderr, "initial tokens: [ ");
for (int i = 0; i < (int) prompt_tokens.size(); ++i) {
fprintf(stderr, "%d ", prompt_tokens[i]);
}
fprintf(stderr, "]\n");
}
for (int f = 0; f < (int) params.fname_inp.size(); ++f) {
const auto fname_inp = params.fname_inp[f];
const auto fname_out = f < (int) params.fname_out.size() && !params.fname_out[f].empty() ? params.fname_out[f] : params.fname_inp[f];
@ -718,8 +702,7 @@ int main(int argc, char ** argv) {
wparams.speed_up = params.speed_up;
wparams.prompt_tokens = prompt_tokens.empty() ? nullptr : prompt_tokens.data();
wparams.prompt_n_tokens = prompt_tokens.empty() ? 0 : prompt_tokens.size();
wparams.initial_prompt = params.prompt.c_str();
wparams.greedy.best_of = params.best_of;
wparams.beam_search.beam_size = params.beam_size;

10
whisper.cpp
View File

@ -3121,6 +3121,7 @@ struct whisper_full_params whisper_full_default_params(enum whisper_sampling_str
/*.speed_up =*/ false,
/*.audio_ctx =*/ 0,
/*.initial_prompt =*/ nullptr,
/*.prompt_tokens =*/ nullptr,
/*.prompt_n_tokens =*/ 0,
@ -3793,6 +3794,15 @@ int whisper_full_with_state(
prompt_past.clear();
}
// initial prompt
if (!params.prompt_tokens && params.initial_prompt) {
std::vector<whisper_token> prompt_tokens;
prompt_tokens.resize(1024);
prompt_tokens.resize(whisper_tokenize(ctx, params.initial_prompt, prompt_tokens.data(), prompt_tokens.size()));
params.prompt_tokens = prompt_tokens.data();
params.prompt_n_tokens = prompt_tokens.size();
}
// prepend the prompt tokens to the prompt_past
if (params.prompt_tokens && params.prompt_n_tokens > 0) {
// parse tokens from the pointer

1
whisper.h
View File

@ -356,6 +356,7 @@ extern "C" {
// tokens to provide to the whisper decoder as initial prompt
// these are prepended to any existing text context from a previous call
const char * initial_prompt;
const whisper_token * prompt_tokens;
int prompt_n_tokens;