Skip to content
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

allow stream prompt #2634

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

allow stream prompt #2634

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
25 changes: 20 additions & 5 deletions examples/stream/stream.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,8 @@ struct whisper_params {
std::string language = "en";
std::string model = "models/ggml-base.en.bin";
std::string fname_out;

std::string initial_prompt;
};

void whisper_print_usage(int argc, char ** argv, const whisper_params & params);
Expand Down Expand Up @@ -72,7 +74,7 @@ static bool whisper_params_parse(int argc, char ** argv, whisper_params & params
else if (arg == "-sa" || arg == "--save-audio") { params.save_audio = true; }
else if (arg == "-ng" || arg == "--no-gpu") { params.use_gpu = false; }
else if (arg == "-fa" || arg == "--flash-attn") { params.flash_attn = true; }

else if ( arg == "--prompt") {params.initial_prompt = argv[++i]; }
else {
fprintf(stderr, "error: unknown argument: %s\n", arg.c_str());
whisper_print_usage(argc, argv, params);
Expand Down Expand Up @@ -109,6 +111,7 @@ void whisper_print_usage(int /*argc*/, char ** argv, const whisper_params & para
fprintf(stderr, " -sa, --save-audio [%-7s] save the recorded audio to a file\n", params.save_audio ? "true" : "false");
fprintf(stderr, " -ng, --no-gpu [%-7s] disable GPU inference\n", params.use_gpu ? "false" : "true");
fprintf(stderr, " -fa, --flash-attn [%-7s] flash attention during inference\n", params.flash_attn ? "true" : "false");
fprintf(stderr, " --prompt PROMPT [%-7s] initial prompt (max n_text_ctx/2 tokens)\n", params.initial_prompt.c_str());
fprintf(stderr, "\n");
}

Expand Down Expand Up @@ -164,7 +167,13 @@ int main(int argc, char ** argv) {
std::vector<float> pcmf32_new(n_samples_30s, 0.0f);

std::vector<whisper_token> prompt_tokens;

prompt_tokens.resize(1024);
int n= whisper_tokenize(ctx, params.initial_prompt.c_str(),prompt_tokens.data(),1024);
if (n < 0) {
fprintf(stderr, "%s: error: failed to tokenize prompt '%s'\n", __func__, params.initial_prompt.c_str());
return 3;
}
prompt_tokens.resize(n);
// print some info about the processing
{
fprintf(stderr, "\n");
Expand Down Expand Up @@ -318,8 +327,8 @@ int main(int argc, char ** argv) {
//wparams.temperature_inc = -1.0f;
wparams.temperature_inc = params.no_fallback ? 0.0f : wparams.temperature_inc;

wparams.prompt_tokens = params.no_context ? nullptr : prompt_tokens.data();
wparams.prompt_n_tokens = params.no_context ? 0 : prompt_tokens.size();
wparams.prompt_tokens = prompt_tokens.data();
wparams.prompt_n_tokens = prompt_tokens.size();

if (whisper_full(ctx, wparams, pcmf32.data(), pcmf32.size()) != 0) {
fprintf(stderr, "%s: failed to process audio\n", argv[0]);
Expand Down Expand Up @@ -397,7 +406,13 @@ int main(int argc, char ** argv) {
// Add tokens of the last full length segment as the prompt
if (!params.no_context) {
prompt_tokens.clear();

prompt_tokens.resize(1024);
int n= whisper_tokenize(ctx, params.initial_prompt.c_str(),prompt_tokens.data(),1024);
if (n < 0) {
fprintf(stderr, "%s: error: failed to tokenize prompt '%s'\n", __func__, params.initial_prompt.c_str());
return 3;
}
prompt_tokens.resize(n);
const int n_segments = whisper_full_n_segments(ctx);
for (int i = 0; i < n_segments; ++i) {
const int token_count = whisper_full_n_tokens(ctx, i);
Expand Down