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.

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

Add additional params to addon.node #2000

Merged
merged 5 commits into from
May 13, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
3 changes: 3 additions & 0 deletions examples/addon.node/__test__/whisper.spec.js
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,9 @@ const whisperParamsMock = {
model: path.join(__dirname, "../../../models/ggml-base.en.bin"),
fname_inp: path.join(__dirname, "../../../samples/jfk.wav"),
use_gpu: true,
no_prints: true,
comma_in_time: false,
translate: true,
no_timestamps: false,
};

Expand Down
21 changes: 17 additions & 4 deletions examples/addon.node/addon.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,9 @@ struct whisper_params {
bool print_colors = false;
bool print_progress = false;
bool no_timestamps = false;
bool no_prints = false;
bool use_gpu = true;
bool comma_in_time = true;

std::string language = "en";
std::string prompt;
Expand Down Expand Up @@ -120,7 +122,14 @@ void whisper_print_segment_callback(struct whisper_context * ctx, struct whisper
}
}

void cb_log_disable(enum ggml_log_level, const char *, void *) {}

int run(whisper_params &params, std::vector<std::vector<std::string>> &result) {

if (params.no_prints) {
whisper_log_set(cb_log_disable, NULL);
}

if (params.fname_inp.empty()) {
fprintf(stderr, "error: no input files specified\n");
return 2;
Expand Down Expand Up @@ -155,14 +164,14 @@ int run(whisper_params &params, std::vector<std::vector<std::string>> &result) {
}

// print system information
{
if (!params.no_prints) {
fprintf(stderr, "\n");
fprintf(stderr, "system_info: n_threads = %d / %d | %s\n",
params.n_threads*params.n_processors, std::thread::hardware_concurrency(), whisper_print_system_info());
}

// print some info about the processing
{
if (!params.no_prints) {
fprintf(stderr, "\n");
if (!whisper_is_multilingual(ctx)) {
if (params.language != "en" || params.translate) {
Expand Down Expand Up @@ -248,8 +257,8 @@ int run(whisper_params &params, std::vector<std::vector<std::string>> &result) {
const int64_t t0 = whisper_full_get_segment_t0(ctx, i);
const int64_t t1 = whisper_full_get_segment_t1(ctx, i);

result[i].emplace_back(to_timestamp(t0, true));
result[i].emplace_back(to_timestamp(t1, true));
result[i].emplace_back(to_timestamp(t0, params.comma_in_time));
result[i].emplace_back(to_timestamp(t1, params.comma_in_time));
result[i].emplace_back(text);
}

Expand Down Expand Up @@ -300,13 +309,17 @@ Napi::Value whisper(const Napi::CallbackInfo& info) {
std::string model = whisper_params.Get("model").As<Napi::String>();
std::string input = whisper_params.Get("fname_inp").As<Napi::String>();
bool use_gpu = whisper_params.Get("use_gpu").As<Napi::Boolean>();
bool no_prints = whisper_params.Get("no_prints").As<Napi::Boolean>();
bool no_timestamps = whisper_params.Get("no_timestamps").As<Napi::Boolean>();
bool comma_in_time = whisper_params.Get("comma_in_time").As<Napi::Boolean>();

params.language = language;
params.model = model;
params.fname_inp.emplace_back(input);
params.use_gpu = use_gpu;
params.no_prints = no_prints;
params.no_timestamps = no_timestamps;
params.comma_in_time = comma_in_time;

Napi::Function callback = info[1].As<Napi::Function>();
Worker* worker = new Worker(callback, params);
Expand Down
8 changes: 6 additions & 2 deletions examples/addon.node/index.js
Original file line number Diff line number Diff line change
Expand Up @@ -10,8 +10,11 @@ const whisperAsync = promisify(whisper);
const whisperParams = {
language: "en",
model: path.join(__dirname, "../../models/ggml-base.en.bin"),
fname_inp: "../../samples/jfk.wav",
fname_inp: path.join(__dirname, "../../samples/jfk.wav"),
use_gpu: true,
no_prints: true,
comma_in_time: false,
translate: true,
no_timestamps: false,
};

Expand All @@ -34,5 +37,6 @@ for (const key in params) {
console.log("whisperParams =", whisperParams);

whisperAsync(whisperParams).then((result) => {
console.log(`Result from whisper: ${result}`);
console.log();
console.log(result);
});