mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2025-06-01 07:25:49 +02:00
* Add VAD models * Extract function to normalize model path from ruby_whisper_initialize() * Define ruby_whisper_vad_params struct * Add VAD-related features to Whisper::Params * Add tests for VAD-related features * Define Whisper::VADParams * Add Whisper::VAD::Params attributes * Add test suite for VAD::Params * Make older test to follow namespace change * Add test for transcription with VAD * Add assertion for test_vad_params * Add signatures for VAD-related methods * Define VAD::Params#== * Add test for VAD::Params#== * Fix Params#vad_params * Add test for Params#vad_params * Fix signature of Params#vad_params * Use macro to define VAD::Params params * Define VAD::Params#initialize * Add tests for VAD::Params#initialize * Add signature for VAD::Params.new * Add documentation on VAD in README * Wrap register_callbask in prepare_transcription for clear meanings * Set whisper_params.vad_params just before transcription * Don't touch NULL * Define ruby_whisper_params_type * Use TypedData_XXX for ruby_whisper_params instead of Data_XXX * Remove unused functions * Define rb_whisper_model_data_type * Use TypedData_XXX for ruby_whisper_model instead of Data_XXX * Define ruby_whisper_segment_type * Use TypedData_XXX for ruby_whisper_segment instead of Data_XXX * Define ruby_whisper_type * Use TypedData_XXX for ruby_whisper instead of Data_XXX * Qualify with const
88 lines
2.5 KiB
C++
88 lines
2.5 KiB
C++
#include <ruby.h>
|
|
#include "ruby_whisper.h"
|
|
#include "common-whisper.h"
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
extern const rb_data_type_t ruby_whisper_type;
|
|
extern const rb_data_type_t ruby_whisper_params_type;
|
|
|
|
extern ID id_to_s;
|
|
extern ID id_call;
|
|
|
|
extern void
|
|
prepare_transcription(ruby_whisper_params * rwp, VALUE * self);
|
|
|
|
/*
|
|
* transcribe a single file
|
|
* can emit to a block results
|
|
*
|
|
* params = Whisper::Params.new
|
|
* params.duration = 60_000
|
|
* whisper.transcribe "path/to/audio.wav", params do |text|
|
|
* puts text
|
|
* end
|
|
*
|
|
* call-seq:
|
|
* transcribe(path_to_audio, params) {|text| ...}
|
|
**/
|
|
VALUE
|
|
ruby_whisper_transcribe(int argc, VALUE *argv, VALUE self) {
|
|
ruby_whisper *rw;
|
|
ruby_whisper_params *rwp;
|
|
VALUE wave_file_path, blk, params;
|
|
|
|
rb_scan_args(argc, argv, "02&", &wave_file_path, ¶ms, &blk);
|
|
TypedData_Get_Struct(self, ruby_whisper, &ruby_whisper_type, rw);
|
|
TypedData_Get_Struct(params, ruby_whisper_params, &ruby_whisper_params_type, rwp);
|
|
|
|
if (!rb_respond_to(wave_file_path, id_to_s)) {
|
|
rb_raise(rb_eRuntimeError, "Expected file path to wave file");
|
|
}
|
|
|
|
std::string fname_inp = StringValueCStr(wave_file_path);
|
|
|
|
std::vector<float> pcmf32; // mono-channel F32 PCM
|
|
std::vector<std::vector<float>> pcmf32s; // stereo-channel F32 PCM
|
|
|
|
if (!read_audio_data(fname_inp, pcmf32, pcmf32s, rwp->diarize)) {
|
|
fprintf(stderr, "error: failed to open '%s' as WAV file\n", fname_inp.c_str());
|
|
return self;
|
|
}
|
|
// Commented out because it is work in progress
|
|
// {
|
|
// static bool is_aborted = false; // NOTE: this should be atomic to avoid data race
|
|
|
|
// rwp->params.encoder_begin_callback = [](struct whisper_context * /*ctx*/, struct whisper_state * /*state*/, void * user_data) {
|
|
// bool is_aborted = *(bool*)user_data;
|
|
// return !is_aborted;
|
|
// };
|
|
// rwp->params.encoder_begin_callback_user_data = &is_aborted;
|
|
// }
|
|
|
|
prepare_transcription(rwp, &self);
|
|
|
|
if (whisper_full_parallel(rw->context, rwp->params, pcmf32.data(), pcmf32.size(), 1) != 0) {
|
|
fprintf(stderr, "failed to process audio\n");
|
|
return self;
|
|
}
|
|
const int n_segments = whisper_full_n_segments(rw->context);
|
|
VALUE output = rb_str_new2("");
|
|
for (int i = 0; i < n_segments; ++i) {
|
|
const char * text = whisper_full_get_segment_text(rw->context, i);
|
|
output = rb_str_concat(output, rb_str_new2(text));
|
|
}
|
|
VALUE idCall = id_call;
|
|
if (blk != Qnil) {
|
|
rb_funcall(blk, idCall, 1, output);
|
|
}
|
|
return self;
|
|
}
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|