mirror of
https://github.com/ggerganov/whisper.cpp
synced 2026-03-16 11:50:36 +01:00
aa1bc0d1a6
* ruby : Bump version to 1.3.6 * Fix code in example * Add sample code to transcribe from MemoryView * Define GetVADContext macro * Use GetVADContext * Extract parse_full_args function * Use parse_full_args in ruby_whisper_full_parallel * Free samples after use * Check return value of parse_full_args() * Define GetVADParams macro * Add VAD::Context#segments_from_samples * Add tests for VAD::Context#segments_from_samples * Add signature for VAD::Context#segments_from_samples * Add sample code for VAD::Context#segments_from_samples * Add test for Whisper::Context#transcribe with Pathname * Make Whisper::Context#transcribe and Whisper::VAD::Context#detect accept Pathname * Update signature of Whisper::Context#transcribe * Fix variable name * Don't free memory view * Make parse_full_args return struct * Fallback when failed to get MemoryView * Add num of samples when too long * Check members of MemoryView * Fix a typo * Remove unnecessary include * Fix a typo * Fix a typo * Care the case of MemoryView doesn't fit spec * Add TODO comment * Add optimazation option to compiler flags * Use ALLOC_N instead of malloc * Add description to sample code * Rename and change args: parse_full_args -> parse_samples * Free samples when exception raised * Assign type check result to a variable * Define wrapper function of whisper_full * Change signature of parse_samples for rb_ensure * Ensure release MemoryView * Extract fill_samples function * Free samples memory when filling it failed * Free samples memory when transcription failed * Prepare transcription in wrapper funciton * Change function name * Simplify function boundary
52 lines
1.4 KiB
C++
52 lines
1.4 KiB
C++
#include "ruby_whisper.h"
|
|
#include "common-whisper.h"
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
extern ID id_to_path;
|
|
|
|
extern VALUE cVADSegments;
|
|
|
|
extern const rb_data_type_t ruby_whisper_vad_context_type;
|
|
extern const rb_data_type_t ruby_whisper_vad_params_type;
|
|
extern const rb_data_type_t ruby_whisper_vad_segments_type;
|
|
|
|
extern VALUE ruby_whisper_vad_segments_s_init(struct whisper_vad_segments *segments);
|
|
|
|
VALUE
|
|
ruby_whisper_vad_detect(VALUE self, VALUE file_path, VALUE params) {
|
|
ruby_whisper_vad_context *rwvc;
|
|
ruby_whisper_vad_params *rwvp;
|
|
std::string cpp_file_path;
|
|
std::vector<float> pcmf32;
|
|
std::vector<std::vector<float>> pcmf32s;
|
|
whisper_vad_segments *segments;
|
|
|
|
GetVADContext(self, rwvc);
|
|
TypedData_Get_Struct(params, ruby_whisper_vad_params, &ruby_whisper_vad_params_type, rwvp);
|
|
|
|
if (rb_respond_to(file_path, id_to_path)) {
|
|
file_path = rb_funcall(file_path, id_to_path, 0);
|
|
}
|
|
cpp_file_path = StringValueCStr(file_path);
|
|
|
|
if (!read_audio_data(cpp_file_path, pcmf32, pcmf32s, false)) {
|
|
rb_raise(rb_eRuntimeError, "Failed to open '%s' as WAV file\n", cpp_file_path.c_str());
|
|
}
|
|
|
|
segments = whisper_vad_segments_from_samples(rwvc->context, rwvp->params, pcmf32.data(), pcmf32.size());
|
|
if (segments == nullptr) {
|
|
rb_raise(rb_eRuntimeError, "Failed to process audio\n");
|
|
}
|
|
|
|
return ruby_whisper_vad_segments_s_init(segments);
|
|
}
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|