mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2025-08-09 01:04:36 +02:00
common : separate whisper sources (#2846)
* common : separate whisper sources * examples : add chrono * examples : add more headers
This commit is contained in:
@ -11,8 +11,6 @@
|
||||
#include <fstream>
|
||||
#include <sstream>
|
||||
|
||||
#define COMMON_SAMPLE_RATE 16000
|
||||
|
||||
//
|
||||
// GPT CLI argument parsing
|
||||
//
|
||||
@ -139,16 +137,6 @@ gpt_vocab::id gpt_sample_top_k_top_p_repeat(
|
||||
// Check if a buffer is a WAV audio file
|
||||
bool is_wav_buffer(const std::string buf);
|
||||
|
||||
// Read WAV audio file and store the PCM data into pcmf32
|
||||
// fname can be a buffer of WAV data instead of a filename
|
||||
// The sample rate of the audio must be equal to COMMON_SAMPLE_RATE
|
||||
// If stereo flag is set and the audio has 2 channels, the pcmf32s will contain 2 channel PCM
|
||||
bool read_audio_data(
|
||||
const std::string & fname,
|
||||
std::vector<float> & pcmf32,
|
||||
std::vector<std::vector<float>> & pcmf32s,
|
||||
bool stereo);
|
||||
|
||||
// Write PCM data into WAV audio file
|
||||
class wav_writer {
|
||||
private:
|
||||
@ -266,23 +254,6 @@ bool vad_simple(
|
||||
// compute similarity between two strings using Levenshtein distance
|
||||
float similarity(const std::string & s0, const std::string & s1);
|
||||
|
||||
//
|
||||
// SAM argument parsing
|
||||
//
|
||||
|
||||
struct sam_params {
|
||||
int32_t seed = -1; // RNG seed
|
||||
int32_t n_threads = std::min(4, (int32_t) std::thread::hardware_concurrency());
|
||||
|
||||
std::string model = "models/sam-vit-b/ggml-model-f16.bin"; // model path
|
||||
std::string fname_inp = "img.jpg";
|
||||
std::string fname_out = "img.out";
|
||||
};
|
||||
|
||||
bool sam_params_parse(int argc, char ** argv, sam_params & params);
|
||||
|
||||
void sam_print_usage(int argc, char ** argv, const sam_params & params);
|
||||
|
||||
//
|
||||
// Terminal utils
|
||||
//
|
||||
@ -330,14 +301,5 @@ const std::vector<std::string> k_colors = {
|
||||
// Other utils
|
||||
//
|
||||
|
||||
// convert timestamp to string, 6000 -> 01:00.000
|
||||
std::string to_timestamp(int64_t t, bool comma = false);
|
||||
|
||||
// given a timestamp get the sample
|
||||
int timestamp_to_sample(int64_t t, int n_samples, int whisper_sample_rate);
|
||||
|
||||
// check if file exists using ifstream
|
||||
bool is_file_exist(const char *fileName);
|
||||
|
||||
// write text to file, and call system("command voice_id file")
|
||||
bool speak_with_file(const std::string & command, const std::string & text, const std::string & path, int voice_id);
|
||||
bool is_file_exist(const char * filename);
|
||||
|
Reference in New Issue
Block a user