common : separate whisper sources (#2846)
Some checks failed
Bindings Tests (Ruby) / ubuntu-22 (push) Waiting to run
CI / ubuntu-22 (linux/amd64) (push) Waiting to run
CI / ubuntu-22 (linux/ppc64le) (push) Waiting to run
CI / ubuntu-22-arm64 (linux/arm64) (push) Waiting to run
CI / ubuntu-22-arm-v7 (linux/arm/v7) (push) Waiting to run
CI / macOS-latest (push) Waiting to run
CI / ubuntu-22-gcc (linux/amd64, Debug) (push) Waiting to run
CI / ubuntu-22-gcc (linux/amd64, Release) (push) Waiting to run
CI / ubuntu-22-gcc (linux/ppc64le, Debug) (push) Waiting to run
CI / ubuntu-22-gcc (linux/ppc64le, Release) (push) Waiting to run
CI / ubuntu-22-gcc-arm64 (linux/arm64, Debug) (push) Waiting to run
CI / ubuntu-22-gcc-arm64 (linux/arm64, Release) (push) Waiting to run
CI / ubuntu-22-gcc-arm-v7 (linux/arm/v7, Debug) (push) Waiting to run
CI / ubuntu-22-gcc-arm-v7 (linux/arm/v7, Release) (push) Waiting to run
CI / ubuntu-22-clang (linux/amd64, Debug) (push) Waiting to run
CI / ubuntu-22-clang (linux/amd64, Release) (push) Waiting to run
CI / ubuntu-22-clang (linux/arm64, Debug) (push) Waiting to run
CI / ubuntu-22-clang (linux/arm64, Release) (push) Waiting to run
CI / ubuntu-22-clang (linux/ppc64le, Debug) (push) Waiting to run
CI / ubuntu-22-clang (linux/ppc64le, Release) (push) Waiting to run
CI / ubuntu-22-gcc-sanitized (linux/amd64, ADDRESS) (push) Waiting to run
CI / ubuntu-22-gcc-sanitized (linux/amd64, THREAD) (push) Waiting to run
CI / ubuntu-22-gcc-sanitized (linux/amd64, UNDEFINED) (push) Waiting to run
CI / ubuntu-22-cmake-sycl (linux/amd64, icx, icpx, ON) (push) Waiting to run
CI / ubuntu-22-cmake-sycl (linux/arm/v7, icx, icpx, ON) (push) Waiting to run
CI / ubuntu-22-cmake-sycl (linux/arm64, icx, icpx, ON) (push) Waiting to run
CI / ubuntu-22-cmake-sycl (linux/ppc64le, icx, icpx, ON) (push) Waiting to run
CI / ubuntu-22-cmake-sycl-fp16 (linux/amd64, icx, icpx, ON) (push) Waiting to run
CI / ubuntu-22-cmake-sycl-fp16 (linux/arm/v7, icx, icpx, ON) (push) Waiting to run
CI / ubuntu-22-cmake-sycl-fp16 (linux/arm64, icx, icpx, ON) (push) Waiting to run
CI / ubuntu-22-cmake-sycl-fp16 (linux/ppc64le, icx, icpx, ON) (push) Waiting to run
CI / windows-msys2 (Release, clang-x86_64, CLANG64) (push) Waiting to run
CI / windows-msys2 (Release, ucrt-x86_64, UCRT64) (push) Waiting to run
CI / windows (Win32, Release, win32-x86, x86, 2.28.5, ON) (push) Waiting to run
CI / windows (x64, Release, win32-x86-64, x64, 2.28.5, ON) (push) Waiting to run
CI / windows-blas (Win32, ON, Release, x86, 2.28.5, ON) (push) Waiting to run
CI / windows-blas (x64, ON, Release, x64, 2.28.5, ON) (push) Waiting to run
CI / windows-cublas (x64, Release, ON, 11.8.0, ON, 2.28.5) (push) Waiting to run
CI / windows-cublas (x64, Release, ON, 12.2.0, ON, 2.28.5) (push) Waiting to run
CI / emscripten (Release) (push) Waiting to run
CI / ios-xcode-build (Release) (push) Waiting to run
CI / android (push) Waiting to run
CI / quantize (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/main.Dockerfile platform:linux/amd64 tag:main]) (push) Waiting to run
Examples Tests / addon_node-ubuntu-22 (16.x) (push) Has been cancelled
Examples Tests / addon_node-ubuntu-22 (18.x) (push) Has been cancelled

* common : separate whisper sources

* examples : add chrono

* examples : add more headers
This commit is contained in:
Georgi Gerganov
2025-02-27 12:50:32 +02:00
committed by GitHub
parent 9f83f67221
commit c64f3e8ada
13 changed files with 228 additions and 276 deletions

View File

@ -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);