File: mtmd-audio.h

package info (click to toggle)
llama.cpp 6641%2Bdfsg-1
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 43,640 kB
  • sloc: cpp: 218,020; ansic: 117,624; python: 29,020; lisp: 9,094; sh: 5,776; objc: 1,045; javascript: 828; xml: 259; makefile: 219
file content (47 lines) | stat: -rw-r--r-- 858 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
#pragma once

#include "ggml.h"

#include <cstdint>
#include <vector>
#include <string>

#define WHISPER_ASSERT GGML_ASSERT

#define WHISPER_SAMPLE_RATE 16000
#define WHISPER_N_FFT       400
#define WHISPER_HOP_LENGTH  160
#define WHISPER_CHUNK_SIZE  30

#define COMMON_SAMPLE_RATE 16000

namespace whisper_preprocessor {

struct whisper_mel {
    int n_len;
    int n_len_org;
    int n_mel;

    std::vector<float> data;
};

struct whisper_filters {
    int32_t n_mel;
    int32_t n_fft;

    std::vector<float> data;
};

bool preprocess_audio(
        const float * samples,
        size_t n_samples,
        const whisper_filters & filters,
        std::vector<whisper_mel> & output);

} // namespace whisper_preprocessor

namespace whisper_precalc_filters {

whisper_preprocessor::whisper_filters get_128_bins();

} // namespace whisper_precalc_filters