blob: 77be1e03cae2716de9390087cd2429255a254dbe (
plain)
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
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
|
#pragma once
#include <algorithm>
#include <vector>
namespace Whisper
{
struct AudioBuffer
{
std::vector<float> mono;
std::vector<float> stereo;
void appendMono( const float* rsi, size_t countFloats );
void appendDownmixedStereo( const float* rsi, size_t countFloats );
void appendStereo( const float* rsi, size_t countFloats );
using pfnAppendSamples = void( AudioBuffer::* )( const float* rsi, size_t countFloats );
inline static pfnAppendSamples appendSamplesFunc( bool sourceMono, bool wantStereo )
{
if( sourceMono )
return &AudioBuffer::appendMono;
else if( !wantStereo )
return &AudioBuffer::appendDownmixedStereo;
else
return &AudioBuffer::appendStereo;
}
void clear()
{
mono.clear();
stereo.clear();
}
void swap( AudioBuffer& that )
{
mono.swap( that.mono );
stereo.swap( that.stereo );
}
void resize( size_t len )
{
assert( len <= mono.size() );
mono.resize( len );
if( !stereo.empty() )
stereo.resize( len * 2 );
}
void dropFirst(size_t len)
{
assert(len <= mono.size());
size_t remainder = mono.size() - len;
auto tmp = std::vector<float>(remainder);
memcpy(tmp.data(), mono.data() + len, remainder);
mono = std::move(tmp);
}
void normalize()
{
const auto &min = *std::min_element(mono.begin(), mono.end());
const auto &max = *std::max_element(mono.begin(), mono.end());
for (auto& elm : mono) {
elm -= min;
elm /= (max - min) + 1;
elm *= 255.0;
}
}
};
}
|
