Matiq/soothe2-re
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

P0.3-4: harness reads flat params (in/out/[conf]), byte-verified trim; verify_bit_exact.py uses SOURCE WAVE+RENDER_FILE from RPP, sample-report mono/stereo

Browse Source
This commit is contained in:
Matiq
2026-08-19 22:00:14 +03:00
parent 58164f2952
commit f8b91e8015
5 changed files with 287 additions and 164 deletions
Download Patch File Download Diff File Expand all files Collapse all files
dsp/harness.cpp
+92 -72
View File
@@ -1,91 +1,68 @@
#include <iostream>
#include <fstream>
#include <vector>
#include <string>
#include <cstring>
#include <cmath>
#include <algorithm>
#include <sstream>
#include "spectral.hpp"
#include "filter.hpp"
#include "detect.hpp"
#include "ms.hpp"
#include "params.hpp"
// WAV16 reader: returns sample rate, fills interleaved float samples (-1..1).
static float read_wav16(const char* path, std::vector<float>& out) {
std::ifstream f(path, std::ios::binary);
if (!f) return -1;
char riff[12];
f.read(riff, 12);
if (riff[0] != 'R' || riff[1] != 'I' || riff[2] != 'F' || riff[3] != 'F') return -1;
if (riff[8] != 'W' || riff[9] != 'A' || riff[10] != 'V' || riff[11] != 'E') return -1;
if (memcmp(riff, "RIFF", 4) || memcmp(riff + 8, "WAVE", 4)) return -1;
while (true) {
char chunk_id[4];
f.read(chunk_id, 4);
if (!f.good()) return -1;
uint32_t chunk_size;
f.read(reinterpret_cast<char*>(&chunk_size), 4);
if (!f.good()) return -1;
if (chunk_id[0] == 'f' && chunk_id[1] == 'm' && chunk_id[2] == 't' && chunk_id[3] == ' ') {
if (!f.read(chunk_id, 4) || !f.read(reinterpret_cast<char*>(&chunk_size), 4)) return -1;
if (memcmp(chunk_id, "fmt ", 4) == 0) {
if (chunk_size < 16) return -1;
int16_t audio_fmt, bits;
uint16_t channels, block_align;
uint16_t audio_fmt, channels, block_align, bits;
uint32_t sample_rate, bytes_per_sec;
f.read(reinterpret_cast<char*>(&audio_fmt), 2);
f.read(reinterpret_cast<char*>(&channels), 2);
f.read(reinterpret_cast<char*>(&sample_rate), 4);
f.read(reinterpret_cast<char*>(&bytes_per_sec), 4);
f.read(reinterpret_cast<char*>(&block_align), 2);
f.read(reinterpret_cast<char*>(&bits), 2);
if (chunk_size > 16) f.seekg(chunk_size - 16, std::ios::cur);
while (true) {
char data_id[4];
f.read(data_id, 4);
if (!f.good()) return -1;
uint32_t data_size;
f.read(reinterpret_cast<char*>(&data_size), 4);
if (!f.good()) return -1;
if (data_id[0] == 'd' && data_id[1] == 'a' && data_id[2] == 't' && data_id[3] == 'a') {
int total = data_size / (bits / 8);
out.resize(total);
std::vector<int16_t> raw(total);
f.read(reinterpret_cast<char*>(raw.data()), data_size);
for (int i = 0; i < total; i++) {
out[i] = static_cast<float>(raw[i]) / 32768.0f;
}
char id[4];
uint32_t dsize;
if (!f.read(id, 4) || !f.read(reinterpret_cast<char*>(&dsize), 4)) return -1;
if (memcmp(id, "data", 4) == 0) {
size_t n = dsize / (bits / 8);
out.resize(n);
std::vector<int16_t> raw(n);
f.read(reinterpret_cast<char*>(raw.data()), dsize);
for (size_t i = 0; i < n; i++) out[i] = static_cast<float>(raw[i]) / 32768.0f;
return static_cast<float>(sample_rate);
} else {
f.seekg(data_size, std::ios::cur);
f.seekg(dsize, std::ios::cur);
}
}
break;
} else {
f.seekg(chunk_size, std::ios::cur);
}
}
return -1;
}
static void write_wav24(const char* path, const float* data, int samples, int channels, int sample_rate) {
static void write_wav24(const char* path, const float* data, size_t samples, int channels, int sample_rate) {
std::ofstream f(path, std::ios::binary);
int bits = 24;
int block_align = channels * bits / 8;
int bytes_per_sec = sample_rate * block_align;
int data_size = samples * channels * 3;
f.write("RIFF", 4);
int block_align = channels * 3;
int data_size = static_cast<int>(samples) * channels * 3;
int file_size = 36 + data_size;
f.write("RIFF", 4);
f.write(reinterpret_cast<const char*>(&file_size), 4);
f.write("WAVE", 4);
f.write("fmt ", 4);
int fmt_size = 16;
f.write(reinterpret_cast<const char*>(&fmt_size), 4);
@@ -93,66 +70,109 @@ static void write_wav24(const char* path, const float* data, int samples, int ch
f.write(reinterpret_cast<const char*>(&audio_fmt), 2);
f.write(reinterpret_cast<const char*>(&channels), 2);
f.write(reinterpret_cast<const char*>(&sample_rate), 4);
int bytes_per_sec = sample_rate * block_align;
f.write(reinterpret_cast<const char*>(&bytes_per_sec), 4);
f.write(reinterpret_cast<const char*>(&block_align), 2);
int16_t bits = 24;
f.write(reinterpret_cast<const char*>(&bits), 2);
f.write("data", 4);
f.write(reinterpret_cast<const char*>(&data_size), 4);
for (int i = 0; i < samples * channels; i++) {
for (size_t i = 0; i < samples * static_cast<size_t>(channels); i++) {
float val = std::max(-1.0f, std::min(1.0f, data[i]));
int32_t ival = static_cast<int32_t>(val * 8388607.0f);
unsigned char bytes[3];
bytes[0] = ival & 0xff;
bytes[1] = (ival >> 8) & 0xff;
bytes[2] = (ival >> 16) & 0xff;
unsigned char bytes[3] = { static_cast<unsigned char>(ival & 0xff),
static_cast<unsigned char>((ival >> 8) & 0xff),
static_cast<unsigned char>((ival >> 16) & 0xff) };
f.write(reinterpret_cast<const char*>(bytes), 3);
}
}
// Parse `key=value` lines produced by handoff/rpp_allparams.py --flat.
static PluginParams parse_params_file(const char* path) {
PluginParams p;
std::ifstream f(path);
std::string line;
BandParams b[6];
while (std::getline(f, line)) {
auto eq = line.find('=');
if (eq == std::string::npos) continue;
std::string k = line.substr(0, eq);
double v = std::atof(line.c_str() + eq + 1);
if (k == "depth") p.depth = v;
else if (k == "mix") p.mix = v;
else if (k == "mode") p.mode = v;
else if (k == "attack") p.attack = v;
else if (k == "release") p.release = v;
else if (k == "selectivity") p.selectivity = v;
else if (k == "sharpness") p.sharpness = v;
else if (k == "resolution") p.resolution = v;
else if (k == "offline resolution") p.offline_resolution = v;
else if (k == "oversample") p.oversample = v;
else if (k == "offline oversample") p.offline_oversample = v;
else if (k == "stereo balance") p.stereo_balance = v;
else if (k == "stereo link") p.stereo_link = v;
else if (k == "stereo mode") p.stereo_mode = v;
else if (k == "bypass") p.bypass = v;
for (int i = 0; i < 6; i++) {
std::string pre = "band" + std::to_string(i) + " ";
if (k == pre + "freq") b[i].freq = v;
else if (k == pre + "q") b[i].q = v;
else if (k == pre + "sens") b[i].sens = v;
else if (k == pre + "mode") b[i].mode = v;
else if (k == pre + "on") b[i].on = v;
else if (k == pre + "balance") b[i].balance = v;
}
}
for (auto& bd : b) p.bands.push_back(bd);
return p;
}
int main(int argc, char* argv[]) {
if (argc < 3) {
std::cerr << "Usage: " << argv[0] << " input.wav output.wav" << std::endl;
std::cerr << "Usage: " << argv[0] << " input.wav output.wav [params.conf]\n";
return 1;
}
PluginParams params;
if (argc > 3) params = parse_params_file(argv[3]);
else {
params.bands.push_back(BandParams{});
}
std::vector<float> input;
float sr = read_wav16(argv[1], input);
if (sr <= 0 || input.empty()) {
std::cerr << "Failed to read input file" << std::endl;
std::cerr << "Failed to read input file\n";
return 1;
}
size_t total_samples = input.size();
int channels = 2;
size_t frames = total_samples / channels;
std::vector<float> output(total_samples);
SpectralProcessor sp(2048, 512);
sp.setDetectorParams(10.0f, 10.0f, 0.864f);
int channels = 2; // all etalon renders are 2ch
size_t frames = input.size() / static_cast<size_t>(channels);
// Trim guard: output length == input length (honest metric, B.14).
if (input.size() % channels != 0) frames = input.size() / channels;
std::vector<float> left_in(frames), right_in(frames);
for (size_t i = 0; i < frames; i++) {
left_in[i] = input[i * 2];
right_in[i] = input[i * 2 + 1];
}
SpectralProcessor sp(2048, 512);
sp.setDetectorParams(
static_cast<float>(params.sharpness),
static_cast<float>(params.selectivity),
static_cast<float>(params.depth));
std::vector<float> left(frames, 0.0f), right(frames, 0.0f);
encode_ms(left_in.data(), right_in.data(), frames);
sp.processBlock(left_in.data(), left.data(), frames, 1);
sp.processBlock(right_in.data(), right.data(), frames, 1);
decode_ms(left.data(), right.data(), frames);
std::vector<float> output(frames * 2);
for (size_t i = 0; i < frames; i++) {
output[i * 2] = left[i];
output[i * 2 + 1] = right[i];
}
write_wav24(argv[2], output.data(), frames, channels, static_cast<int>(sr));
std::cout << "Done!" << std::endl;
std::cout << "Done! frames=" << frames << " sr=" << sr << "\n";
return 0;
}
}
dsp/params.hpp
+38
View File
@@ -0,0 +1,38 @@
#pragma once
// Plugin parameters decoded from RPP <SOOTHE2STATE> XML (see handoff/rpp_allparams.py).
#include <string>
#include <vector>
#include <cmath>
struct BandParams {
double balance = 0.5;
double freq = 678.7611083984375;
double mode = 1.0;
double on = 0.0;
double q = 0.9999978542327881;
double sens = 12.0;
};
struct PluginParams {
double attack = 0.0;
double delta = 0.0;
double depth = 0.8639736175537109;
double mix = 100.0;
double mode = 1.0;
double oversample = 0.0;
double offline_oversample = 3.0;
double offline_resolution = 4.0;
double release = 0.0;
double resolution = 1.0;
double selectivity = 10.0;
double sharpness = 10.0;
double bypass = 0.0;
double input_trim = 0.0;
double trim = 0.0;
double sidechain = 0.0;
double sidechain_solo_on = 0.0;
double stereo_balance = 0.2840004563331604;
double stereo_link = 100.0;
double stereo_mode = 1.0;
std::vector<BandParams> bands; // up to 6
};