sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 109 Packages Projects Releases Wiki Activity

mtmd: add more sanity checks (#21047)

Browse Source
This commit is contained in:
Xuan-Son Nguyen
2026-03-27 11:00:52 +01:00
committed by GitHub
parent 20197b6fe3
commit 871f1a2d2f
6 changed files with 48 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/mtmd-audio.cpp
+10 -8
View File
@@ -13,23 +13,20 @@
constexpr bool DEBUG = false;
void mtmd_audio_cache::fill_sin_cos_table(int n) {
void mtmd_audio_cache::fill_sin_cos_table(uint32_t n) {
sin_vals.resize(n);
cos_vals.resize(n);
for (int i = 0; i < n; i++) {
for (uint32_t i = 0; i < n; i++) {
double theta = (2 * M_PI * i) / n;
sin_vals[i] = sinf(theta);
cos_vals[i] = cosf(theta);
}
}
void mtmd_audio_cache::fill_hann_window(int length, bool periodic) {
void mtmd_audio_cache::fill_hann_window(uint32_t length, bool periodic) {
hann_window.resize(length);
int offset = -1;
if (periodic) {
offset = 0;
}
for (int i = 0; i < length; i++) {
int offset = periodic ? 0 : -1;
for (uint32_t i = 0; i < length; i++) {
hann_window[i] = 0.5 * (1.0 - cosf((2.0 * M_PI * i) / (length + offset)));
}
}
@@ -165,6 +162,7 @@ static void dft_impl(const mtmd_audio_cache & cache, const float * in, int N, fl
// false = input is complex-valued (interleaved real/imag, stride 2)
template <bool Inverse, bool RealInput>
static void fft_impl(const mtmd_audio_cache & cache, float * in, int N, float * out) {
GGML_ASSERT(N > 0);
const int n_sin_cos_vals = cache.sin_vals.size();
if (N == 1) {
@@ -407,6 +405,8 @@ static bool log_mel_spectrogram(
}
GGML_ASSERT(params.n_fft_bins > 0);
GGML_ASSERT(params.hop_length > 0);
out.n_mel = params.n_mel;
out.n_len = (n_samples - frame_size) / frame_step + 1;
// TODO: handle these checks better
@@ -438,6 +438,7 @@ static bool log_mel_spectrogram(
const int effective_n_len = n_samples_in / frame_step;
if (params.norm_per_feature) {
GGML_ASSERT(effective_n_len > 1);
for (int i = 0; i < out.n_mel; i++) {
double mean = 0;
for (int j = 0; j < effective_n_len; ++j) {
@@ -639,6 +640,7 @@ mtmd_audio_streaming_istft::mtmd_audio_streaming_istft(int n_fft, int hop_length
padding_to_remove((n_fft - hop_length) / 2),
ifft_in(n_fft * 2 * 4, 0.0f), // extra space for recursive IFFT
ifft_out(n_fft * 2 * 4, 0.0f) {
GGML_ASSERT(n_fft > 0 && hop_length > 0 && hop_length <= n_fft);
cache.fill_sin_cos_table(n_fft);
cache.fill_hann_window(n_fft, true);
}