Skip to content

mtmd: propagate const to preproc class #28310

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ngxson merged 1 commit into from
Sep 3, 2026
Merged

mtmd: propagate const to preproc class #28310

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 11 additions & 11 deletions tools/mtmd/mtmd-audio.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -549,7 +549,7 @@ void mtmd_audio_preprocessor_whisper::initialize() {

bool mtmd_audio_preprocessor_whisper::preprocess(const float * samples,
size_t n_samples,
std::vector<mtmd_audio_mel> & output) {
std::vector<mtmd_audio_mel> & output) const {
if (n_samples == 0) {
// empty audio
return false;
Expand Down Expand Up @@ -637,7 +637,7 @@ void mtmd_audio_preprocessor_qwen3a::initialize() {

bool mtmd_audio_preprocessor_qwen3a::preprocess(const float * samples,
size_t n_samples,
std::vector<mtmd_audio_mel> & output) {
std::vector<mtmd_audio_mel> & output) const {
if (n_samples == 0) {
return false;
}
Expand Down Expand Up @@ -739,7 +739,7 @@ void mtmd_audio_preprocessor_dots3note::initialize() {

bool mtmd_audio_preprocessor_dots3note::preprocess(const float * samples,
size_t n_samples,
std::vector<mtmd_audio_mel> & output) {
std::vector<mtmd_audio_mel> & output) const {
if (n_samples == 0) {
return false;
}
Expand Down Expand Up @@ -839,7 +839,7 @@ void mtmd_audio_preprocessor_mimo_audio::initialize() {

bool mtmd_audio_preprocessor_mimo_audio::preprocess(const float * samples,
size_t n_samples,
std::vector<mtmd_audio_mel> & output) {
std::vector<mtmd_audio_mel> & output) const {
if (n_samples == 0) {
return false;
}
Expand Down Expand Up @@ -898,7 +898,7 @@ void mtmd_audio_preprocessor_qwen3tts_spk::initialize() {

bool mtmd_audio_preprocessor_qwen3tts_spk::preprocess(const float * samples,
size_t n_samples,
std::vector<mtmd_audio_mel> & output) {
std::vector<mtmd_audio_mel> & output) const {
if (n_samples == 0) {
return false;
}
Expand Down Expand Up @@ -955,7 +955,7 @@ void mtmd_audio_preprocessor_conformer::initialize() {

bool mtmd_audio_preprocessor_conformer::preprocess(const float * samples,
size_t n_samples,
std::vector<mtmd_audio_mel> & output) {
std::vector<mtmd_audio_mel> & output) const {
// empty audio
if (n_samples == 0) {
return false;
Expand Down Expand Up @@ -1003,7 +1003,7 @@ void mtmd_audio_preprocessor_granite_speech::initialize() {

bool mtmd_audio_preprocessor_granite_speech::preprocess(const float * samples,
size_t n_samples,
std::vector<mtmd_audio_mel> & output) {
std::vector<mtmd_audio_mel> & output) const {
if (n_samples == 0) {
return false;
}
Expand Down Expand Up @@ -1117,7 +1117,7 @@ void mtmd_audio_preprocessor_gemma4a::initialize() {

bool mtmd_audio_preprocessor_gemma4a::preprocess(const float * samples,
size_t n_samples,
std::vector<mtmd_audio_mel> & output) {
std::vector<mtmd_audio_mel> & output) const {
if (n_samples == 0) {
return false;
}
Expand Down Expand Up @@ -1266,7 +1266,7 @@ void mtmd_audio_preprocessor_parakeet::initialize() {

bool mtmd_audio_preprocessor_parakeet::preprocess(const float * samples,
size_t n_samples_in,
std::vector<mtmd_audio_mel> & output) {
std::vector<mtmd_audio_mel> & output) const {
if (n_samples_in == 0) {
return false;
}
Expand Down Expand Up @@ -1386,7 +1386,7 @@ void mtmd_audio_preprocessor_gemma4ua::initialize() {

bool mtmd_audio_preprocessor_gemma4ua::preprocess(const float * samples,
size_t n_samples,
std::vector<mtmd_audio_mel> & output) {
std::vector<mtmd_audio_mel> & output) const {
if (n_samples == 0) {
return false;
}
Expand Down Expand Up @@ -1527,7 +1527,7 @@ std::vector<float> mtmd_audio_streaming_istft::flush() {

bool mtmd_audio_preprocessor_pockettts::preprocess(const float * samples,
size_t n_samples,
std::vector<mtmd_audio_mel> & output) {
std::vector<mtmd_audio_mel> & output) const {
// the encoder needs whole frames, see pad_for_conv1d() in the reference
const int64_t frame_size = (int64_t) hparams.mimi_downsample * 120;
if (n_samples == 0 || frame_size <= 0) {
Expand Down
24 changes: 12 additions & 12 deletions tools/mtmd/mtmd-audio.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,13 +57,13 @@ struct mtmd_audio_preprocessor {

virtual ~mtmd_audio_preprocessor() = default;
virtual void initialize() = 0; // NOT thread-safe
virtual bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) = 0;
virtual bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) const = 0;
};

struct mtmd_audio_preprocessor_whisper : mtmd_audio_preprocessor {
mtmd_audio_preprocessor_whisper(const clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) {}
void initialize() override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) const override;

private:
mtmd_audio_cache cache;
Expand All @@ -72,7 +72,7 @@ struct mtmd_audio_preprocessor_whisper : mtmd_audio_preprocessor {
struct mtmd_audio_preprocessor_conformer : mtmd_audio_preprocessor {
mtmd_audio_preprocessor_conformer(const clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) {}
void initialize() override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) const override;

private:
mtmd_audio_cache cache;
Expand All @@ -81,7 +81,7 @@ struct mtmd_audio_preprocessor_conformer : mtmd_audio_preprocessor {
struct mtmd_audio_preprocessor_granite_speech : mtmd_audio_preprocessor {
mtmd_audio_preprocessor_granite_speech(const clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) {}
void initialize() override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) const override;

private:
mtmd_audio_cache cache;
Expand All @@ -90,7 +90,7 @@ struct mtmd_audio_preprocessor_granite_speech : mtmd_audio_preprocessor {
struct mtmd_audio_preprocessor_gemma4a : mtmd_audio_preprocessor {
mtmd_audio_preprocessor_gemma4a(const clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) {}
void initialize() override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) const override;

private:
mtmd_audio_cache cache;
Expand All @@ -99,13 +99,13 @@ struct mtmd_audio_preprocessor_gemma4a : mtmd_audio_preprocessor {
struct mtmd_audio_preprocessor_gemma4ua : mtmd_audio_preprocessor {
mtmd_audio_preprocessor_gemma4ua(const clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) {}
void initialize() override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) const override;
};

struct mtmd_audio_preprocessor_qwen3a : mtmd_audio_preprocessor {
mtmd_audio_preprocessor_qwen3a(const clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) {}
void initialize() override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) const override;

private:
mtmd_audio_cache cache;
Expand All @@ -114,7 +114,7 @@ struct mtmd_audio_preprocessor_qwen3a : mtmd_audio_preprocessor {
struct mtmd_audio_preprocessor_dots3note : mtmd_audio_preprocessor {
mtmd_audio_preprocessor_dots3note(const clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) {}
void initialize() override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) const override;

private:
mtmd_audio_cache cache;
Expand All @@ -123,7 +123,7 @@ struct mtmd_audio_preprocessor_dots3note : mtmd_audio_preprocessor {
struct mtmd_audio_preprocessor_mimo_audio : mtmd_audio_preprocessor {
mtmd_audio_preprocessor_mimo_audio(const clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) {}
void initialize() override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) const override;

private:
mtmd_audio_cache cache;
Expand All @@ -132,7 +132,7 @@ struct mtmd_audio_preprocessor_mimo_audio : mtmd_audio_preprocessor {
struct mtmd_audio_preprocessor_qwen3tts_spk : mtmd_audio_preprocessor {
mtmd_audio_preprocessor_qwen3tts_spk(const clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) {}
void initialize() override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) const override;

private:
mtmd_audio_cache cache;
Expand All @@ -142,13 +142,13 @@ struct mtmd_audio_preprocessor_qwen3tts_spk : mtmd_audio_preprocessor {
struct mtmd_audio_preprocessor_pockettts : mtmd_audio_preprocessor {
mtmd_audio_preprocessor_pockettts(const clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) {}
void initialize() override {}
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) const override;
};

struct mtmd_audio_preprocessor_parakeet : mtmd_audio_preprocessor {
mtmd_audio_preprocessor_parakeet(clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) { }
void initialize() override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) override;
bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) const override;

private:
mtmd_audio_cache cache;
Expand Down
Loading
Loading