mtmd: refactor audio preprocessing (#17978)

* mtmd: refactor audio preprocessing

* refactor

Co-authored-by: Tarek <tdakhran@users.noreply.github.com>

* wip

* wip (2)

* improve constructor

* fix use_natural_log

* fix padding for short input

* clean up

* remove need_chunking

---------

Co-authored-by: Tarek <tdakhran@users.noreply.github.com>
This commit is contained in:
Xuan-Son Nguyen
2025-12-15 14:16:52 +01:00
committed by GitHub
co-authored by Tarek
parent 4a4f7e6550
commit 96a181a933
5 changed files with 379 additions and 596 deletions
+9
View File
@@ -65,6 +65,13 @@ struct clip_hparams {
int32_t n_mel_bins = 0; // whisper preprocessor
int32_t proj_stack_factor = 0; // ultravox
// audio-to-mel preprocessor params
int32_t audio_chunk_len = -1; // in seconds
int32_t audio_sample_rate = -1;
int32_t audio_n_fft = -1;
int32_t audio_window_len = -1;
int32_t audio_hop_len = -1;
// legacy
bool has_llava_projector = false;
int minicpmv_version = 0;
@@ -278,3 +285,5 @@ struct clip_model {
|| proj_type == PROJECTOR_TYPE_VOXTRAL;
}
};
const clip_hparams * clip_get_hparams(const struct clip_ctx * ctx);