vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-04-28 03:30:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

mtmd: refactor audio preprocessing (#17978)

Browse source 
* 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
parent 4a4f7e6550
commit 96a181a933
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 379 additions and 596 deletions
Download patch file Download diff file Expand all files Collapse all files

32
tools/mtmd/mtmd.cpp
View file

@ -151,8 +151,7 @@ struct mtmd_context {
// string template for slice image delimiters with row/col (idefics3)
std::string sli_img_start_tmpl;
// for whisper, we pre-calculate the mel filter bank
whisper_preprocessor::whisper_filters w_filters;
std::unique_ptr<mtmd_audio_preprocessor> audio_preproc;
// TODO @ngxson : add timings
@ -317,14 +316,25 @@ struct mtmd_context {
GGML_ASSERT(ctx_a != nullptr);
projector_type proj = clip_get_projector_type(ctx_a);
if (clip_has_whisper_encoder(ctx_a)) {
// TODO @ngxson : check if model n_mel is 128 or 80
w_filters = whisper_precalc_filters::get_128_bins();
}
LOG_WRN("%s: audio input is in experimental stage and may have reduced quality:\n"
" https://github.com/ggml-org/llama.cpp/discussions/13759\n", __func__);
// set preprocessor
switch (proj) {
case PROJECTOR_TYPE_QWEN2A:
case PROJECTOR_TYPE_QWEN25O:
case PROJECTOR_TYPE_ULTRAVOX:
case PROJECTOR_TYPE_VOXTRAL:
audio_preproc = std::make_unique<mtmd_audio_preprocessor_whisper>(ctx_a);
break;
default:
GGML_ABORT("unsupported audio projector type");
}
// initialize audio preprocessor
audio_preproc->initialize();
// set special tokens
if (proj == PROJECTOR_TYPE_QWEN2A) {
// <|audio_bos|> ... (embeddings) ... <|audio_eos|>
aud_beg = "<|audio_bos|>";
@ -653,11 +663,10 @@ struct mtmd_tokenizer {
}
// preprocess audio
GGML_ASSERT(ctx->w_filters.n_mel); // make sure we have filter preloaded
std::vector<whisper_preprocessor::whisper_mel> mel_spec_chunks;
std::vector<mtmd_audio_mel> mel_spec_chunks;
const float * samples = (const float *)bitmap->data.data();
size_t n_samples = bitmap->data.size() / sizeof(float);
bool ok = whisper_preprocessor::preprocess_audio(samples, n_samples, ctx->w_filters, mel_spec_chunks);
bool ok = ctx->audio_preproc->preprocess(samples, n_samples, mel_spec_chunks);
if (!ok) {
LOG_ERR("Unable to preprocess audio\n");
return 2;
@ -863,8 +872,7 @@ int mtmd_get_audio_bitrate(mtmd_context * ctx) {
if (!ctx->ctx_a) {
return -1;
}
// for now, we assume that all audio models have the same bitrate
return 16000; // 16kHz
return clip_get_hparams(ctx->ctx_a)->audio_sample_rate;
}
//