ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

mtmd : add ultravox audio input (#13623)

Browse source 
* convert ok, load ok

* warmup ok

* test

* still does not work?

* fix padding

* temporary give up

* fix merge conflict

* build_ultravox()

* rm test

* fix merge conflict

* add necessary mtmd APIs

* first working version (only 4s of audio)

* will this monster compile?

* fix compile

* please compile

* fPIC

* fix windows

* various fixes

* clean up audio_helpers

* fix conversion

* add some debug stuff

* long audio input ok

* adapt the api

* add --audio arg

* final touch UX

* add miniaudio to readme

* fix typo

* refactor kv metadata

* mtmd_default_marker()
This commit is contained in:
Xuan-Son Nguyen 2025-05-22 20:42:48 +02:00 • committed by GitHub
parent ab86335760
commit 797990c4bc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 95401 additions and 259 deletions
Download patch file Download diff file Expand all files Collapse all files

6
tools/mtmd/clip.h
View file

@ -93,3 +93,9 @@ bool clip_is_llava(const struct clip_ctx * ctx);
bool clip_is_gemma3(const struct clip_ctx * ctx);
bool clip_encode_float_image (struct clip_ctx * ctx, int n_threads, float * img, int h, int w, float * vec);
// use by audio input
void clip_image_f32_batch_add_mel(struct clip_image_f32_batch * batch, int n_mel, int n_frames, float * mel);
bool clip_has_vision_encoder(const struct clip_ctx * ctx);
bool clip_has_audio_encoder(const struct clip_ctx * ctx);