server : support audio input (#13714)

* server : support audio input

* add audio support on webui
This commit is contained in:
Xuan-Son Nguyen 2025-05-23 11:03:47 +02:00 committed by GitHub
parent faaaff5f94
commit 9ecf3e66a3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 276 additions and 173 deletions

View file

@ -12,17 +12,7 @@ size_t mtmd_helper_get_n_tokens(const mtmd_input_chunks * chunks) {
size_t n_tokens = 0;
for (size_t i = 0; i < mtmd_input_chunks_size(chunks); i++) {
auto chunk = mtmd_input_chunks_get(chunks, i);
auto chunk_type = mtmd_input_chunk_get_type(chunk);
if (chunk_type == MTMD_INPUT_CHUNK_TYPE_TEXT) {
size_t n_tokens_text;
mtmd_input_chunk_get_tokens_text(chunk, &n_tokens_text);
n_tokens += n_tokens_text;
} else if (chunk_type == MTMD_INPUT_CHUNK_TYPE_IMAGE) {
auto tokens_image = mtmd_input_chunk_get_tokens_image(chunk);
n_tokens += mtmd_image_tokens_get_n_tokens(tokens_image);
} else {
GGML_ASSERT(false && "chunk type not supported");
}
n_tokens += mtmd_input_chunk_get_n_tokens(chunk);
}
return n_tokens;
}
@ -31,17 +21,7 @@ llama_pos mtmd_helper_get_n_pos(const mtmd_input_chunks * chunks) {
llama_pos n_pos = 0;
for (size_t i = 0; i < mtmd_input_chunks_size(chunks); i++) {
auto chunk = mtmd_input_chunks_get(chunks, i);
auto chunk_type = mtmd_input_chunk_get_type(chunk);
if (chunk_type == MTMD_INPUT_CHUNK_TYPE_TEXT) {
size_t n_tokens_text;
mtmd_input_chunk_get_tokens_text(chunk, &n_tokens_text);
n_pos += n_tokens_text;
} else if (chunk_type == MTMD_INPUT_CHUNK_TYPE_IMAGE) {
auto tokens_image = mtmd_input_chunk_get_tokens_image(chunk);
n_pos += mtmd_image_tokens_get_n_pos(tokens_image);
} else {
GGML_ASSERT(false && "chunk type not supported");
}
n_pos += mtmd_input_chunk_get_n_pos(chunk);
}
return n_pos;
}

View file

@ -751,6 +751,10 @@ const unsigned char * mtmd_bitmap_get_data(const mtmd_bitmap * bitmap) {
return bitmap->data.data();
}
size_t mtmd_bitmap_get_n_bytes(const mtmd_bitmap * bitmap) {
return bitmap->data.size();
}
bool mtmd_bitmap_is_audio(const mtmd_bitmap * bitmap) {
return bitmap->is_audio;
}

View file

@ -119,11 +119,12 @@ MTMD_API bool mtmd_support_audio(mtmd_context * ctx);
// the data is in float format (PCM F32)
MTMD_API mtmd_bitmap * mtmd_bitmap_init (uint32_t nx, uint32_t ny, const unsigned char * data);
MTMD_API mtmd_bitmap * mtmd_bitmap_init_from_audio(size_t n_samples, const float * data);
MTMD_API uint32_t mtmd_bitmap_get_nx (const mtmd_bitmap * bitmap);
MTMD_API uint32_t mtmd_bitmap_get_ny (const mtmd_bitmap * bitmap);
MTMD_API const unsigned char * mtmd_bitmap_get_data(const mtmd_bitmap * bitmap);
MTMD_API bool mtmd_bitmap_is_audio(const mtmd_bitmap * bitmap);
MTMD_API void mtmd_bitmap_free (mtmd_bitmap * bitmap);
MTMD_API uint32_t mtmd_bitmap_get_nx (const mtmd_bitmap * bitmap);
MTMD_API uint32_t mtmd_bitmap_get_ny (const mtmd_bitmap * bitmap);
MTMD_API const unsigned char * mtmd_bitmap_get_data (const mtmd_bitmap * bitmap);
MTMD_API size_t mtmd_bitmap_get_n_bytes(const mtmd_bitmap * bitmap);
MTMD_API bool mtmd_bitmap_is_audio (const mtmd_bitmap * bitmap);
MTMD_API void mtmd_bitmap_free (mtmd_bitmap * bitmap);
// bitmap ID is optional, but useful for KV cache tracking
// these getters/setters are dedicated functions, so you can for example calculate the hash of the image based on mtmd_bitmap_get_data()
MTMD_API const char * mtmd_bitmap_get_id(const mtmd_bitmap * bitmap);
@ -322,6 +323,7 @@ struct bitmap {
uint32_t nx() { return mtmd_bitmap_get_nx(ptr.get()); }
uint32_t ny() { return mtmd_bitmap_get_ny(ptr.get()); }
const unsigned char * data() { return mtmd_bitmap_get_data(ptr.get()); }
size_t n_bytes() { return mtmd_bitmap_get_n_bytes(ptr.get()); }
std::string id() { return mtmd_bitmap_get_id(ptr.get()); }
void set_id(const char * id) { mtmd_bitmap_set_id(ptr.get(), id); }
};