mtmd : Adding support for Nvidia Music Flamingo Model (#18470)

* Inital commit, debugging q5_k_s quant

* Made hf_to_gguf extend whisper to reduce code duplication

* addressed convert_hf_to_gguf pull request issue

---------

Co-authored-by: Henry D <henrydorsey147@gmail.com>

tools/mtmd/mtmd.cpp

@@ -330,6 +330,7 @@ struct mtmd_context {
             case PROJECTOR_TYPE_ULTRAVOX:
             case PROJECTOR_TYPE_VOXTRAL:
             case PROJECTOR_TYPE_GLMA:
+            case PROJECTOR_TYPE_MUSIC_FLAMINGO:
                 audio_preproc = std::make_unique<mtmd_audio_preprocessor_whisper>(ctx_a);
                 break;
             case PROJECTOR_TYPE_LFM2A:
@@ -352,6 +353,9 @@ struct mtmd_context {
             // [BEGIN_AUDIO] ... (embeddings) ...
             aud_beg = "[BEGIN_AUDIO]";
 
+        } else if (proj == PROJECTOR_TYPE_MUSIC_FLAMINGO) {
+            // <sound> ... (embeddings) ...
+            aud_beg = "<sound>";
         }
     }