mtmd: support Qwen3-TTS (note: breaking change to llama-tts binary) (#26254)

* convert text model * main model load ok * convert encoder ok * speaker encoder loading ok * speaker enc graph * adapt vocab for backbone (with some tricks) * add suppress_tokens * poc new mtmd gen api * convert code_predictor to gguf * load gen_code model ok * add clip_encode * wire up * code gen cgraph init version Co-authored-by: Pascal <admin@serveurperso.com> * code2wav convert to gguf * code2wav graph ok * wire up in/out * (wip) subgraph * wire up * wip, correct code2wav * demo (to be removed) * code2wav preserve kv between calls * demo voice clone * llama: add llama_model_get_tok_embd * mtmd_helper_gen_audio API * fix clamp cold prefix Co-authored-by: Pascal <admin@serveurperso.com> * fuse snake op Co-authored-by: Pascal <admin@serveurperso.com> * demo: use proper sampling * update dev docs * polymorphism helper * revamp llama-tts binary * update docs * fix compile * fix lint * nits * add guide + docs * more timings info * clean up code comments * security fixes * update docs * use ggml_build_forward_select, clean up comments * fix ci * use ISO 639-1 language code * rename CODE2WAV --> GEN_WAV, update docs * clean up * clean up tts.cpp * add seq_id * add step_prompt() * mtmd_helper_model_can_chat * clean up comments --------- Co-authored-by: Pascal <admin@serveurperso.com>
2026-08-04 17:26:15 +02:00
parent 1c3c9674de
commit 0713275082
42 changed files with 3808 additions and 1895 deletions
@@ -327,6 +327,60 @@ struct mtmd_caps {
 };
 MTMD_API struct mtmd_caps mtmd_get_cap_from_file(const char * mmproj_fname);

+/////////////////////////////////////////
+// EXPERIMENTAL API for audio generation, subjected to breaking changes
+
+// represent the pipeline type
+enum mtmd_gen_audio_type {
+    MTMD_GEN_AUDIO_TYPE_NONE, // not supported
+    MTMD_GEN_AUDIO_TYPE_QWEN3TTS,
+};
+struct mtmd_gen_audio_info {
+    enum mtmd_gen_audio_type type;
+    int32_t sample_rate; // in Hz, for example 24000 for qwen3tts
+};
+MTMD_API struct mtmd_gen_audio_info mtmd_gen_audio_get_info(const mtmd_context * ctx);
+
+enum mtmd_gen_process_type {
+    MTMD_GEN_PROCESS_TYPE_GEN_CODE, // h_state to semantic (codes, mel-spectrogram, etc.)
+    MTMD_GEN_PROCESS_TYPE_GEN_WAV,  // convert semantic to PCM audio
+                                    // for qwen3tts, this is code2wav
+};
+struct mtmd_gen_inp {
+    enum mtmd_gen_process_type type;
+
+    // for MTMD_GEN_PROCESS_TYPE_GEN_CODE
+    int32_t code0;  // the sampled codebook 0 entry from backbone
+    float * embd;   // the hidden state from backbone, must have n_text_embd elements
+    int32_t top_k;
+    float   top_p;
+
+    // for MTMD_GEN_PROCESS_TYPE_GEN_WAV
+    int32_t * codes;
+    size_t    n_codes;
+    const char * state_data;
+    size_t       state_size;
+};
+struct mtmd_gen_out {
+    // note: output memory is allocated by the context, valid until next process() call
+
+    // for MTMD_GEN_PROCESS_TYPE_GEN_CODE
+    const int32_t * codes;
+    size_t n_codes;
+    const float * embd; // the generated hidden state, to be fed back to backbone
+                        // it must have n_text_embd elements
+
+    // for MTMD_GEN_PROCESS_TYPE_GEN_WAV
+    const float * audio;
+    size_t        n_samples;
+    const char * state_data;
+    size_t       state_size;
+};
+// note: this API is stateless, caller must handle state management and audio frame accumulation
+MTMD_API int32_t mtmd_gen_audio_process(mtmd_context * ctx,
+                                const struct mtmd_gen_inp * inp,
+                                struct mtmd_gen_out * out);
+
 /////////////////////////////////////////

 // test function, to be used in test-mtmd-c-api.c