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
@@ -157,6 +157,73 @@ MTMD_API int32_t mtmd_helper_video_read_next(mtmd_helper_video * ctx,
            mtmd_bitmap ** out_bitmap,
            char ** out_text);

+// return true if model can be used for chat
+MTMD_API bool mtmd_helper_model_can_chat(struct llama_context * lctx, struct mtmd_context * mctx);
+
+//
+// Audio generation helpers
+// (early-stage experimental, subjected to breaking changes)
+//
+
+// audio generation helper context
+// contains accumulator for generated audio features and PCM audio
+struct mtmd_helper_gen_audio;
+typedef struct mtmd_helper_gen_audio mtmd_helper_gen_audio;
+
+enum mtmd_helper_gen_audio_outtype {
+    MTMD_HELPER_GEN_AUDIO_OUTTYPE_PCM, // raw PCM
+    MTMD_HELPER_GEN_AUDIO_OUTTYPE_WAV, // WAV PCM 16-bit LE, mono
+};
+struct mtmd_helper_gen_audio_inp {
+    llama_seq_id seq_id;
+
+    const char * prompt;
+    size_t       prompt_len;
+
+    mtmd_bitmap * speaker_ref; // optional, can be NULL
+    const char * lang; // optional, can be NULL
+
+    int32_t top_k;
+    float   top_p;
+
+    enum mtmd_helper_gen_audio_outtype out_type;
+};
+
+MTMD_API mtmd_helper_gen_audio * mtmd_helper_gen_audio_init(
+                                    struct llama_context * lctx,
+                                    struct mtmd_context * mctx);
+
+MTMD_API void mtmd_helper_gen_audio_free(mtmd_helper_gen_audio * ctx);
+
+MTMD_API void mtmd_helper_gen_audio_reset(mtmd_helper_gen_audio * ctx);
+
+MTMD_API int32_t mtmd_helper_gen_audio_set_input(
+                        mtmd_helper_gen_audio * ctx,
+                        const struct mtmd_helper_gen_audio_inp * inp);
+
+// processes at most n_batch prompt tokens per call
+// returns: >0 = number of prompt tokens remaining, 0 = done, <0 = error
+MTMD_API int32_t mtmd_helper_gen_audio_step_prompt(
+                        mtmd_helper_gen_audio * ctx,
+                        int32_t n_batch);
+
+// generates one frame; must only be called after step_prompt() has returned 0
+// h_state_out is valid until next step_gen() or reset() call
+MTMD_API int32_t mtmd_helper_gen_audio_step_gen(
+                        mtmd_helper_gen_audio * ctx,
+                        llama_token sampled,
+                        const float *  h_state_in,
+                        const float ** h_state_out);
+
+// out_data valid until next get_output() or reset() call
+// out_n_samples (optional, can be NULL) receives the number of generated PCM samples
+MTMD_API int32_t mtmd_helper_gen_audio_get_output(
+                        mtmd_helper_gen_audio * ctx,
+                        int32_t * out_sample_rate,
+                        const char ** out_data,
+                        size_t * out_data_len,
+                        int64_t * out_n_samples);
+
 #ifdef __cplusplus
 } // extern "C"
 #endif
@@ -177,6 +244,31 @@ struct mtmd_helper_video_deleter {
 };
 using video_ptr = std::unique_ptr<mtmd_helper_video, mtmd_helper_video_deleter>;

+// audio generation-related C++ wrappers
+struct mtmd_helper_gen_audio_deleter {
+    void operator()(mtmd_helper_gen_audio * val) { mtmd_helper_gen_audio_free(val); }
+};
+using gen_audio_ptr = std::unique_ptr<mtmd_helper_gen_audio, mtmd_helper_gen_audio_deleter>;
+struct gen_audio {
+    gen_audio_ptr ctx;
+    gen_audio(struct llama_context * lctx, struct mtmd_context * mctx) : ctx(mtmd_helper_gen_audio_init(lctx, mctx)) {}
+    void reset() {
+        mtmd_helper_gen_audio_reset(ctx.get());
+    }
+    int32_t set_input(const struct mtmd_helper_gen_audio_inp * inp) {
+        return mtmd_helper_gen_audio_set_input(ctx.get(), inp);
+    }
+    int32_t step_prompt(int32_t n_batch) {
+        return mtmd_helper_gen_audio_step_prompt(ctx.get(), n_batch);
+    }
+    int32_t step_gen(llama_token sampled, const float * h_state, const float ** h_state_out) {
+        return mtmd_helper_gen_audio_step_gen(ctx.get(), sampled, h_state, h_state_out);
+    }
+    int32_t get_output(int32_t * out_sample_rate, const char ** out_data, size_t * out_data_len, int64_t * out_n_samples = nullptr) {
+        return mtmd_helper_gen_audio_get_output(ctx.get(), out_sample_rate, out_data, out_data_len, out_n_samples);
+    }
+};
+
 } // namespace mtmd_helper
 #endif