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
@@ -791,6 +791,66 @@ bool mtmd_audio_preprocessor_mimo_audio::preprocess(const float *
    return true;
 }

+//
+// mtmd_audio_preprocessor_qwen3tts_spk
+//
+// same as mel_spectrogram() in modeling_qwen3_tts.py
+// ECAPA-TDNN takes the whole clip in one pass, so no Whisper-style chunking or normalization
+//
+
+void mtmd_audio_preprocessor_qwen3tts_spk::initialize() {
+    cache.fill_sin_cos_table(hparams.audio_n_fft);
+    cache.fill_hann_window(hparams.audio_window_len, true);
+    cache.fill_mel_filterbank_matrix(hparams.n_mel_bins, hparams.audio_n_fft, hparams.audio_sample_rate);
+}
+
+bool mtmd_audio_preprocessor_qwen3tts_spk::preprocess(const float *                 samples,
+                                                      size_t                        n_samples,
+                                                      std::vector<mtmd_audio_mel> & output) {
+    if (n_samples == 0) {
+        return false;
+    }
+
+    GGML_ASSERT(!cache.sin_vals.empty());
+    GGML_ASSERT(!cache.cos_vals.empty());
+    GGML_ASSERT(!cache.filters.data.empty());
+
+    // reflect pad by (n_fft - hop) / 2 = 384, matching center=False STFT framing
+    const int pad = (hparams.audio_n_fft - hparams.audio_hop_len) / 2;
+    if (n_samples < (size_t) pad + 1) {
+        return false;
+    }
+
+    std::vector<float> padded(n_samples + 2 * pad, 0.0f);
+    for (int i = 0; i < pad; i++) {
+        padded[i] = samples[pad - i];
+    }
+    std::copy(samples, samples + n_samples, padded.begin() + pad);
+    for (int i = 0; i < pad; i++) {
+        padded[n_samples + pad + i] = samples[n_samples - 2 - i];
+    }
+
+    filter_params params;
+    params.n_mel            = hparams.n_mel_bins;
+    params.n_fft_bins       = 1 + (hparams.audio_n_fft / 2);
+    params.hann_window_size = hparams.audio_window_len;
+    params.hop_length       = hparams.audio_hop_len;
+    params.sample_rate      = hparams.audio_sample_rate;
+    params.no_padding       = true; // reflect padding already applied above
+    params.use_natural_log  = true;
+    params.use_magnitude    = true;
+    params.mel_floor        = 1e-5f;
+
+    mtmd_audio_mel out;
+    bool ok = log_mel_spectrogram(padded.data(), (int) padded.size(), 4, params, cache, out);
+    if (!ok) {
+        return false;
+    }
+
+    output.push_back(std::move(out));
+    return true;
+}
+
 //
 // mtmd_audio_preprocessor_conformer
 //