Function mtmd_debug_preprocess_audio

tools/mtmd/mtmd.cpp:1486–1509

}

void mtmd_debug_preprocess_audio(mtmd_context * ctx, const std::vector<float> & samples) {
    if (!ctx->ctx_a) {
        LOG_ERR("%s: model does not support audio input\n", __func__);
        return;
    }
    std::vector<mtmd_audio_mel> mel_spec_chunks;
    bool ok = ctx->audio_preproc->preprocess(samples.data(), samples.size(), mel_spec_chunks);
    if (!ok) {
        LOG_ERR("%s: failed to preprocess audio\n", __func__);
        return;
    }
    LOG_INF("%s: preprocessed audio to %zu mel spec chunks\n", __func__, mel_spec_chunks.size());
    for (size_t i = 0; i < mel_spec_chunks.size(); i++) {
        LOG_INF("%s: mel spec chunk %zu has n_len=%d, n_mel=%d\n", __func__, i, mel_spec_chunks[i].n_len, mel_spec_chunks[i].n_mel);

        // dump mel entries: data is stored as [n_mel][n_len] (mel-major)
        const auto & mel = mel_spec_chunks[i];
        for (int m = 0; m < mel.n_mel; m++) {
            for (int t = 0; t < mel.n_len; t++) {
                LOG_INF("mel[%zu][m=%d][t=%d] = %f\n", i, m, t, mel.data[m * mel.n_len + t]);
            }
        }
    }
}