const ort = require('onnxruntime-node');
const fs = require('fs');
const D='/private/tmp/claude-502/-Users-Studio-Documents-BandLineupDisplay/cee248f6-d861-4845-bd13-03867cf46596/scratchpad/piper/';
const cfg = JSON.parse(fs.readFileSync(D+'lessac.json','utf8'));
console.log('sample_rate', cfg.audio.sample_rate, 'num_symbols', cfg.num_symbols, 'phoneme_type', cfg.phoneme_type, 'lang', cfg.language && cfg.language.code);
console.log('inference defaults', JSON.stringify(cfg.inference));
const map = cfg.phoneme_id_map;
// crude: use the espeak IPA of the sentence is unavailable here; approximate with the raw characters that exist in the map
const IPA = "dʒiːzəs sɛd tuː ðɛm aɪ æm ðə bɹɛd ʌv laɪf huːɛvɚ kʌmz tuː miː";
const ids=[map['^'][0]];
for (const ch of IPA){ if(map[ch]){ ids.push(map[ch][0]); ids.push(map['_'][0]); } }
ids.push(map['$'][0]);
(async()=>{
  const ep = process.argv[2]||'cpu';
  const t=Date.now();
  const sess = await ort.InferenceSession.create(D+'lessac.onnx',{executionProviders:[ep]});
  console.log(`[${ep}] load ${Date.now()-t}ms inputs=${sess.inputNames.join(',')}`);
  const mk=(len)=>({
    input: new ort.Tensor('int64', BigInt64Array.from(ids.map(BigInt)), [1, ids.length]),
    input_lengths: new ort.Tensor('int64', BigInt64Array.from([BigInt(ids.length)]), [1]),
    scales: new ort.Tensor('float32', Float32Array.from([cfg.inference.noise_scale, len, cfg.inference.noise_w]), [3])
  });
  for (const ls of [1.0, 0.85, 0.7]) {
    const feeds = mk(ls);
    let o = await sess.run(feeds);
    const k=sess.outputNames[0];
    const frames=o[k].data.length;
    let tot=0; for(let i=0;i<8;i++){const a=Date.now(); await sess.run(feeds); tot+=Date.now()-a;}
    const avg=tot/8/1000, dur=frames/cfg.audio.sample_rate;
    console.log(`[${ep}] length_scale=${ls}  audio ${dur.toFixed(2)}s  infer ${avg.toFixed(3)}s  RTF ${(avg/dur).toFixed(4)}  rss ${Math.round(process.memoryUsage().rss/1048576)}MB`);
  }
})().catch(e=>console.log(`[${process.argv[2]}] ERR`, e.message));