G2P (Grapheme To Phoneme) Exploration

import { KokoroTTS } from "kokoro-js";

const tts = await KokoroTTS.from_pretrained(
  "onnx-community/Kokoro-82M-ONNX",
  { dtype: "q8" }, // fp32, fp16, q8, q4, q4f16
);

const text = "Life is like a box of chocolates. You never know what you're gonna get.";
const audio = await tts.generate(text,
  { voice: "af_sky" }, // See `tts.list_voices()`
);
audio.save("audio.wav");

// npm i @xenova/transformers
import { SamModel, AutoProcessor, RawImage } from '@xenova/transformers';

// Load model and processor
const model = await SamModel.from_pretrained('Xenova/slimsam-77-uniform');
const processor = await AutoProcessor.from_pretrained('Xenova/slimsam-77-uniform');

// Prepare image and input points
const img_url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/corgi.jpg';
const raw_image = await RawImage.read(img_url);
const input_points = [[[340, 250]]];

// Process inputs and perform mask generation
const inputs = await processor(raw_image, input_points);
const outputs = await model(inputs);

// Post-process masks
const masks = await processor.post_process_masks(outputs.pred_masks, inputs.original_sizes, inputs.reshaped_input_sizes);
console.log(masks);

// Visualize the mask
const image = RawImage.fromTensor(masks[0][0].mul(255));
image.save('mask.png');