import { pipeline } from '@xenova/transformers';


// Create English text-to-speech pipeline
const synthesizer = await pipeline('text-to-speech', 'Xenova/mms-tts-eng');


// Generate speech
const output = await synthesizer('I love transformers');
// {
//   audio: Float32Array(26112) [...],
//   sampling_rate: 16000
// }

2. CLIPSeg 用于零樣本圖像分割。(#478)

import { AutoTokenizer, AutoProcessor, CLIPSegForImageSegmentation, RawImage } from '@xenova/transformers';


// Load tokenizer, processor, and model
const tokenizer = await AutoTokenizer.from_pretrained('Xenova/clipseg-rd64-refined');
const processor = await AutoProcessor.from_pretrained('Xenova/clipseg-rd64-refined');
const model = await CLIPSegForImageSegmentation.from_pretrained('Xenova/clipseg-rd64-refined');


// Run tokenization
const texts = ['a glass', 'something to fill', 'wood', 'a jar'];
const text_inputs = tokenizer(texts, { padding: true, truncation: true });


// Read image and run processor
const image = await RawImage.read('https://github.com/timojl/clipseg/blob/master/example_image.jpg?raw=true');
const image_inputs = await processor(image);


// Run model with both text and pixel inputs
const { logits } = await model({ ...text_inputs, ...image_inputs });
// logits: Tensor {
//   dims: [4, 352, 352],
//   type: 'float32',
//   data: Float32Array(495616)[ ... ],
//   size: 495616
// }

您可以按如下方式可視化預(yù)測(cè)結(jié)果：

const preds = logits
  .unsqueeze_(1)
  .sigmoid_()
  .mul_(255)
  .round_()
  .to('uint8');


for (let i = 0; i < preds.dims[0]; ++i) {
  const img = RawImage.fromTensor(preds[i]);
  img.save(`prediction_${i}.png`);
}

Original	"a glass"	"something to fill"	"wood"	"a jar"

請(qǐng)查看此處以獲取可用模型列表。

3. SegFormer 用于語義分割和圖像分類。（＃480）

import { pipeline } from '@xenova/transformers';


// Create an image segmentation pipeline
const segmenter = await pipeline('image-segmentation', 'Xenova/segformer_b2_clothes');


// Segment an image
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/young-man-standing-and-leaning-on-car.jpg';
const output = await segmenter(url);

4. Table Transformer 用于從非結(jié)構(gòu)化文檔中提取表格。（＃477）

import { pipeline } from '@xenova/transformers';


// Create an object detection pipeline
const detector = await pipeline('object-detection', 'Xenova/table-transformer-detection', { quantized: false });


// Detect tables in an image
const img = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/invoice-with-table.png';
const output = await detector(img);
// [{ score: 0.9967531561851501, label: 'table', box: { xmin: 52, ymin: 322, xmax: 546, ymax: 525 } }]

5. DiT用于文檔圖像分類。（＃474）

import { pipeline } from '@xenova/transformers';


// Create an image classification pipeline
const classifier = await pipeline('image-classification', 'Xenova/dit-base-finetuned-rvlcdip');


// Classify an image 
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/coca_cola_advertisement.png';
const output = await classifier(url);
// [{ label: 'advertisement', score: 0.9035086035728455 }]

6. SigLIP用于零樣本圖像分類。（＃473）

import { pipeline } from '@xenova/transformers';


// Create a zero-shot image classification pipeline
const classifier = await pipeline('zero-shot-image-classification', 'Xenova/siglip-base-patch16-224');


// Classify images according to provided labels
const url = 'http://images.cocodataset.org/val2017/000000039769.jpg';
const output = await classifier(url, ['2 cats', '2 dogs'], {
    hypothesis_template: 'a photo of {}',
});
// [
//   { score: 0.16770583391189575, label: '2 cats' },
//   { score: 0.000022096000975579955, label: '2 dogs' }
// ]

7. RoFormer 用于蒙版語言建模、序列分類、標(biāo)記分類和問題回答。(#464)

import { pipeline } from '@xenova/transformers';


// Create a masked language modelling pipeline
const pipe = await pipeline('fill-mask', 'Xenova/antiberta2');


// Predict missing token
const output = await pipe('? Q V Q ... C A [MASK] D ... T V S S');

8.分段任意模型 (SAM)

分段任意模型（SAM）可以在給定輸入圖像和輸入點(diǎn)的情況下，用于生成場(chǎng)景中對(duì)象的分割蒙版。請(qǐng)查看此處以獲取完整的預(yù)轉(zhuǎn)換模型列表。對(duì)該模型的支持已在#510中添加。

例子+源碼:https://huggingface.co/spaces/Xenova/segment-anything-web

示例：使用 Xenova/slimsam-77-uniform 執(zhí)行掩模生成。

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


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


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]]] // 2D localization of a window


const inputs = await processor(raw_image, input_points);
const outputs = await model(inputs);


const masks = await processor.post_process_masks(outputs.pred_masks, inputs.original_sizes, inputs.reshaped_input_sizes);
console.log(masks);
// [
//   Tensor {
//     dims: [ 1, 3, 410, 614 ],
//     type: 'bool',
//     data: Uint8Array(755220) [ ... ],
//     size: 755220
//   }
// ]
const scores = outputs.iou_scores;
console.log(scores);
// Tensor {
//   dims: [ 1, 1, 3 ],
//   type: 'float32',
//   data: Float32Array(3) [
//     0.8350210189819336,
//     0.9786665439605713,
//     0.8379436731338501
//   ],
//   size: 3
// }

這樣可以將這三個(gè)預(yù)測(cè)蒙板可視化：

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

接下來，選擇 IoU 分?jǐn)?shù)最高的通道，在本例中是第二個(gè)（綠色）通道。將其與原始圖像相交，我們得到了該主題的孤立版本：

其他改進(jìn)

• 修復(fù)了@Lian1230在#461中提交的關(guān)于Next.js Dockerfile的HOSTNAME 問題。

• 在#467中，在 README 中添加了空模板的鏈接。

• 在 #503 中添加對(duì)使用 ConvNextFeatureExtractor 處理非方形圖像的支持

• 通過 #507 對(duì)遠(yuǎn)程 URL 中的修訂進(jìn)行編碼

• @Lian1230 在 #461 中進(jìn)行了他們的首次貢獻(xiàn)。

改進(jìn)#485中的pipeline函數(shù)的類型。感謝@wesbos提出的建議！

意味著當(dāng)您將鼠標(biāo)懸停在類名稱上時(shí)，您將獲得示例代碼來幫助您。

此版本是 #485 的后續(xù)版本，具有額外的以智能感知為中心的改進(jìn)（請(qǐng)參閱 PR）。

添加對(duì)跨編碼器模型的支持（+修復(fù)令牌類型 ID）（#501）

示例：使用 Xenova/ms-marco-TinyBERT-L-2-v2 進(jìn)行信息檢索。

import { AutoTokenizer, AutoModelForSequenceClassification } from '@xenova/transformers';


const model = await AutoModelForSequenceClassification.from_pretrained('Xenova/ms-marco-TinyBERT-L-2-v2');
const tokenizer = await AutoTokenizer.from_pretrained('Xenova/ms-marco-TinyBERT-L-2-v2');


const features = tokenizer(
    ['How many people live in Berlin?', 'How many people live in Berlin?'],
    {
        text_pair: [
            'Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.',
            'New York City is famous for the Metropolitan Museum of Art.',
        ],
        padding: true,
        truncation: true,
    }
)


const { logits } = await model(features)
console.log(logits.data);
// quantized:   [ 7.210887908935547, -11.559350967407227 ]
// unquantized: [ 7.235750675201416, -11.562294006347656 ]