processors

Processors are used to prepare inputs (e.g., text, image or audio) for a model.

Example: Using a WhisperProcessor to prepare an audio input for a model.

import { AutoProcessor, read_audio } from '@huggingface/transformers';

const processor = await AutoProcessor.from_pretrained('openai/whisper-tiny.en');
const audio = await read_audio('https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/mlk.flac', 16000);
const { input_features } = await processor(audio);
// Tensor {
//   data: Float32Array(240000) [0.4752984642982483, 0.5597258806228638, 0.56434166431427, ...],
//   dims: [1, 80, 3000],
//   type: 'float32',
//   size: 240000,
// }

• processors
  • static
    • .Processor
      • new Processor(config, components, chat_template)
      • instance
        • .image_processor ⇒ *
        • .tokenizer ⇒ PreTrainedTokenizer | undefined
        • .feature_extractor ⇒ *
        • .apply_chat_template(messages, options) ⇒ *
        • .batch_decode(...args) ⇒ *
        • .decode(...args) ⇒ *
        • ._call(input, ...args) ⇒ Promise.<any>
      • static
        • .from_pretrained(pretrained_model_name_or_path, options) ⇒ Promise.<Processor>
  • inner
    • ~PreTrainedTokenizer : Object

processors.Processor

Represents a Processor that extracts features from an input.

Kind: static class of processors

• .Processor
  • new Processor(config, components, chat_template)
  • instance
    • .image_processor ⇒ *
    • .tokenizer ⇒ PreTrainedTokenizer | undefined
    • .feature_extractor ⇒ *
    • .apply_chat_template(messages, options) ⇒ *
    • .batch_decode(...args) ⇒ *
    • .decode(...args) ⇒ *
    • ._call(input, ...args) ⇒ Promise.<any>
  • static
    • .from_pretrained(pretrained_model_name_or_path, options) ⇒ Promise.<Processor>

new Processor(config, components, chat_template)

Creates a new Processor with the given components

processor.image_processor ⇒ <code> * </code>

Kind: instance property of Processor
Returns: * - The image processor of the processor, if it exists.

processor.tokenizer ⇒ <code> PreTrainedTokenizer </code> | <code> undefined </code>

Kind: instance property of Processor
Returns: PreTrainedTokenizer | undefined - The tokenizer of the processor, if it exists.

processor.feature_extractor ⇒ <code> * </code>

Kind: instance property of Processor
Returns: * - The feature extractor of the processor, if it exists.

processor.apply_chat_template(messages, options) ⇒ <code> * </code>

Kind: instance method of Processor

processor.batch_decode(...args) ⇒ <code> * </code>

Kind: instance method of Processor

processor.decode(...args) ⇒ <code> * </code>

Kind: instance method of Processor

processor._call(input, ...args) ⇒ <code> Promise. < any > </code>

Calls the feature_extractor function with the given input.

Kind: instance method of Processor
Returns: Promise.<any> - A Promise that resolves with the extracted features.

Processor.from_pretrained(pretrained_model_name_or_path, options) ⇒ <code> Promise. < Processor > </code>

Instantiate one of the processor classes of the library from a pretrained model.

The processor class to instantiate is selected based on the image_processor_type (or feature_extractor_type; legacy) property of the config object (either passed as an argument or loaded from pretrained_model_name_or_path if possible)

Kind: static method of Processor
Returns: Promise.<Processor> - A new instance of the Processor class.

processors~PreTrainedTokenizer : <code> Object </code>

Additional processor-specific properties.

Kind: inner typedef of processors