Minimal fixes for type declarations to resolve errors when importing transformers.js via typescript (partially resolves #1093) (#1122)

* Explicitly declare `batch_decode` as a function with polymorphic args/returns

Resolves typescript inference errors in `models/mgp_str/processing_mgp_str.js` where it does extend from `Processor` but the override returns an object instead of a string array.

* Directly refer to `PretrainedProcessorOptions` in typedec for `AutoProcessor.from_pretrained`

Resolves an issue with tsc where using `@type {typeof Processor.from_pretrained}` does not actually import the `PretrainedProcessorOptions` type alias defined in `processing_utils.js`.

* Explicitly define third argument for Phi3VProcessor._call

Resolves a typescript error where typescript tries to destructure an array directly into padding/truncation/num_crops. Also improves the type safety of calling this function.

* Fix decode type

* Re-use `from_pretrained` types where possible

---------

Co-authored-by: Joshua Lochner <[email protected]>

Author: shrirajh

src/base/feature_extraction_utils.js

@@ -17,23 +17,23 @@ export class FeatureExtractor extends Callable {
     }
 
     /**
-     * Instantiate one of the processor classes of the library from a pretrained model.
+     * Instantiate one of the feature extractor 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)
+     * The feature extractor class to instantiate is selected based on the `feature_extractor_type` property of
+     * the config object (either passed as an argument or loaded from `pretrained_model_name_or_path` if possible)
      * 
      * @param {string} pretrained_model_name_or_path The name or path of the pretrained model. Can be either:
-     * - A string, the *model id* of a pretrained processor hosted inside a model repo on huggingface.co.
+     * - A string, the *model id* of a pretrained feature_extractor hosted inside a model repo on huggingface.co.
      *   Valid model ids can be located at the root-level, like `bert-base-uncased`, or namespaced under a
      *   user or organization name, like `dbmdz/bert-base-german-cased`.
-     * - A path to a *directory* containing processor files, e.g., `./my_model_directory/`.
-     * @param {import('../utils/hub.js').PretrainedOptions} options Additional options for loading the processor.
+     * - A path to a *directory* containing feature_extractor files, e.g., `./my_model_directory/`.
+     * @param {import('../utils/hub.js').PretrainedOptions} options Additional options for loading the feature_extractor.
      * 
-     * @returns {Promise<FeatureExtractor>} A new instance of the Processor class.
+     * @returns {Promise<FeatureExtractor>} A new instance of the Feature Extractor class.
      */
     static async from_pretrained(pretrained_model_name_or_path, options) {
-        const preprocessorConfig = await getModelJSON(pretrained_model_name_or_path, FEATURE_EXTRACTOR_NAME, true, options);
-        return new this(preprocessorConfig);
+        const config = await getModelJSON(pretrained_model_name_or_path, FEATURE_EXTRACTOR_NAME, true, options);
+        return new this(config);
     }
 }
 

src/base/processing_utils.js

@@ -121,8 +121,8 @@ export class Processor extends Callable {
     /**
      * Instantiate one of the processor classes of the library from a pretrained model.
      * 
-     * The processor class to instantiate is selected based on the `feature_extractor_type` property of the config object
-     * (either passed as an argument or loaded from `pretrained_model_name_or_path` if possible)
+     * 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)
      * 
      * @param {string} pretrained_model_name_or_path The name or path of the pretrained model. Can be either:
      * - A string, the *model id* of a pretrained processor hosted inside a model repo on huggingface.co.

src/models/auto/feature_extraction_auto.js

@@ -6,22 +6,6 @@ import * as AllFeatureExtractors from '../feature_extractors.js';
 
 export class AutoFeatureExtractor {
 
-    /**
-     * Instantiate one of the feature extractor classes of the library from a pretrained model.
-     * 
-     * The processor class to instantiate is selected based on the `feature_extractor_type` property of
-     * the config object (either passed as an argument or loaded from `pretrained_model_name_or_path` if possible)
-     * 
-     * @param {string} pretrained_model_name_or_path The name or path of the pretrained model. Can be either:
-     * - A string, the *model id* of a pretrained processor hosted inside a model repo on huggingface.co.
-     *   Valid model ids can be located at the root-level, like `bert-base-uncased`, or namespaced under a
-     *   user or organization name, like `dbmdz/bert-base-german-cased`.
-     * - A path to a *directory* containing processor files, e.g., `./my_model_directory/`.
-     * @param {import('../../utils/hub.js').PretrainedOptions} options Additional options for loading the processor.
-     * 
-     * @returns {Promise<AllFeatureExtractors.ImageProcessor>} A new instance of the Processor class.
-     */
-
     /** @type {typeof FeatureExtractor.from_pretrained} */
     static async from_pretrained(pretrained_model_name_or_path, options={}) {
 

src/models/auto/processing_auto.js

@@ -40,22 +40,6 @@ import * as AllFeatureExtractors from '../feature_extractors.js';
  */
 export class AutoProcessor {
 
-    /**
-     * 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)
-     * 
-     * @param {string} pretrained_model_name_or_path The name or path of the pretrained model. Can be either:
-     * - A string, the *model id* of a pretrained processor hosted inside a model repo on huggingface.co.
-     *   Valid model ids can be located at the root-level, like `bert-base-uncased`, or namespaced under a
-     *   user or organization name, like `dbmdz/bert-base-german-cased`.
-     * - A path to a *directory* containing processor files, e.g., `./my_model_directory/`.
-     * @param {import('../../utils/hub.js').PretrainedOptions} options Additional options for loading the processor.
-     * 
-     * @returns {Promise<Processor>} A new instance of the Processor class.
-     */
-
     /** @type {typeof Processor.from_pretrained} */
     static async from_pretrained(pretrained_model_name_or_path, options={}) {
 

src/models/phi3_v/processing_phi3_v.js

@@ -14,7 +14,7 @@ export class Phi3VProcessor extends Processor {
      * 
      * @param {string|string[]} text 
      * @param {RawImage|RawImage[]} images 
-     * @param  {...any} args 
+     * @param  { { padding?: boolean, truncation?: boolean, num_crops?: number } | undefined } options
      * @returns {Promise<any>}
      */
     async _call(text, images = null, {

src/pipelines.js

@@ -1916,7 +1916,7 @@ export class AutomaticSpeechRecognitionPipeline extends (/** @type {new (options
             const max_new_tokens = Math.floor(aud.length / sampling_rate) * 6;
             const outputs = await this.model.generate({ max_new_tokens, ...kwargs, ...inputs });
 
-            const text = this.processor.batch_decode(outputs, { skip_special_tokens: true })[0];
+            const text = this.processor.batch_decode(/** @type {Tensor} */(outputs), { skip_special_tokens: true })[0];
             toReturn.push({ text });
         }
         return single ? toReturn[0] : toReturn;