diff --git a/docs/source/en/task_summary.mdx b/docs/source/en/task_summary.mdx
index 95c2d9c201a586..55e4a230a1b65e 100644
--- a/docs/source/en/task_summary.mdx
+++ b/docs/source/en/task_summary.mdx
@@ -967,3 +967,158 @@ Here is an example of doing translation using a model and a tokenizer. The proce
 </frameworkcontent>
 
 We get the same translation as with the pipeline example.
+
+## Audio classification
+
+Audio classification assigns a class to an audio signal. The Keyword Spotting dataset from the [SUPERB](https://huggingface.co/datasets/superb) benchmark is an example dataset that can be used for audio classification fine-tuning. This dataset contains ten classes of keywords for classification. If you'd like to fine-tune a model for audio classification, take a look at the [run_audio_classification.py](https://github.com/huggingface/transformers/blob/main/examples/pytorch/audio-classification/run_audio_classification.py) script or this [how-to guide](./tasks/audio_classification).
+
+The following examples demonstrate how to use a [`pipeline`] and a model and tokenizer for audio classification inference:
+
+```py
+>>> from transformers import pipeline
+
+>>> audio_classifier = pipeline(
+...     task="audio-classification", model="ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition"
+... )
+>>> audio_classifier("jfk_moon_speech.wav")
+[{'label': 'calm', 'score': 0.13856211304664612},
+ {'label': 'disgust', 'score': 0.13148026168346405},
+ {'label': 'happy', 'score': 0.12635163962841034},
+ {'label': 'angry', 'score': 0.12439591437578201},
+ {'label': 'fearful', 'score': 0.12404385954141617}]
+```
+
+The general process for using a model and feature extractor for audio classification is:
+
+1. Instantiate a feature extractor and a model from the checkpoint name.
+2. Process the audio signal to be classified with a feature extractor.
+3. Pass the input through the model and take the `argmax` to retrieve the most likely class.
+4. Convert the class id to a class name with `id2label` to return an interpretable result.
+
+<frameworkcontent>
+<pt>
+```py
+>>> from transformers import AutoFeatureExtractor, AutoModelForAudioClassification
+>>> from datasets import load_dataset
+>>> import torch
+
+>>> dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
+>>> dataset = dataset.sort("id")
+>>> sampling_rate = dataset.features["audio"].sampling_rate
+
+>>> feature_extractor = AutoFeatureExtractor.from_pretrained("superb/wav2vec2-base-superb-ks")
+>>> model = AutoModelForAudioClassification.from_pretrained("superb/wav2vec2-base-superb-ks")
+
+>>> inputs = feature_extractor(dataset[0]["audio"]["array"], sampling_rate=sampling_rate, return_tensors="pt")
+
+>>> with torch.no_grad():
+...     logits = model(**inputs).logits
+
+>>> predicted_class_ids = torch.argmax(logits, dim=-1).item()
+>>> predicted_label = model.config.id2label[predicted_class_ids]
+>>> predicted_label
+```
+</pt>
+</frameworkcontent>
+
+## Automatic speech recognition
+
+Automatic speech recognition transcribes an audio signal to text. The [Common Voice](https://huggingface.co/datasets/common_voice) dataset is an example dataset that can be used for automatic speech recognition fine-tuning. It contains an audio file of a speaker and the corresponding sentence. If you'd like to fine-tune a model for automatic speech recognition, take a look at the [run_speech_recognition_ctc.py](https://github.com/huggingface/transformers/blob/main/examples/pytorch/speech-recognition/run_speech_recognition_ctc.py) or [run_speech_recognition_seq2seq.py](https://github.com/huggingface/transformers/blob/main/examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py) scripts or this [how-to guide](./tasks/asr).
+
+The following examples demonstrate how to use a [`pipeline`] and a model and tokenizer for automatic speech recognition inference:
+
+```py
+>>> from transformers import pipeline
+
+>>> speech_recognizer = pipeline(
+...     task="automatic-speech-recognition", model="facebook/wav2vec2-base-960h"
+... )
+>>> speech_recognizer("jfk_moon_speech.wav")
+{'text': "PRESENTETE MISTER VICE PRESIDENT GOVERNOR CONGRESSMEN THOMAS SAN O TE WILAN CONGRESSMAN MILLA MISTER WEBB MSTBELL SCIENIS DISTINGUISHED GUESS AT LADIES AND GENTLEMAN I APPRECIATE TO YOUR PRESIDENT HAVING MADE ME AN HONORARY VISITING PROFESSOR AND I WILL ASSURE YOU THAT MY FIRST LECTURE WILL BE A VERY BRIEF I AM DELIGHTED TO BE HERE AND I'M PARTICULARLY DELIGHTED TO BE HERE ON THIS OCCASION WE MEED AT A COLLEGE NOTED FOR KNOWLEGE IN A CITY NOTED FOR PROGRESS IN A STATE NOTED FOR STRAINTH AN WE STAND IN NEED OF ALL THREE"}
+```
+
+The general process for using a model and processor for automatic speech recognition is:
+
+1. Instantiate a processor (which regroups a feature extractor for input processing and a tokenizer for decoding) and a model from the checkpoint name.
+2. Process the audio signal and text with a processor.
+3. Pass the input through the model and take the `argmax` to retrieve the predicted text.
+4. Decode the text with a tokenizer to obtain the transcription.
+
+<frameworkcontent>
+<pt>
+```py
+>>> from transformers import AutoProcessor, AutoModelForCTC
+>>> from datasets import load_dataset
+>>> import torch
+
+>>> dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
+>>> dataset = dataset.sort("id")
+>>> sampling_rate = dataset.features["audio"].sampling_rate
+
+>>> processor = AutoProcessor.from_pretrained("facebook/wav2vec2-base-960h")
+>>> model = AutoModelForCTC.from_pretrained("facebook/wav2vec2-base-960h")
+
+>>> inputs = processor(dataset[0]["audio"]["array"], sampling_rate=sampling_rate, return_tensors="pt")
+>>> with torch.no_grad():
+...     logits = model(**inputs).logits
+>>> predicted_ids = torch.argmax(logits, dim=-1)
+
+>>> transcription = processor.batch_decode(predicted_ids)
+>>> transcription[0]
+```
+</pt>
+</frameworkcontent>
+
+## Image classification
+
+Like text and audio classification, image classification assigns a class to an image. The [CIFAR-100](https://huggingface.co/datasets/cifar100) dataset is an example dataset that can be used for image classification fine-tuning. It contains an image and the corresponding class. If you'd like to fine-tune a model for image classification, take a look at the [run_image_classification.py](https://github.com/huggingface/transformers/blob/main/examples/pytorch/image-classification/run_image_classification.py) script or this [how-to guide](./tasks/image_classification).
+
+The following examples demonstrate how to use a [`pipeline`] and a model and tokenizer for image classification inference:
+
+```py
+>>> from transformers import pipeline
+
+>>> vision_classifier = pipeline(task="image-classification")
+>>> vision_classifier(
+...     images="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
+... )
+[{'label': 'lynx, catamount', 'score': 0.4403027892112732},
+ {'label': 'cougar, puma, catamount, mountain lion, painter, panther, Felis concolor',
+  'score': 0.03433405980467796},
+ {'label': 'snow leopard, ounce, Panthera uncia',
+  'score': 0.032148055732250214},
+ {'label': 'Egyptian cat', 'score': 0.02353910356760025},
+ {'label': 'tiger cat', 'score': 0.023034192621707916}]
+```
+
+The general process for using a model and feature extractor for image classification is:
+
+1. Instantiate a feature extractor and a model from the checkpoint name.
+2. Process the image to be classified with a feature extractor.
+3. Pass the input through the model and take the `argmax` to retrieve the predicted class.
+4. Convert the class id to a class name with `id2label` to return an interpretable result.
+
+<frameworkcontent>
+<pt>
+```py
+>>> from transformers import AutoFeatureExtractor, AutoModelForImageClassification
+>>> import torch
+>>> from datasets import load_dataset
+
+>>> dataset = load_dataset("huggingface/cats-image")
+>>> image = dataset["test"]["image"][0]
+
+>>> feature_extractor = AutoFeatureExtractor.from_pretrained("google/vit-base-patch16-224")
+>>> model = AutoModelForImageClassification.from_pretrained("google/vit-base-patch16-224")
+
+>>> inputs = feature_extractor(image, return_tensors="pt")
+
+>>> with torch.no_grad():
+...     logits = model(**inputs).logits
+
+>>> predicted_label = logits.argmax(-1).item()
+>>> print(model.config.id2label[predicted_label])
+Egyptian cat
+```
+</pt>
+</frameworkcontent>