How to implement a custom Pytorch Dataset with map() method

Many of the Pytorch examples use the Dataset map() method. For example:

https://huggingface.co/voidful/wav2vec2-large-xlsr-53-tw-gpt

ds = load_dataset("common_voice", 'zh-TW', split="test")
ds = ds.cast_column("audio", Audio(sampling_rate=16_000))
def map_to_array(batch):
    audio = batch["audio"]
    batch["speech"] = processor(audio["array"], sampling_rate=audio["sampling_rate"]).input_values[0]
    batch["sampling_rate"] = audio["sampling_rate"]
    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower().replace("’", "'")
    return batch
ds = ds.map(map_to_array)

def map_to_pred(batch):
    features = processor(batch["speech"], sampling_rate=batch["sampling_rate"][0], padding=True, return_tensors="pt")
    input_values = features.input_values.to(device)
    attention_mask = features.attention_mask.to(device)
    with torch.no_grad():
        logits = model(input_values, attention_mask=attention_mask).logits
    pred_ids = torch.argmax(logits, dim=-1)
    batch["predicted"] = processor.batch_decode(pred_ids)
    batch["target"] = batch["sentence"]
    return batch


result = ds.map(map_to_pred, batched=True, batch_size=3, remove_columns=list(ds.features.keys()))

However, implementing a custom Map style dataset only requires __len__() and __getitem__()

What is the correct way to convert a custom Dataset into one with all the useful methods needed by the examples?