Wordinfolost

---
name: wordinfolost
description: Compute the WordInfoLost metric — provided by torchmetrics. Use when the user has predictions and ground-truth and needs to compute WordInfoLost, or asks how to score with WordInfoLost.
metadata:
  skill_kind: metric
  source_lib: torchmetrics
  import_path: torchmetrics.WordInfoLost
  source: library_introspection
---

# wordinfolost

> Metric `WordInfoLost` from `torchmetrics` (torchmetrics.WordInfoLost)

## When to invoke this skill

The user has predictions + ground truth and asks to evaluate with WordInfoLost, or
mentions `torchmetrics.WordInfoLost` directly, or wants the standard torchmetrics implementation.

## Reference signature

```python
from torchmetrics import WordInfoLost

# _WordInfoLost(**kwargs: Any) -> None
```

## Library docstring

```
Wrapper for deprecated import.

>>> preds = ["this is the prediction", "there is an other sample"]
>>> target = ["this is the reference", "there is another one"]
>>> wil = _WordInfoLost()
>>> wil(preds, target)
tensor(0.6528)
```

## Quick recipe

```python
import torchmetrics as _m
score = _m.WordInfoLost(y_true, y_pred)
```

## Don'ts

- Don't reimplement when the library version handles edge cases (NaN, ties, empty inputs) better than a hand-rolled formula.
- Always check the library version's argument order — sklearn is `(y_true, y_pred)` while torchmetrics is `(preds, target)`.