Compute akki2825/accents_unplugged_eval via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of akki2825/accents_unplugged_eval.
Installs into .claude/skills of the current project.
Are you the author of Akki2825 Accents Unplugged Eval?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/qhjqhj00-akki2825-accents-unplugged-eval)
---
name: akki2825-accents-unplugged-eval
description: Compute akki2825/accents_unplugged_eval via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of akki2825/accents_unplugged_eval.
metadata:
skill_kind: metric
source_lib: huggingface-evaluate
hf_module: akki2825/accents_unplugged_eval
source: library_introspection
---
# akki2825-accents-unplugged-eval
> Metric `akki2825/accents_unplugged_eval` from the HuggingFace `evaluate` library.
## When to invoke
User asks to compute `akki2825/accents_unplugged_eval` or wants HF evaluate's canonical version.
## Recipe
```python
import evaluate
metric = evaluate.load("akki2825/accents_unplugged_eval")
result = metric.compute(predictions=preds, references=refs)
print(result)
```
## Don'ts
- Don't assume your in-house `akki2825/accents_unplugged_eval` matches HF — version conventions vary.
- Many evaluate metrics have task-specific arguments (`average=`, `lang=`, `model_type=`); read the metric card before reporting numbers.
