test both cer and wer

eval_cer.py

@@ -140,4 +140,35 @@ class CER(evaluate.Metric):
             incorrect += measures["substitutions"] + measures["deletions"] + measures["insertions"]
             total += measures["substitutions"] + measures["deletions"] + measures["hits"]
 
-        return incorrect / total
+        return incorrect / total
+
+@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
+class WER(evaluate.Metric):
+    def _info(self):
+        return evaluate.MetricInfo(
+            description=_DESCRIPTION,
+            citation=_CITATION,
+            inputs_description=_KWARGS_DESCRIPTION,
+            features=datasets.Features(
+                {
+                    "predictions": datasets.Value("string", id="sequence"),
+                    "references": datasets.Value("string", id="sequence"),
+                }
+            ),
+            codebase_urls=["https://github.com/jitsi/jiwer/"],
+            reference_urls=[
+                "https://en.wikipedia.org/wiki/Word_error_rate",
+            ],
+        )
+
+    def _compute(self, predictions=None, references=None, concatenate_texts=False):
+        if concatenate_texts:
+            return compute_measures(references, predictions)["wer"]
+        else:
+            incorrect = 0
+            total = 0
+            for prediction, reference in zip(predictions, references):
+                measures = compute_measures(reference, prediction)
+                incorrect += measures["substitutions"] + measures["deletions"] + measures["insertions"]
+                total += measures["substitutions"] + measures["deletions"] + measures["hits"]
+            return incorrect / total