Update README.md

README.md

@@ -79,6 +79,22 @@ import torchaudio
 from datasets import load_dataset, load_metric
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import re
+import jiwer
+
+def chunked_wer(targets, predictions, chunk_size=None):
+    if chunk_size is None: return jiwer.wer(targets, predictions)
+    start = 0
+    end = chunk_size
+    H, S, D, I = 0, 0, 0, 0
+    while start < len(targets):
+        chunk_metrics = jiwer.compute_measures(targets[start:end], predictions[start:end])
+        H = H + chunk_metrics["hits"]
+        S = S + chunk_metrics["substitutions"]
+        D = D + chunk_metrics["deletions"]
+        I = I + chunk_metrics["insertions"]
+        start += chunk_size
+        end += chunk_size
+    return float(S + D + I) / float(H + S + D)
 
 test_dataset = load_dataset("common_voice", "eo", split="test") #TODO: replace {lang_id} in your language code here. Make sure the code is one of the *ISO codes* of [this](https://huggingface.co/languages) site.
 wer = load_metric("wer")
@@ -87,7 +103,7 @@ processor = Wav2Vec2Processor.from_pretrained("cpierse/wav2vec2-large-xlsr-53-es
 model = Wav2Vec2ForCTC.from_pretrained("cpierse/wav2vec2-large-xlsr-53-esperanto")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“]' 
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\„\«\(\»\)\’\']' 
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 # Preprocessing the datasets.
@@ -114,7 +130,7 @@ def evaluate(batch):
 
 result = test_dataset.map(evaluate, batched=True, batch_size=8)
 
-print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
+print("WER: {:2f}".format(100 * chunked_wer(predictions=result["pred_strings"], targets=result["sentence"],chunk_size=2000)))
 ```
 
 **Test Result**: 14.36 %