eval code was not working

README.md

@@ -43,7 +43,7 @@ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 test_dataset = load_dataset("common_voice", "de", split="test[:2%]") 
 
 processor = Wav2Vec2Processor.from_pretrained("marcel/wav2vec2-large-xlsr-german-demo")
-model = Wav2Vec2ForCTC.from_pretrained("marcel/wav2vec2-large-xlsr-german-demo")
+model = Wav2Vec2ForCTC.from_pretrained("marcel/wav2vec2-large-xlsr-german-demo") 
 
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
@@ -79,61 +79,61 @@ from datasets import load_dataset, load_metric
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import re
 
-test_dataset = load_dataset("common_voice", "de", split="test") [this](https://huggingface.co/languages) site.
+test_dataset = load_dataset("common_voice", "de", split="test[:10%]")
 wer = load_metric("wer")
 
-processor = Wav2Vec2Processor.from_pretrained('marcel/wav2vec2-large-xlsr-53-german-demo')
-model = Wav2Vec2ForCTC.from_pretrained('marcel/wav2vec2-large-xlsr-53-german-demo') 
+processor = Wav2Vec2Processor.from_pretrained("marcel/wav2vec2-large-xlsr-german-demo")
+model = Wav2Vec2ForCTC.from_pretrained("marcel/wav2vec2-large-xlsr-german-demo") 
 model.to("cuda")
 
 chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\”\�\カ\æ\無\ན\カ\臣\ѹ\…\«\»\ð\ı\„\幺\א\ב\比\ш\ע\)\ứ\в\œ\ч\+\—\ш\‚\נ\м\ń\乡\$\=\ש\ф\支\(\°\и\к\̇]'
 substitutions = {
-	'e' : '[\ə\é\ě\ę\ê\ế\ế\ë\ė\е]',
-	'o' : '[\ō\ô\ô\ó\ò\ø\ọ\ŏ\õ\ő\о]',
-	'a' : '[\á\ā\ā\ă\ã\å\â\à\ą\а]',
-	'c' : '[\č\ć\ç\с]',
-	'l' : '[\ł]',
-	'u' : '[\ú\ū\ứ\ů]',
-	'und' : '[\&]',
-	'r' : '[\ř]',
-	'y' : '[\ý]',
-	's' : '[\ś\š\ș\ş]',
-	'i' : '[\ī\ǐ\í\ï\î\ï]',
-	'z' : '[\ź\ž\ź\ż]',
-	'n' : '[\ñ\ń\ņ]',
-	'g' : '[\ğ]',
-	'ss' : '[\ß]',
-	't' : '[\ț\ť]',
-	'd' : '[\ď\đ]',
-	"'": '[\ʿ\་\’\`\´\ʻ\`\‘]',
-	'p': '\р'
+    'e' : '[\ə\é\ě\ę\ê\ế\ế\ë\ė\е]',
+    'o' : '[\ō\ô\ô\ó\ò\ø\ọ\ŏ\õ\ő\о]',
+    'a' : '[\á\ā\ā\ă\ã\å\â\à\ą\а]',
+    'c' : '[\č\ć\ç\с]',
+    'l' : '[\ł]',
+    'u' : '[\ú\ū\ứ\ů]',
+    'und' : '[\&]',
+    'r' : '[\ř]',
+    'y' : '[\ý]',
+    's' : '[\ś\š\ș\ş]',
+    'i' : '[\ī\ǐ\í\ï\î\ï]',
+    'z' : '[\ź\ž\ź\ż]',
+    'n' : '[\ñ\ń\ņ]',
+    'g' : '[\ğ]',
+    'ss' : '[\ß]',
+    't' : '[\ț\ť]',
+    'd' : '[\ď\đ]',
+    "'": '[\ʿ\་\’\`\´\ʻ\`\‘]',
+    'p': '\р'
 }
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
 def speech_file_to_array_fn(batch):
-	batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
-	for x in substitutions:
-		batch["sentence"] = re.sub(substitutions[x], x, batch["sentence"])
-		speech_array, sampling_rate = torchaudio.load(batch["path"])
-	speech_array, sampling_rate = torchaudio.load(batch["path"])
-	batch["speech"] = resampler(speech_array).squeeze().numpy()
-	return batch
+    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
+    for x in substitutions:
+        batch["sentence"] = re.sub(substitutions[x], x, batch["sentence"])
+        speech_array, sampling_rate = torchaudio.load(batch["path"])
+    speech_array, sampling_rate = torchaudio.load(batch["path"])
+    batch["speech"] = resampler(speech_array).squeeze().numpy()
+    return batch
 
 test_dataset = test_dataset.map(speech_file_to_array_fn)
 
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
 def evaluate(batch):
-	inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+    inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
 
-	with torch.no_grad():
-		logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
+    with torch.no_grad():
+        logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
 
-	pred_ids = torch.argmax(logits, dim=-1)
-	batch["pred_strings"] = processor.batch_decode(pred_ids)
-	return batch
+    pred_ids = torch.argmax(logits, dim=-1)
+    batch["pred_strings"] = processor.batch_decode(pred_ids)
+    return batch
 
 result = test_dataset.map(evaluate, batched=True, batch_size=8)