Update README.md

README.md

@@ -62,6 +62,7 @@ inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tens
 with torch.no_grad():
 	logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
 
+
 predicted_ids = torch.argmax(logits, dim=-1)
 
 print("Prediction:", processor.batch_decode(predicted_ids))
@@ -88,7 +89,7 @@ processor = Wav2Vec2Processor.from_pretrained("shahukareem/wav2vec2-large-xlsr-5
 model = Wav2Vec2ForCTC.from_pretrained("shahukareem/wav2vec2-large-xlsr-53-dhivehi")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�\\\\،\\\\.\\\\؟\\\\!\\\\'\\\\"\\\\–\\\\’]'
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\،\.\؟\!\'\"\–\’]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 # Preprocessing the datasets.
@@ -104,14 +105,14 @@ 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)
+\tinputs = 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
+\twith torch.no_grad():
+\t\tlogits = 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
+\tpred_ids = torch.argmax(logits, dim=-1)
+\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
+\treturn batch
 
 result = test_dataset.map(evaluate, batched=True, batch_size=8)
 
@@ -124,15 +125,16 @@ print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"],
 The Common Voice `train` and `validation` datasets were used for training.
 
 ## Example predictions
+
 reference: ކަރަންޓް ވައިރުކޮށް ބޮކި ހަރުކުރުން
 predicted: ކަރަންޓް ވައިރުކޮށް ބޮކި ހަރުކުރުން
---
+--\
 reference: ދެން އެކުދިންނާ ދިމާއަށް އަތް ދިށްކޮށްލެވެ
 predicted: ދެން އެކުދިންނާ ދިމާއަށް އަތް ދިއްކޮށްލެވެ ް
---
+--\
 reference: ރަކި ހިނިތުންވުމަކާއެކު އޭނާ އަމިއްލައަށް ތައާރަފްވި
 predicted: ރަކި ހިނިތުންވުމަކާއެކު އޭނާ އަމިއްލައަށް ތައަރަފްވި
---
+--\
 reference: ކޮޓަރީގެ ކުޑަދޮރުން ބޭރު ބަލަހައްޓައިގެން އިން ރޫނާގެ މޫނުމަތިން ފާޅުވަމުން ދިޔައީ ކަންބޮޑުވުމުގެ އަސަރުތައް
 predicted: ކޮޓަރީގެ ކުޑަދޮރުން ބޭރު ބަލަހައްޓައިގެން އިން ރނާގެ މޫނުމަތިން ފާޅުވަމުން ދިޔައީ ކަންބޮޑުވުމުގެ އަސަރުތައް
---
+--\