Update README.md

README.md

@@ -1,7 +1,6 @@
 ---
 language: ar
 datasets:
-- common_voice
 - common_voice: Common Voice Corpus 4
 metrics:
 - wer
@@ -52,15 +51,15 @@ 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):
-\\\\\\\\\\\\\\\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
-\\\\\\\\\\\\\\\\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
-\\\\\\\\\\\\\\\\treturn batch
+    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)
 inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
 
 with torch.no_grad():
-\\\\\\\\\\\\\\\\tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
+     logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
 
 predicted_ids = torch.argmax(logits, dim=-1)
 
@@ -87,31 +86,44 @@ processor = Wav2Vec2Processor.from_pretrained("anas/wav2vec2-large-xlsr-arabic")
 model = Wav2Vec2ForCTC.from_pretrained("anas/wav2vec2-large-xlsr-arabic/")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\“]'
+chars_to_ignore_regex = '[\,\؟\.\!\-\;\\:\'\"\☭\«\»\؛\—\ـ\_\،\“\%\‘\”\�]'
 
 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):
-\\\\\\\\\\\\\\\\tbatch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
-\\\\\\\\\\\\\\\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
-\\\\\\\\\\\\\\\\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
-\\\\\\\\\\\\\\\\treturn batch
+    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
+    batch["sentence"] = re.sub('[a-z]','',batch["sentence"])
+    batch["sentence"] = re.sub("[إأٱآا]", "ا", batch["sentence"])
+    noise = re.compile(""" ّ    | # Tashdid
+                             َ    | # Fatha
+                             ً    | # Tanwin Fath
+                             ُ    | # Damma
+                             ٌ    | # Tanwin Damm
+                             ِ    | # Kasra
+                             ٍ    | # Tanwin Kasr
+                             ْ    | # Sukun
+                             ـ     # Tatwil/Kashida
+                         """, re.VERBOSE)
+    batch["sentence"] = re.sub(noise, '', batch["sentence"])
+    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):
-\\\\\\\\\\\\\\\\tinputs = 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)
 
-\\\\\\\\\\\\\\\\twith torch.no_grad():
-\\\\\\\\\\\\\\\\t\\\\\\\\\\\\\\\\tlogits = 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
 
-\\\\\\\\\\\\\\\\tpred_ids = torch.argmax(logits, dim=-1)
-\\\\\\\\\\\\\\\\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
-\\\\\\\\\\\\\\\\treturn 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)