Update README.md

README.md

@@ -1,3 +1,4 @@
+---
 language: tr
 datasets:
 - common_voice 
@@ -51,15 +52,15 @@ 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):
-	speech_array, sampling_rate = torchaudio.load(batch["path"])
-	batch["speech"] = resampler(speech_array).squeeze().numpy()
-	return batch
+\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
+\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
+\treturn 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():
-	logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
+\tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
 
 predicted_ids = torch.argmax(logits, dim=-1)
 
@@ -87,30 +88,30 @@ processor = Wav2Vec2Processor.from_pretrained("aniltrkkn/wav2vec2-large-xlsr-53-
 model = Wav2Vec2ForCTC.from_pretrained("aniltrkkn/wav2vec2-large-xlsr-53-turkish")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“]'
 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"] = str(unicode_tr(re.sub(chars_to_ignore_regex, "", batch["sentence"])).lower())
-	speech_array, sampling_rate = torchaudio.load(batch["path"])
-	batch["speech"] = resampler(speech_array).squeeze().numpy()
-	return batch
+\tbatch["sentence"] = str(unicode_tr(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
 
 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)
 
@@ -123,16 +124,16 @@ print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"],
 unicode_tr package is used for converting sentences to lower case since regular lower() does not work well with Turkish.
 
 Since training data is very limited for Turkish, all data is employed with a K-Fold (k=5) training approach. Best model out of the 5 trainings is uploaded. Training arguments:
-    --num_train_epochs="30" \
-    --per_device_train_batch_size="32" \
-    --evaluation_strategy="steps" \
-    --activation_dropout="0.055" \
-    --attention_dropout="0.094" \
-    --feat_proj_dropout="0.04" \
-    --hidden_dropout="0.047" \
-    --layerdrop="0.041" \
-    --learning_rate="2.34e-4" \
-    --mask_time_prob="0.082" \
-    --warmup_steps="250" \
+    --num_train_epochs="30" \\
+    --per_device_train_batch_size="32" \\
+    --evaluation_strategy="steps" \\
+    --activation_dropout="0.055" \\
+    --attention_dropout="0.094" \\
+    --feat_proj_dropout="0.04" \\
+    --hidden_dropout="0.047" \\
+    --layerdrop="0.041" \\
+    --learning_rate="2.34e-4" \\
+    --mask_time_prob="0.082" \\
+    --warmup_steps="250" \\
 
 All trainings took ~20 hours with a GeForce RTX 3090 Graphics Card.