Update README.md

README.md

@@ -11,7 +11,7 @@ tags:
 - xlsr-fine-tuning-week
 license: apache-2.0
 model-index:
-- name: (Anton Lozhkov) Russian XLSR Wav2Vec2 Large 53
+- name: Russian XLSR Wav2Vec2 Large 53 by Anton Lozhkov
   results:
   - task: 
       name: Speech Recognition
@@ -51,15 +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):
-	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)
 
@@ -90,36 +90,36 @@ model.to("cuda")
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 def clean_sentence(sent):
-	sent = sent.lower()
-	# replace non-alphanumeric characters with space ("какой-то, вот" -> "какой то  вот")
-	sent = "".join(ch if ch.isalnum() else " " for ch in sent)
-	# remove repeated spaces
-	sent = " ".join(sent.split())
-	# these letters are considered equivalent in written Russian
-	sent = sent.replace('ё', 'е')
-	return sent
+\tsent = sent.lower()
+\t# replace non-alphanumeric characters with space ("какой-то, вот" -> "какой то  вот")
+\tsent = "".join(ch if ch.isalnum() else " " for ch in sent)
+\t# remove repeated spaces
+\tsent = " ".join(sent.split())
+\t# these letters are considered equivalent in written Russian
+\tsent = sent.replace('ё', 'е')
+\treturn sent
 
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
 def speech_file_to_array_fn(batch):
-	batch["sentence"] = clean_sentence(batch["sentence"])
-	speech_array, sampling_rate = torchaudio.load(batch["path"])
-	batch["speech"] = resampler(speech_array).squeeze().numpy()
-	return batch
+\tbatch["sentence"] = clean_sentence(batch["sentence"])
+\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)