upd readme

README.md

@@ -48,15 +48,15 @@ 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)
 
@@ -92,30 +92,30 @@ resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # We need to read the aduio files as arrays
 # Note: this models is trained ignoring accents on letters as below
 def speech_file_to_array_fn(batch):
-\\tbatch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower().strip()
-\\tbatch["sentence"] = re.sub(re.compile('[äá]'), 'a', batch['sentence'])
-\\tbatch["sentence"] = re.sub(re.compile('[öó]'), 'o', batch['sentence'])
-\\tbatch["sentence"] = re.sub(re.compile('[èé]'), 'e', batch['sentence'])
-\\tbatch["sentence"] = re.sub(re.compile("[ïí]"), 'i', batch['sentence'])
-\\tbatch["sentence"] = re.sub(re.compile("[üů]"), 'u', batch['sentence'])
-\\tbatch['sentence'] = re.sub('  ', ' ', batch['sentence'])
-\\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().strip()
+    batch["sentence"] = re.sub(re.compile('[äá]'), 'a', batch['sentence'])
+    batch["sentence"] = re.sub(re.compile('[öó]'), 'o', batch['sentence'])
+    batch["sentence"] = re.sub(re.compile('[èé]'), 'e', batch['sentence'])
+    batch["sentence"] = re.sub(re.compile("[ïí]"), 'i', batch['sentence'])
+    batch["sentence"] = re.sub(re.compile("[üů]"), 'u', batch['sentence'])
+    batch['sentence'] = re.sub('  ', ' ', 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)