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
+\\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():
-\tlogits = 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)
 
@@ -67,7 +67,7 @@ print("Reference:", test_dataset["sentence"][:2])
 
 ## Evaluation
 
-The model can be evaluated as follows on the {language} test data of Common Voice.  # TODO: replace #TODO: replace language with your {language}, *e.g.* French
+The model can be evaluated as follows on the Czech test data of Common Voice.
 
 
 ```python
@@ -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
+\\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
 
 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)
+\\tinputs = 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
+\\twith torch.no_grad():
+\\t\\tlogits = 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
+\\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)