Update README.md

README.md

@@ -1,5 +1,5 @@
 ---
-language: {tt}
+language: tt
 datasets:
 - common_voice
 metrics:
@@ -11,19 +11,19 @@ tags:
 - xlsr-fine-tuning-week
 license: apache-2.0
 model-index:
-- name: {Tatar XLSR Wav2Vec2 Large 53}
-results:
-- task:
-name: Speech Recognition
-type: automatic-speech-recognition
-dataset:
-name: Common Voice {tt}
-type: common_voice
-args: {tt}
-metrics:
-- name: Test WER
-type: wer
-value: {30.93}
+- name: Tatar XLSR Wav2Vec2 Large 53
+  results:
+  - task: 
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice tt
+      type: common_voice
+      args: tt
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 30.93
 ---
 
 # Wav2Vec2-Large-XLSR-53-Tatar
@@ -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
+	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():
-logits = 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)
 
@@ -93,24 +93,24 @@ 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"] = 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
+	batch["sentence"] = 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
 
 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)
+	inputs = 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
+	with torch.no_grad():
+		logits = 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
+	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)
 
@@ -122,4 +122,4 @@ print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"],
 
 ## Training
 
-The Common Voice `train` and `validation` datasets were used for training.
+The Common Voice `train` and `validation` datasets were used for training.