Update README.md

README.md

@@ -24,7 +24,7 @@ model-index:
          value: ???
 ---
 
-# Wav2Vec2-Large-XLSR-53-Hungarian
+# Wav2Vec2-Large-XLSR-53-Finnish
 
 Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Finnish using the [Common Voice](https://huggingface.co/datasets/common_voice)
 When using this model, make sure that your speech input is sampled at 16kHz.
@@ -49,15 +49,15 @@ 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)
 
@@ -85,41 +85,42 @@ processor = Wav2Vec2Processor.from_pretrained("birgermoell/wav2vec2-large-xlsr-f
 model = Wav2Vec2ForCTC.from_pretrained("birgermoell/wav2vec2-large-xlsr-finnish")
 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"] = 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"] = 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
+\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
+\treturn batch
 
 result = test_dataset.map(evaluate, batched=True, batch_size=8)
 
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 ```
 
-**Test Result**: ???
-
+**Test Result**:
+The WER is 55.097365
 
 ## Training
 
 The Common Voice `train` and `validation` datasets were used for training.
-The script used for training can be found ???
+The script used for training can be found here
+https://colab.research.google.com/drive/16AyzqMWU_aWNe3IA-NxrhskB1WLPHG-Q?usp=sharing