Update README.md

README.md

@@ -44,7 +44,19 @@ import torchaudio
 from datasets import load_dataset
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 
-test_dataset = load_dataset('csv', data_files='/content/ne_np_female/line_index_test.csv',split = 'test')
+!wget https://www.openslr.org/resources/43/ne_np_female.zip
+!unzip ne_np_female.zip
+!ls ne_np_female
+
+colnames=['path','sentence'] 
+df  = pd.read_csv('/content/ne_np_female/line_index.tsv',sep='\t',header=None,names = colnames)
+df['path'] = '/content/ne_np_female/wavs/'+df['path'] +'.wav'
+
+train, test = train_test_split(df, test_size=0.1)
+
+test.to_csv('/content/ne_np_female/line_index_test.csv')
+
+test_dataset = load_dataset('csv', data_files='/content/ne_np_female/line_index_test.csv',split = 'train')
 
 processor = Wav2Vec2Processor.from_pretrained("gagan3012/wav2vec2-xlsr-nepali")
 model = Wav2Vec2ForCTC.from_pretrained("gagan3012/wav2vec2-xlsr-nepali") 
@@ -54,15 +66,15 @@ 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)
 
@@ -88,37 +100,49 @@ from datasets import load_dataset, load_metric
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import re
 
-test_dataset = load_dataset('csv', data_files='/content/ne_np_female/line_index_test.csv',split = 'test')
+!wget https://www.openslr.org/resources/43/ne_np_female.zip
+!unzip ne_np_female.zip
+!ls ne_np_female
+
+colnames=['path','sentence'] 
+df  = pd.read_csv('/content/ne_np_female/line_index.tsv',sep='\t',header=None,names = colnames)
+df['path'] = '/content/ne_np_female/wavs/'+df['path'] +'.wav'
+
+train, test = train_test_split(df, test_size=0.1)
+
+test.to_csv('/content/ne_np_female/line_index_test.csv')
+
+test_dataset = load_dataset('csv', data_files='/content/ne_np_female/line_index_test.csv',split = 'train')
 wer = load_metric("wer")
 
 processor = Wav2Vec2Processor.from_pretrained("gagan3012/wav2vec2-xlsr-nepali")
 model = Wav2Vec2ForCTC.from_pretrained("gagan3012/wav2vec2-xlsr-nepali") 
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“]'  # TODO: adapt this list to include all special characters you removed from the data
+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):
-\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
+	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):
-\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)