Update README.md

README.md

@@ -30,7 +30,7 @@ model-index:
 
 # Wav2Vec2-Large-XLSR-53-khmer 
 
-Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Khmer using the [Common Voice](https://huggingface.co/datasets/common_voice), and [OpenSLR Kh](http://www.openslr.org/43/). 
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Khmer using the [Common Voice](https://huggingface.co/datasets/common_voice), and [OpenSLR Kh](http://www.openslr.org/42/). 
 
 When using this model, make sure that your speech input is sampled at 16kHz.
 
@@ -44,12 +44,12 @@ import torchaudio
 from datasets import load_dataset
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 
-!wget https://www.openslr.org/resources/43/km_kh_male.zip
+!wget https://www.openslr.org/resources/42/km_kh_male.zip
 !unzip km_kh_male.zip
 !ls km_kh_male
 
 colnames=['path','sentence'] 
-df  = pd.read_csv('/content/km_kh_male/line_index.tsv',sep='\\\\\\\\\\\\\\\\t',header=None,names = colnames)
+df  = pd.read_csv('/content/km_kh_male/line_index.tsv',sep='\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\t',header=None,names = colnames)
 df['path'] = '/content/km_kh_male/wavs/'+df['path'] +'.wav'
 
 train, test = train_test_split(df, test_size=0.1)
@@ -66,15 +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
+\\\\\\\\\\\\\\\\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)
 
@@ -103,13 +103,17 @@ from sklearn.model_selection import train_test_split
 import pandas as pd
 from datasets import load_dataset
 
-#!wget https://www.openslr.org/resources/43/ne_np_female.zip
-#!unzip ne_np_female.zip
-#!ls ne_np_female
-!mkdir cer
-!wget -O cer/cer.py https://huggingface.co/ctl/wav2vec2-large-xlsr-cantonese/raw/main/cer.py
+!wget https://www.openslr.org/resources/42/km_kh_male.zip
+!unzip km_kh_male.zip
+!ls km_kh_male
 
+colnames=['path','sentence'] 
+df  = pd.read_csv('/content/km_kh_male/line_index.tsv',sep='\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\t',header=None,names = colnames)
+df['path'] = '/content/km_kh_male/wavs/'+df['path'] +'.wav'
 
+train, test = train_test_split(df, test_size=0.1)
+
+test.to_csv('/content/km_kh_male/line_index_test.csv')
 
 test_dataset = load_dataset('csv', data_files='/content/km_kh_male/line_index_test.csv',split = 'train')
 wer = load_metric("wer")
@@ -120,30 +124,30 @@ processor = Wav2Vec2Processor.from_pretrained("gagan3012/wav2vec2-xlsr-khmer")
 model = Wav2Vec2ForCTC.from_pretrained("gagan3012/wav2vec2-xlsr-khmer") 
 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):
-\tbatch["text"] = re.sub(chars_to_ignore_regex, '', batch["text"]).lower()
-\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
-\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
-\treturn batch
+\\tbatch["text"] = re.sub(chars_to_ignore_regex, '', batch["text"]).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):
-\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
 
 cer = load_metric("cer")