Update README.md

README.md

@@ -170,6 +170,7 @@ import torchaudio
 from datasets import load_dataset, load_metric
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import re
+
 ENCODER = {
     "ia ": "iê ",
     "ìa ": "iề ",
@@ -272,15 +273,16 @@ ENCODER = {
     "ưỡ": "\xa6",
     "ượ": "\xa7",
 }
-  
+
 def decode_string(x):
   for k, v in list(reversed(list(ENCODER.items()))):
     x = x.replace(v, k)
   return x
+
 test_dataset = load_dataset("common_voice", "vi", split="test")
 wer = load_metric("wer")
-processor = Wav2Vec2Processor.from_pretrained(MODEL)
-model = Wav2Vec2ForCTC.from_pretrained(MODEL)
+processor = Wav2Vec2Processor.from_pretrained("Nhut/wav2vec2-large-xlsr-vietnamese")
+model = Wav2Vec2ForCTC.from_pretrained("Nhut/wav2vec2-large-xlsr-vietnamese")
 model.to("cuda")
 
 chars_to_ignore_regex = '[\\\+\@\ǀ\,\?\.\!\-\;\:\"\“\%\‘\”\�]'
@@ -294,7 +296,7 @@ def speech_file_to_array_fn(batch):
   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):
@@ -306,6 +308,7 @@ def evaluate(batch):
   # decode_string: We replace the encoded letter with the initial letters
   batch["pred_strings"] = [decode_string(x) for x in batch["pred_strings"]]
   return 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"])))
 ```