Update README.md

README.md

@@ -49,8 +49,8 @@ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 
 test_dataset = load_dataset("common_voice", "pt", split="test[:2%]") 
 
-processor = Wav2Vec2Processor.from_pretrained("joorock12/wav2vec2-large-xlsr-53-portuguese")
-model = Wav2Vec2ForCTC.from_pretrained("joorock12/wav2vec2-large-xlsr-53-portuguese")
+processor = Wav2Vec2Processor.from_pretrained("joorock12/wav2vec2-large-xlsr-portuguese")
+model = Wav2Vec2ForCTC.from_pretrained("joorock12/wav2vec2-large-xlsr-portuguese")
 
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
@@ -89,11 +89,11 @@ import re
 test_dataset = load_dataset("common_voice", "pt", split="test")
 wer = load_metric("wer")
 
-processor = Wav2Vec2Processor.from_pretrained("joorock12/wav2vec2-large-xlsr-53-portuguese")
-model = Wav2Vec2ForCTC.from_pretrained("joorock12/wav2vec2-large-xlsr-53-portuguese")
+processor = Wav2Vec2Processor.from_pretrained("joorock12/wav2vec2-large-xlsr-portuguese")
+model = Wav2Vec2ForCTC.from_pretrained("joorock12/wav2vec2-large-xlsr-portuguese")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“]'
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\'\�]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 # Preprocessing the datasets.