update model card

README.md

@@ -26,12 +26,12 @@ from datasets import load_dataset
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 
 model_name = "elgeish/wav2vec2-base-timit-asr"
-processor = Wav2Vec2Processor.from_pretrained(model_name, do_lower_case=True)
+processor = Wav2Vec2Processor.from_pretrained(model_name)
 model = Wav2Vec2ForCTC.from_pretrained(model_name)
 model.eval()
 
 dataset = load_dataset("timit_asr", split="test").shuffle().select(range(10))
-char_translations = str.maketrans({"-": " ", ".": "", "?": ""})
+char_translations = str.maketrans({"-": " ", ",": "", ".": "", "?": ""})
 
 def prepare_example(example):
     example["speech"], _ = sf.read(example["file"])
@@ -47,6 +47,7 @@ with torch.no_grad():
     predicted_ids = torch.argmax(model(inputs.input_values).logits, dim=-1)
 predicted_ids[predicted_ids == -100] = processor.tokenizer.pad_token_id  # see fine-tuning script
 predicted_transcripts = processor.tokenizer.batch_decode(predicted_ids)
+
 for reference, predicted in zip(dataset["text"], predicted_transcripts):
     print("reference:", reference)
     print("predicted:", predicted)