Update: 사용 example 수정

README.md

@@ -41,6 +41,8 @@ Just using `load_metric("wer")` and `load_metric("wer")` in huggingface `dataset
 
 ## How to Get Started With the Model
 ```python
+import librosa
+from pyctcdecode import build_ctcdecoder
 from transformers import (
     AutoConfig,
     AutoFeatureExtractor,
@@ -49,16 +51,13 @@ from transformers import (
     Wav2Vec2ProcessorWithLM,
 )
 from transformers.pipelines import AutomaticSpeechRecognitionPipeline
-import librosa
+
+audio_path = ""
 
 # 모델과 토크나이저, 예측을 위한 각 모듈들을 불러옵니다.
-config = AutoConfig.from_pretrained(model_config_path)
-model = AutoModelForCTC.from_pretrained(
-    model_name_or_path,
-    config=config,
-)
-feature_extractor = AutoFeatureExtractor.from_pretrained(model_name_or_path)
-tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
+model = AutoModelForCTC.from_pretrained("42MARU/ko-spelling-wav2vec2-conformer-del-1s")
+feature_extractor = AutoFeatureExtractor.from_pretrained("42MARU/ko-spelling-wav2vec2-conformer-del-1s")
+tokenizer = AutoTokenizer.from_pretrained("42MARU/ko-spelling-wav2vec2-conformer-del-1s")
 beamsearch_decoder = build_ctcdecoder(
     labels=list(tokenizer.encoder.keys()),
     kenlm_model_path=None,