Update README.md

README.md

@@ -21,7 +21,6 @@ CED are simple ViT-Transformer-based models for audio tagging. Notable differenc
 - **Demo:** https://huggingface.co/spaces/mispeech/ced-base
 
 ## Install
-
 ```bash
 git clone https://github.com/jimbozhang/hf_transformers_custom_model_ced.git
 pip install -r requirements.txt
@@ -32,20 +31,21 @@ pip install -r requirements.txt
 >>> from ced_model.feature_extraction_ced import CedFeatureExtractor
 >>> from ced_model.modeling_ced import CedForAudioClassification
 
->>> model_id = "mispeech/ced-tiny"
->>> feature_extractor = CedFeatureExtractor.from_pretrained(model_id)
->>> model = CedForAudioClassification.from_pretrained(model_id)
+>>> model_name = "mispeech/ced-tiny"
+>>> feature_extractor = CedFeatureExtractor.from_pretrained(model_name)
+>>> model = CedForAudioClassification.from_pretrained(model_name)
 
 >>> import torchaudio
 >>> audio, sampling_rate = torchaudio.load("resources/JeD5V5aaaoI_931_932.wav")
-
+>>> assert sampling_rate == 16000
 >>> inputs = feature_extractor(audio, sampling_rate=sampling_rate, return_tensors="pt")
+
+>>> import torch
 >>> with torch.no_grad():
 ...     logits = model(**inputs).logits
 
->>> import torch
->>> predicted_class_ids = torch.argmax(logits, dim=-1).item()
->>> model.config.id2label[predicted_class_ids]
+>>> predicted_class_id = torch.argmax(logits, dim=-1).item()
+>>> model.config.id2label[predicted_class_id]
 'Finger snapping'
 ```