update hubert classificaiton

app.py

@@ -330,15 +330,40 @@ import torch
 
 # if __name__ == "__main__":
 #     main()
-
+from transformers import Wav2Vec2FeatureExtractor, HubertForSequenceClassification
+import torch
+import soundfile as sf
+
+def load_audio(file_path):
+    # Load an audio file, return waveform and sampling rate
+    waveform, sample_rate = sf.read(file_path)
+    return waveform, sample_rate
+
+def prepare_dataset(data_paths):
+    # Dummy function to simulate loading and processing a dataset
+    # Replace this with actual data loading and processing logic
+    features = []
+    labels = []
+    for path, label in data_paths:
+        waveform, sr = load_audio(path)
+        input_values = feature_extractor(waveform, sampling_rate=sr, return_tensors="pt").input_values
+        features.append(input_values)
+        labels.append(label)
+    return torch.cat(features, dim=0), torch.tensor(labels)
+
+    
 def main():
     st.write("## Federated Learning with dynamic models and datasets for mobile devices")
     dataset_name = st.selectbox("Dataset", ["audio_instruction_task","imdb", "amazon_polarity", "ag_news"])
     model_name = st.selectbox("Model", ["facebook/hubert-base-ls960","bert-base-uncased", "distilbert-base-uncased"])
 
     # net = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2).to(DEVICE)
-    processor = Wav2Vec2Processor.from_pretrained(model_name)
+    # processor = Wav2Vec2Processor.from_pretrained(model_name)
+    # net = HubertForSequenceClassification.from_pretrained(model_name, num_labels=2).to(DEVICE)
+
+    feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_name)
     net = HubertForSequenceClassification.from_pretrained(model_name, num_labels=2).to(DEVICE)
+
     NUM_CLIENTS = st.slider("Number of Clients", min_value=1, max_value=10, value=2)
     NUM_ROUNDS = st.slider("Number of Rounds", min_value=1, max_value=10, value=3)