Update app.py

app.py

@@ -16,18 +16,18 @@ from collections import Counter
 device = torch.device("cpu")
 processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
 model = Wav2Vec2ForSequenceClassification.from_pretrained("facebook/wav2vec2-base-960h", num_labels=2).to(device)
-# model_path = "dysarthria_classifier12.pth"
-# model_path = 'model_weights2.pth'
-model_path = '/home/user/app/dysarthria_classifier12.pth'
+model_path = "dysarthria_classifier12.pth"
+# model_path = '/home/user/app/dysarthria_classifier12.pth'
+model.load_state_dict(torch.load(model_path, map_location=torch.device('cpu')))
 
-if os.path.exists(model_path):
-    print(f"Loading saved model {model_path}")
-    model.load_state_dict(torch.load(model_path, map_location=torch.device('cpu')))
+# if os.path.exists(model_path):
+#     print(f"Loading saved model {model_path}")
+#     model.load_state_dict(torch.load(model_path))
 
 
-title = "Upload an mp3 file for supranuclear palsy (SP) detection! (Thai Language)"
+title = "Upload an mp3 file for parkinsons detection! (Thai Language)"
 description = """
-The model was trained on Thai audio recordings with the following sentences, so submit audio recordings for one of these sentences:\n
+The model was trained on Thai audio recordings with the following sentences: \n
 ชาวไร่ตัดต้นสนทำท่อนซุง\n
 ปูม้าวิ่งไปมาบนใบไม้ (เน้นใช้ริมฝีปาก)\n
 อีกาคอยคาบงูคาบไก่ (เน้นใช้เพดานปาก)\n
@@ -39,7 +39,13 @@ The model was trained on Thai audio recordings with the following sentences, so
 <img src="https://huggingface.co/spaces/course-demos/Rick_and_Morty_QA/resolve/main/rick.png" width=200px>
 """
 
-def actualpredict(file_path):
+
+
+
+
+def predict(file_path):
+    max_length = 100000
+
     model.eval()
     with torch.no_grad():
         wav_data, _ = sf.read(file_path.name)
@@ -56,44 +62,15 @@ def actualpredict(file_path):
         logits = model(**inputs).logits
         logits = logits.squeeze()
         predicted_class_id = torch.argmax(logits, dim=-1).item()
-    return predicted_class_id
-
-
-def predict(file_upload):
-    
-    max_length = 100000
-    warn_output = " "
-    ans = " "
-    # file_path = file_upload
-    # if (microphone is not None) and (file_upload is not None):
-    #     warn_output = (
-    #         "WARNING: You've uploaded an audio file and used the microphone. "
-    #         "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
-    #     )
-
-    # elif (microphone is None) and (file_upload is None):
-    #     return "ERROR: You have to either use the microphone or upload an audio file"
-    # if(microphone is not None):
-    #     file_path = microphone
-    # if(file_upload is not None):
-    #     file_path = file_upload
 
-    predicted_class_id = actualpredict(file_upload)
-    if(predicted_class_id==0):
-        ans = "no_parkinson"
-    else:
-        ans = "parkinson"
     return predicted_class_id
 gr.Interface(
     fn=predict,
-    inputs=[
-        gr.inputs.Audio(source="upload", type="filepath", optional=True),
-    ],
+    inputs="file",
     outputs="text",
     title=title,
     description=description,
 ).launch()
 
-        # gr.inputs.Audio(source="microphone", type="filepath", optional=True),
 # iface = gr.Interface(fn=predict, inputs="file", outputs="text")
 # iface.launch()