Upload app.py

app.py

@@ -0,0 +1,153 @@
+import os
+from fastai.vision.all import *
+import gradio as gr
+import pickle
+import tempfile
+from transformers import AutoTokenizer, AutoModelWithLMHead
+from speechbrain.inference.interfaces import foreign_class
+
+
+
+# Facial expression classifier
+
+# Emotion
+learn_emotion = load_learner('emotions_vgg19.pkl')
+learn_emotion_labels = learn_emotion.dls.vocab
+
+
+# Predict
+def predict(img):
+    img = PILImage.create(img)
+    pred_emotion, pred_emotion_idx, probs_emotion = learn_emotion.predict(img)
+    predicted_emotion = learn_emotion_labels[pred_emotion_idx]
+    return predicted_emotion
+
+
+# Gradio
+title = "Facial Emotion Detector"
+
+description = gr.Markdown(
+                """Ever wondered what a person might be feeling looking at their picture?
+                 Well, now you can! Try this fun app. Just upload a facial image in JPG or
+                 PNG format. You can now see what they might have felt when the picture
+                 was taken.
+
+                 **Tip**: Be sure to only include face to get best results. Check some sample images
+                 below for inspiration!""").value
+
+article = gr.Markdown(
+             """**DISCLAIMER:** This model does not reveal the actual emotional state of a person. Use and
+             interpret results at your own risk!. 
+
+             **PREMISE:** The idea is to determine an overall emotion of a person
+             based on the pictures. We are restricting pictures to only include close-up facial
+             images.
+
+             **DATA:** FER2013 dataset consists of 48x48 pixel grayscale images of faces.Images
+             are assigned one of the 7 emotions: Angry, Disgust, Fear, Happy, Sad, Surprise, and Neutral.
+             
+              """).value
+
+enable_queue=True
+
+examples = ['happy1.jpg', 'happy2.jpg', 'angry1.png', 'angry2.jpg', 'neutral1.jpg', 'neutral2.jpg']
+
+image_mode=gr.Interface(fn = predict, 
+             inputs = gr.Image( image_mode='L'), 
+             outputs = [gr.Label(label='Emotion')], #gr.Label(),
+             title = title,
+             examples = examples,
+             description = description,
+             article=article,
+             allow_flagging='never')
+
+
+
+
+# Txet Model
+
+# Load tokenizer and model from pickles
+with open("emotion_tokenizer.pkl", "rb") as f:
+    tokenizer = pickle.load(f)
+
+with open("emotion_model.pkl", "rb") as f:
+    model = pickle.load(f)
+
+
+
+def classify_emotion(text):
+    # Tokenize input text and generate output
+    input_ids = tokenizer.encode("emotion: " + text, return_tensors="pt")
+    output = model.generate(input_ids)
+    output_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    
+    # Classify the emotion into positive, negative, or neutral
+    if output_text in ["joy", "love"]:
+        return "Positive"
+    elif output_text == "surprise":
+        return "Neutral"
+    else:
+        return "Negative"
+    return output_text
+
+
+text_model = gr.Interface(fn=classify_emotion, inputs="textbox", outputs="textbox")
+
+
+
+
+
+
+
+
+
+# Initialize the classifier
+classifier = foreign_class(source="speechbrain/emotion-recognition-wav2vec2-IEMOCAP", pymodule_file="custom_interface.py", classname="CustomEncoderWav2vec2Classifier")
+
+def save_uploaded_file(uploaded_file):
+    temp_dir = tempfile.TemporaryDirectory()
+    file_path = os.path.join(temp_dir.name, uploaded_file.name)
+    with open(file_path, "wb") as f:
+        f.write(uploaded_file.getbuffer())
+    return file_path
+
+
+def emotion(file_path):
+   
+    if file_path:
+        # Classify the file
+        out_prob, score, index, text_lab = classifier.classify_file(file_path)
+        if isinstance(text_lab, list):
+            text_lab = text_lab[0]
+        # Map the original labels to the desired categories
+        emotion_mapping = {
+            'neu': 'Neutral',
+            'ang': 'Angry',
+            'hap': 'Happy',
+            'sad': 'Sadness'
+        }
+        # Get the corresponding category from the mapping
+        emotion_category = emotion_mapping.get(text_lab, 'Unknown')
+        
+        emotion_category = emotion_mapping.get(text_lab, 'Unknown')
+        # Return the emotion category
+        return emotion_category
+    else:
+        return "Please provide the path to an audio file."
+
+
+
+
+
+audio_model = gr.Interface(fn=emotion, inputs="textbox", outputs="textbox")
+
+
+
+
+
+
+
+main_model = gr.TabbedInterface([text_model, image_mode,audio_model], ["Text Emotion Recognition", "Image Emotion Recognition" , "Audio Emotion Recognition"])
+
+if _name_ == "_main_":
+ main_model.launch()