Update app.py

app.py

@@ -1,23 +1,53 @@
 import torch
 from transformers import pipeline
 import gradio as gr
+# Import the necessary libraries
+import torch
+from transformers import pipeline
+import gradio as gr
+import whisper
+
+# Load the Whisper model for transcription
+whisper_model = whisper.load_model("base")
+
+# Load the emotion recognition pipeline
+emotion_recognition = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", return_all_scores=True)
 
-# Load the sentiment analysis pipeline with a specified model
-sentiment_analysis = pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english")
+# Function to transcribe audio
+def transcribe_audio(audio_file):
+    result = whisper_model.transcribe(audio_file)
+    return result["text"]
 
-# Define a simple Gradio interface function
-def simple_sentiment_analysis(text):
-    sentiment = sentiment_analysis(text)
-    return sentiment[0]['label']
+# Function to transcribe audio and recognize emotions
+def transcribe_and_recognize_emotions(audio_file):
+    # Transcribe audio
+    transcription = transcribe_audio(audio_file)
+
+    # Recognize emotions of the transcribed text
+    emotions = emotion_recognition(transcription)
+
+    # Extract the emotion with the highest score
+    dominant_emotion = max(emotions[0], key=lambda x: x['score'])['label']
+
+    return transcription, dominant_emotion
+
+# Define the Gradio interface function
+def gradio_transcription_emotion_interface(audio):
+    transcription, emotion = transcribe_and_recognize_emotions(audio)
+    return transcription, emotion
 
 # Set up Gradio Interface
 iface = gr.Interface(
-    fn=simple_sentiment_analysis,
-    inputs=gr.Textbox(lines=2, placeholder="Enter text here..."),
-    outputs=gr.Label(label="Sentiment"),
-    title="Sentiment Analysis",
-    description="Enter text to analyze its sentiment."
+    fn=gradio_transcription_emotion_interface,
+    inputs=gr.Audio(type="filepath"),
+    outputs=[
+        gr.Textbox(label="Transcription"),
+        gr.Label(label="Dominant Emotion")
+    ],
+    title="Audio Transcription and Emotion Recognition",
+    description="Upload or record an audio file to get the transcription and recognize its dominant emotion."
 )
 
-# Launch the interface with share=True for public access
+# Deploy the interface
 iface.launch(debug=True)
+