Update app.py

app.py

@@ -5,7 +5,7 @@ from transformers import pipeline
 sentiment_model = pipeline("sentiment-analysis")
 chatbot_model = pipeline("text-generation", model="microsoft/DialoGPT-medium")
 summarization_model = pipeline("summarization")
-text_to_speech_model = pipeline("text-to-speech")
+speech_to_text_model = pipeline("automatic-speech-recognition")
 
 # Sentiment Analysis Function
 def analyze_sentiment(text):
@@ -26,15 +26,22 @@ def summarize_text(text):
     summary = summarization_model(text, max_length=150, min_length=50, do_sample=False)
     return summary[0]["summary_text"]
 
-# Text-to-Speech Function
-def text_to_speech(text):
-    audio_output = text_to_speech_model(text)
-    return audio_output["audio"]
+# 4️⃣ Speech-to-Text (ASR) Function
+def transcribe_audio(mic=None, file=None):
+    if mic:
+        audio = mic
+    elif file:
+        audio = file
+    else:
+        return "Please record or upload an audio file."
+    
+    transcription = speech_to_text_model(audio)["text"]
+    return transcription
 
 # Create Gradio Interface with Tabs
 with gr.Blocks(theme="dark") as app:
     gr.Markdown("# 🚀 Multi-Tab Language Application")
-    
+
     with gr.Tabs():
         # Sentiment Analysis Tab
         with gr.Tab("Sentiment Analysis"):
@@ -43,7 +50,7 @@ with gr.Blocks(theme="dark") as app:
             sentiment_output = gr.Textbox(label="Sentiment")
             confidence_output = gr.Textbox(label="Confidence Score")
             analyze_button = gr.Button("Analyze")
-            
+
             analyze_button.click(analyze_sentiment, inputs=text_input, outputs=[sentiment_output, confidence_output])
 
         # Chatbot Tab
@@ -52,7 +59,7 @@ with gr.Blocks(theme="dark") as app:
             chatbot_input = gr.Textbox(label="Chat with AI")
             chatbot_output = gr.Textbox(label="Response", interactive=False)
             chat_button = gr.Button("Send")
-            
+
             chat_button.click(chatbot_response, inputs=chatbot_input, outputs=chatbot_output)
 
         # Summarization Tab
@@ -61,17 +68,23 @@ with gr.Blocks(theme="dark") as app:
             summary_input = gr.Textbox(label="Enter long text:", lines=5)
             summary_output = gr.Textbox(label="Summary", interactive=False)
             summarize_button = gr.Button("Summarize")
-            
+
             summarize_button.click(summarize_text, inputs=summary_input, outputs=summary_output)
 
-        # Text-to-Speech Tab
-        with gr.Tab("Text-to-Speech"):
-            gr.Markdown("## 🎙️ Text-to-Speech")
-            tts_input = gr.Textbox(label="Enter text to convert to speech:")
-            tts_output = gr.Audio(label="Generated Speech", autoplay=True)
-            tts_button = gr.Button("Convert to Speech")
+        # Speech-to-Text Tab (Modified)
+        with gr.Tab("Speech-to-Text"):
+            gr.Markdown("## 🎤 Speech-to-Text (ASR)")
+
+            mic_input = gr.Audio(sources=["microphone"], type="filepath", label="Record Audio")
+            mic_input.optional = True  # Mark as optional
+
+            file_input = gr.Audio(sources=["upload"], type="filepath", label="Upload Audio")
+            file_input.optional = True  # Mark as optional
+
+            transcript_output = gr.Textbox(label="Transcription")
+            transcribe_button = gr.Button("Transcribe")
 
-            tts_button.click(text_to_speech, inputs=tts_input, outputs=tts_output)
+            transcribe_button.click(transcribe_audio, inputs=[mic_input, file_input], outputs=transcript_output)
 
 # Launch the application
 app.launch()