Update app.py

app.py

@@ -1,17 +1,37 @@
 import gradio as gr
+import os
 import whisper
-import numpy as np
 
+# Load the Whisper model
 model = whisper.load_model("base")
 
-def transcribe(audio):
-    if not isinstance(audio, np.ndarray):
-        audio = np.array(audio)
+# Function to process the uploaded audio file and perform transcription
+def process_audio(upload):
+    # Save the uploaded audio file
+    file_path = "uploaded_audio.mp3"
+    upload.save(file_path)
+    
+    # Load the audio file and perform preprocessing
+    audio = whisper.load_audio(file_path)
     audio = whisper.pad_or_trim(audio)
     mel = whisper.log_mel_spectrogram(audio).to(model.device)
+    
+    # Detect the spoken language
+    _, probs = model.detect_language(mel)
+    detected_language = max(probs, key=probs.get)
+    
+    # Perform transcription using Whisper ASR
     options = whisper.DecodingOptions()
     result = whisper.decode(model, mel, options)
-    return result.text
+    transcription = result.text
+    
+    return transcription
 
-iface = gr.Interface(fn=transcribe, inputs="audio", outputs="text")
-iface.launch()
+# Create an audio input component for uploading the audio file
+audio_input = gr.inputs.Audio(label="Upload Audio", type="file")
+
+# Create a text output component for displaying the transcription
+text_output = gr.outputs.Textbox(label="Transcription")
+
+# Create a Gradio interface
+gr.Interface(fn=process_audio, inputs=audio_input, outputs=text_output, title="Audio Transcription").launch()