Update app.py

app.py

@@ -1,86 +1,43 @@
 import gradio as gr
+import whisper
 import os
-from transformers import WhisperProcessor, WhisperForConditionalGeneration
-import numpy as np
-import librosa
 
-# Initialize Whisper model
-processor = WhisperProcessor.from_pretrained("openai/whisper-base")
-model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-base")
-
-# Set light green theme
-theme = gr.themes.Base(
-    primary_hue="emerald",
-    secondary_hue="emerald",
-    neutral_hue="gray",
-)
-
-def validate_file(file_path):
-    # Check if file exists
-    if not file_path or not os.path.exists(file_path):
-        return False, "No file uploaded or file not found."
-    
-    # Check file size (25 MB limit)
-    file_size_mb = os.path.getsize(file_path) / (1024 * 1024)
-    if file_size_mb > 25:
-        return False, f"File size is {file_size_mb:.2f} MB. Please upload a file smaller than 25 MB."
-    
-    # Check file extension
-    file_extension = os.path.splitext(file_path)[1].lower()
-    if file_extension not in ['.mp3', '.wav']:
-        return False, "Only .mp3 and .wav formats are supported."
-    
-    return True, "File is valid."
+model = whisper.load_model("base")
 
 def transcribe_audio(audio_file):
-    # Check if audio_file is None
+    # Check if file is uploaded
     if audio_file is None:
-        return "Please upload an audio file."
+        return "Error: Please upload an audio file.", None
     
-    # Validate the file first
-    is_valid, message = validate_file(audio_file)
-    if not is_valid:
-        return message
+    # Get the file path - in newer Gradio versions, audio_file might be a string path directly
+    file_path = audio_file if isinstance(audio_file, str) else audio_file.name
+    
+    # Check file size (25MB limit)
+    if os.path.getsize(file_path) > 25 * 1024 * 1024:
+        return "Error: File size exceeds 25MB limit.", None
     
     try:
-        # Load audio file
-        speech_array, sampling_rate = librosa.load(audio_file, sr=16000)
-        
-        # Process the audio file
-        input_features = processor(speech_array, sampling_rate=16000, return_tensors="pt").input_features
+        result = model.transcribe(file_path)
+        output_filename = os.path.splitext(os.path.basename(file_path))[0] + ".txt"
         
-        # Generate token ids
-        predicted_ids = model.generate(input_features)
-        
-        # Decode token ids to text
-        transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]
-        
-        return transcription
+        with open(output_filename, "w") as text_file:
+            text_file.write(result["text"])
         
+        return result["text"], output_filename
+    
     except Exception as e:
-        return f"An error occurred during transcription: {str(e)}"
+        return f"Error during transcription: {str(e)}", None
 
-# Create Gradio interface
-with gr.Blocks(theme=theme) as demo:
-    gr.Markdown("# Audio Transcription with Whisper")
-    gr.Markdown("Upload an audio file (.mp3 or .wav) of maximum 25MB to get the transcription.")
-    
-    with gr.Row():
-        with gr.Column():
-            # Fixed: Use sources parameter instead of type
-            audio_input = gr.Audio(sources=["upload"], label="Upload Audio File")
-            submit_btn = gr.Button("Transcribe", variant="primary")
-        
-        with gr.Column():
-            output = gr.Textbox(label="Transcription Result", lines=10)
-    
-    submit_btn.click(fn=transcribe_audio, inputs=audio_input, outputs=output)
-    
-    gr.Markdown("### Limitations")
-    gr.Markdown("- Maximum file size: 25 MB")
-    gr.Markdown("- Supported formats: .mp3 and .wav")
-    gr.Markdown("- Uses the Whisper base model which works best with clear audio")
+iface = gr.Interface(
+    fn=transcribe_audio,
+    inputs=gr.File(label="Upload Audio File (Max 25MB)", file_types=["audio"]),
+    outputs=[
+        gr.Textbox(label="Transcription"),
+        gr.File(label="Download Transcript")
+    ],
+    title="Free Transcript Maker",
+    description="Upload an audio file (WAV, MP3, etc.) up to 25MB to get its transcription. The transcript will be displayed and available for download. Please use responsibly."
+)
 
-# Launch the app
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch()