Update app.py

app.py

@@ -494,25 +494,26 @@ def transcribe_audio(input_source, pipeline_type, model_id, dtype, batch_size, d
         if verbose:
             yield verbose_messages, "", None
 
-        # Determine if input_source is a URL or file
+        # Determine if input_source is a URL, file path, or uploaded audio
         audio_path = None
         is_temp_file = False
 
-        if isinstance(input_source, str) and (input_source.startswith('http://') or input_source.startswith('https://')):
-            # Input source is a URL
-            audio_path, is_temp_file = download_audio(input_source, download_method)
-            if not audio_path:
-                error_msg = f"Error downloading audio from {input_source} using method {download_method}. Check logs for details."
-                logging.error(error_msg)
-                yield verbose_messages + error_msg, "", None
-                return
-        elif isinstance(input_source, str) and os.path.exists(input_source):
-            # Input source is a local file path
-            audio_path = input_source
-            is_temp_file = False
-        elif hasattr(input_source, 'name'):
-            # Input source is an uploaded file object
-            audio_path = input_source.name
+        if isinstance(input_source, str):
+            if input_source.startswith('http://') or input_source.startswith('https://'):
+                # Input source is a URL
+                audio_path, is_temp_file = download_audio(input_source, download_method)
+                if not audio_path:
+                    error_msg = f"Error downloading audio from {input_source} using method {download_method}. Check logs for details."
+                    logging.error(error_msg)
+                    yield verbose_messages + error_msg, "", None
+                    return
+            elif os.path.exists(input_source):
+                # Input source is a local file path
+                audio_path = input_source
+                is_temp_file = False
+        elif isinstance(input_source, dict) and 'path' in input_source:
+            # Input source is an uploaded audio file
+            audio_path = input_source['path']
             is_temp_file = False
         else:
             error_msg = "No valid audio source provided."
@@ -620,14 +621,13 @@ def transcribe_audio(input_source, pipeline_type, model_id, dtype, batch_size, d
         # Clean up temporary audio files
         if audio_path and is_temp_file and os.path.exists(audio_path):
             os.remove(audio_path)
-
+            
 with gr.Blocks() as iface:
-    gr.Markdown("# Multi-Pipeline Transcription")
-    gr.Markdown("Transcribe audio using multiple pipelines and models.")
+    gr.Markdown("# Audio Transcription")
+    gr.Markdown("Transcribe audio using multiple pipelines and (Faster) Whisper models.")
     
     with gr.Row():
-        #input_source = gr.File(label="Audio Source (Upload a file or enter a URL/YouTube URL)")
-        input_source = gr.Textbox(label="Audio Source (Upload a file or enter a URL/YouTube URL)")
+        input_source = gr.Audio(label="Audio Source (Upload a file or enter a URL/YouTube URL)")
         pipeline_type = gr.Dropdown(
             choices=["faster-batched", "faster-sequenced", "transformers"],
             label="Pipeline Type",