Create app.py

app.py

@@ -0,0 +1,70 @@
+import gradio as gr
+import huggingface_hub
+import os 
+import subprocess
+import threading
+
+# download model
+huggingface_hub.hf_hub_download(
+    repo_id='ariesssxu/vta-ldm-clip4clip-v-large',
+    local_dir='./ckpt'
+)
+
+def stream_output(pipe):
+    for line in iter(pipe.readline, ''):
+        print(line, end='')
+
+def print_directory_contents(path):
+    for root, dirs, files in os.walk(path):
+        level = root.replace(path, '').count(os.sep)
+        indent = ' ' * 4 * (level)
+        print(f"{indent}{os.path.basename(root)}/")
+        subindent = ' ' * 4 * (level + 1)
+        for f in files:
+            print(f"{subindent}{f}")
+            
+def infer(video_in):
+
+    # Need to find path to gradio temp vid from video input
+    # path_to_video
+
+    print(f"VIDEO IN PATH: {video_in}")
+
+    # Execute the inference command
+    command = ['python', 'inference_from_video.py', '--data_path', video_in]
+    process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, bufsize=1)
+
+    # Create threads to handle stdout and stderr
+    stdout_thread = threading.Thread(target=stream_output, args=(process.stdout,))
+    stderr_thread = threading.Thread(target=stream_output, args=(process.stderr,))
+
+    # Start the threads
+    stdout_thread.start()
+    stderr_thread.start()
+
+    # Wait for the process to complete and the threads to finish
+    process.wait()
+    stdout_thread.join()
+    stderr_thread.join()
+
+    print("Inference script finished with return code:", process.returncode)
+
+    # Need to find where are the results stored, default should be "./outputs/tmp"
+    # Print the outputs directory contents
+        print_directory_contents('./outputs/tmp')
+    return "done"
+
+with gr.Blocks() as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown("# Video-To-Audio")
+        video_in = gr.Video(label='Video IN')
+        submit_btn = gr.Button("Submit")
+        #output_sound = gr.Audio(label="Audio OUT")
+        output_sound = gr.Textbox(label="Audio OUT")
+    submit_btn.click(
+        fn = infer,
+        inputs = [video_in],
+        outputs = [output_sound],
+        show_api = False
+    )
+demo.launch(show_api=False, show_error=True)