Update app.py

app.py

@@ -1,61 +1,80 @@
 import gradio as gr
-import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
-import torch
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
-
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
-
-    return image, seed
-
-
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
+import requests
+from pydub import AudioSegment
+import shazamio
+import os
+import time
+
+# Replace with your actual client ID and client secret
+client_id = os.environ.get('SOUNDCLOUD_CLIENT_ID')
+client_secret = os.environ.get('SOUNDCLOUD_CLIENT_SECRET')
+
+def get_soundcloud_access_token(client_id, client_secret):
+    auth_string = f'{client_id}:{client_secret}'
+    auth_headers = {
+        'Authorization': 'Basic ' + base64.b64encode(auth_string.encode()).decode()
+    }
+    data = {
+        'grant_type': 'client_credentials'
+    }
+    response = requests.post('https://api.soundcloud.com/oauth2/token', headers=auth_headers, data=data)
+    if response.status_code == 200:
+        token_data = response.json()
+        return token_data['access_token']
+    else:
+        raise Exception(f"Failed to obtain access token: {response.text}")
+
+def download_audio(streaming_url, output_path, headers):
+    response = requests.get(streaming_url, headers=headers, stream=True)
+    with open(output_path, 'wb') as f:
+        for chunk in response.iter_content(chunk_size=8192):
+            f.write(chunk)
+
+async def identify_track(shazam, audio_chunk):
+    temp_file = 'temp_chunk.wav'
+    audio_chunk.export(temp_file, format='wav')
+    result = await shazam.recognize_file(temp_file)
+    if result and 'track' in result:
+        track_data = result['track']
+        return {
+            'title': track_data['title'],
+            'subtitle': track_data['subtitle']
+        }
+    else:
+        return None
+
+async def process_dj_set(track_url, progress=gr.Progress()):
+    access_token = get_soundcloud_access_token(client_id, client_secret)
+    headers = {
+        'Authorization': 'Bearer ' + access_token
+    }
+    resolve_response = requests.get(f'https://api.soundcloud.com/resolve.json?url={track_url}', headers=headers)
+    if resolve_response.status_code != 200:
+        return "Failed to resolve track URL.", ""
+    track_data = resolve_response.json()
+    streaming_url = track_data['stream_url']
+    download_audio(streaming_url, 'track.wav', headers)
+    audio = AudioSegment.from_wav('track.wav')
+    chunk_duration = 30000  # 30 seconds
+    overlap = 10000  # 10 seconds
+    chunks = []
+    start = 0
+    while start + chunk_duration < len(audio):
+        end = start + chunk_duration
+        chunk = audio[start:end]
+        chunks.append((start, chunk))
+        start += chunk_duration - overlap
+    shazam = shazamio.Shazam()
+    tracklist = []
+    for start_time, chunk in chunks:
+        progress(0.1)
+        track_info = await identify_track(shazam, chunk)
+        if track_info:
+            timestamp = time.strftime("%M:%S", time.gmtime(start_time / 1000))
+            tracklist.append(f"{timestamp} - {track_info['title']} by {track_info['subtitle']}")
+    tracklist_output = "\n".join(tracklist)
+    download_content = tracklist_output
+    return tracklist_output, download_content
 
 css = """
 #col-container {
@@ -66,89 +85,27 @@ css = """
 
 with gr.Blocks(css=css) as demo:
     with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
+        gr.Markdown("# SoundCloud DJ Set Track Identifier")
 
         with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
+            track_url = gr.Text(
+                label="SoundCloud DJ Set URL",
                 show_label=False,
                 max_lines=1,
-                placeholder="Enter your prompt",
+                placeholder="Enter SoundCloud DJ set URL",
                 container=False,
             )
 
-            run_button = gr.Button("Run", scale=0, variant="primary")
-
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
+            run_button = gr.Button("Process", scale=0, variant="primary")
 
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
+        result = gr.Textbox(label="Tracklist", show_label=False)
 
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
+        with gr.Accordion("Download Tracklist", open=False):
+            download_button = gr.File(label="Download", file_name="tracklist.txt")
 
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
+        gr.Examples(examples=["https://soundcloud.com/your-track-url"], inputs=[track_url])
 
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
+    run_button.click(process_dj_set, inputs=track_url, outputs=[result, download_button])
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()