Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Instant Karaoke
+emoji: 📉
+colorFrom: green
+colorTo: indigo
+sdk: gradio
+sdk_version: 6.1.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+short_description: Use AI to split a YT video into instrumental/vocal tracks
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,68 @@
+import os
+import re
+import base64
+import spaces
+import urllib
+import gradio as gr
+import demucs.separate
+
+os.makedirs("/home/user/.cache/torch/hub/checkpoints")
+urllib.request.urlretrieve(
+    "https://dl.fbaipublicfiles.com/demucs/hybrid_transformer/955717e8-8726e21a.th",
+    "/home/user/.cache/torch/hub/checkpoints/955717e8-8726e21a.th"
+)
+
+with open("ytcookies.txt", "wb") as f:
+    f.write(base64.b64decode(os.environ["YT_COOKIE"]))
+
+
+# begin copy-pasted function
+
+from yt_dlp import YoutubeDL
+
+def download_best_audio(url, outtmpl="%(id)s.%(ext)s"):
+    final_filename = None
+
+    def progress_hook(d):
+        nonlocal final_filename
+
+        # Final file after download (and after post-processing, if any)
+        if d.get("status") == "finished" and "filename" in d:
+            final_filename = d["filename"]
+
+        # Some postprocessors (e.g., ffmpeg) report separately
+        if d.get("status") == "postprocessor_finished":
+            final_filename = d.get("filename", final_filename)
+
+    ydl_opts = {
+        "format": "bestaudio/best",
+        "outtmpl": outtmpl,
+        "progress_hooks": [progress_hook],
+        "quiet": True,
+        "cookiefile": "ytcookies.txt"
+    }
+
+    with YoutubeDL(ydl_opts) as ydl:
+        ydl.download([url])
+
+    return final_filename
+
+# end copy-pasted function
+
+@spaces.GPU
+def dummy(nope):
+    pass
+
+def vidplusvox(yturl, progress=gr.Progress(track_tqdm=True)):
+    if not re.fullmatch(r'((?:https?:)?\/\/)?((?:www|m)\.)?((?:youtube(?:-nocookie)?\.com|youtu.be))(\/(?:[\w\-]+\?v=|embed\/|live\/|v\/)?)([\w\-]+)(\S+)?', yturl):
+        raise gr.Error("Invalid YouTube URL", duration=5)
+    infile = download_best_audio(yturl)
+    outinfo = demucs.separate.main(["--mp3", "--two-stems", "vocals", "-n", "htdemucs", "-d", "cpu", infile])
+    stem = "/home/user/app/separated/htdemucs/"+infile.rsplit(".", 1)[0]
+    print(os.listdir(stem))
+    return stem+"/vocals.mp3", stem+"/no_vocals.mp3"
+        
+
+demo = gr.Interface(fn=vidplusvox, inputs=gr.Text(label="YouTube URL"), outputs=[gr.Audio(label="Vocal"),gr.Audio(label="Instrumental")])
+demo.queue()
+demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+demucs
+yt-dlp