initial commit

.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 +1,12 @@
+---
+title: Video2novel
+emoji: 😻
+colorFrom: red
+colorTo: pink
+sdk: gradio
+sdk_version: 5.35.0
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,57 @@
+def process_video(url, cookies_file=None):
+    session_id = str(uuid.uuid4())
+    base_dir = os.path.join("session_data", session_id)
+    os.makedirs(base_dir, exist_ok=True)
+
+    screenshots_dir = os.path.join(base_dir, "screenshots")
+    plots_dir = os.path.join(base_dir, "plots")
+    os.makedirs(screenshots_dir, exist_ok=True)
+    os.makedirs(plots_dir, exist_ok=True)
+
+    # Save cookies file if uploaded
+    cookies_path = None
+    if cookies_file is not None:
+        cookies_path = os.path.join(base_dir, "cookies.txt")
+        with open(cookies_path, "wb") as f:
+            f.write(cookies_file.read())
+
+    # Step 1: Download with cookies support
+    video_id, video_path, audio_path = download_video_audio(url, base_dir, cookies_path)
+
+    # Rest remains the same ...
+    result = model.transcribe(audio_path)
+    vtt_path = os.path.join(base_dir, f"{video_id}.vtt")
+    write_vtt(result["segments"], vtt_path)
+
+    entries = parse_vtt(vtt_path)
+
+    y, sr = librosa.load(audio_path, sr=None)
+    S = np.abs(librosa.stft(y, n_fft=2048, hop_length=512))
+    freqs = librosa.fft_frequencies(sr=sr, n_fft=2048)
+    voice_band = (freqs >= 300) & (freqs <= 3000)
+    voice_energy = S[voice_band, :].mean(axis=0)
+    voice_db = 20 * np.log10(voice_energy + 1e-6)
+    time_stamps = librosa.frames_to_time(np.arange(len(voice_db)), sr=sr, hop_length=512)
+
+    for entry in entries:
+        start = entry[0].split(" --> ")[0]
+        start_sec = parse_timestamp(start)
+        screenshot_path = os.path.join(screenshots_dir, f"{video_id}_{int(start_sec)}.jpg")
+        capture_screenshot(video_path, start_sec, screenshot_path)
+
+        plot_path = os.path.join(plots_dir, f"{video_id}_{int(start_sec)}_sound.png")
+        plt.figure(figsize=(8, 3))
+        plt.plot(time_stamps, voice_db, color="purple")
+        plt.axvline(x=start_sec, color="red", linestyle="--")
+        y_interp = np.interp(start_sec, time_stamps, voice_db)
+        plt.scatter([start_sec], [y_interp], color="red")
+        plt.xlabel("Time (s)")
+        plt.ylabel("dB (voice band)")
+        plt.tight_layout()
+        plt.savefig(plot_path)
+        plt.close()
+
+    html_output_path = os.path.join(base_dir, f"{video_id}.html")
+    final_html = generate_html(entries, video_id, url, screenshots_dir, plots_dir, html_output_path)
+
+    return final_html

requirements.txt

@@ -0,0 +1,7 @@
+gradio
+yt-dlp
+openai-whisper
+librosa
+matplotlib
+soundfile
+ffmpeg-python