Upload 12 files

FAKE.txt

@@ -0,0 +1,323 @@
+aagfhgtpmv.mp4
+aapnvogymq.mp4
+abofeumbvv.mp4
+abqwwspghj.mp4
+acifjvzvpm.mp4
+acqfdwsrhi.mp4
+acxnxvbsxk.mp4
+acxwigylke.mp4
+aczrgyricp.mp4
+adhsbajydo.mp4
+adohikbdaz.mp4
+adylbeequz.mp4
+aelzhcnwgf.mp4
+aettqgevhz.mp4
+aevrfsexku.mp4
+agdkmztvby.mp4
+agqphdxmwt.mp4
+ahbweevwpv.mp4
+ahdbuwqxit.mp4
+ahfazfbntc.mp4
+aipfdnwpoo.mp4
+ajwpjhrbcv.mp4
+aklqzsddfl.mp4
+aknbdpmgua.mp4
+aknmpoonls.mp4
+akvmwkdyuv.mp4
+akxoopqjqz.mp4
+akzbnazxtz.mp4
+aladcziidp.mp4
+alaijyygdv.mp4
+alninxcyhg.mp4
+altziddtxi.mp4
+alvgwypubw.mp4
+amaivqofda.mp4
+amowujxmzc.mp4
+andaxzscny.mp4
+aneclqfpbt.mp4
+aorjvbyxhw.mp4
+apatcsqejh.mp4
+apgjqzkoma.mp4
+apogckdfrz.mp4
+aqpnvjhuzw.mp4
+arkroixhey.mp4
+arlmiizoob.mp4
+arrhsnjqku.mp4
+asdpeebotb.mp4
+aslsvlvpth.mp4
+asmpfjfzif.mp4
+asvcrfdpnq.mp4
+atxvxouljq.mp4
+atyntldecu.mp4
+atzdznmder.mp4
+aufmsmnoye.mp4
+augtsuxpzc.mp4
+avfitoutyn.mp4
+avgiuextiz.mp4
+avibnnhwhp.mp4
+avnqydkqjj.mp4
+avssvvsdhz.mp4
+avtycwsgyb.mp4
+avvdgsennp.mp4
+avywawptfc.mp4
+awhmfnnjih.mp4
+awnwkrqibf.mp4
+awukslzjra.mp4
+axczxisdtb.mp4
+axoygtekut.mp4
+axwgcsyphv.mp4
+axwovszumc.mp4
+ayqvfdhslr.mp4
+azpuxunqyo.mp4
+azsmewqghg.mp4
+bahdpoesir.mp4
+bbhpvrmbse.mp4
+bbhtdfuqxq.mp4
+bbvgxeczei.mp4
+bchnbulevv.mp4
+bctvsmddgq.mp4
+bdbhekrrwo.mp4
+bdgipnyobr.mp4
+bdxuhamuqx.mp4
+benmsfzfaz.mp4
+bgaogsjehq.mp4
+bggsurpgpr.mp4
+bghphrsfxf.mp4
+bgmlwsoamc.mp4
+bguwlyazau.mp4
+bhaaboftbc.mp4
+bhbdugnurr.mp4
+bhpwpydzpo.mp4
+bhsluedavd.mp4
+bjjbwsqjir.mp4
+bjkmjilrxp.mp4
+bjsmaqefoi.mp4
+bkmdzhfzfh.mp4
+bkvetcojbt.mp4
+bkwxhglwct.mp4
+blpchvmhxx.mp4
+blzydqdfem.mp4
+bmbbkwmxqj.mp4
+bmehkyanbj.mp4
+bmhvktyiwp.mp4
+bmioepcpsx.mp4
+bmjmjmbglm.mp4
+bnbuonyoje.mp4
+bndybcqhfr.mp4
+bnjcdrfuov.mp4
+bntlodcfeg.mp4
+bofqajtwve.mp4
+boovltmuwi.mp4
+bopqhhalml.mp4
+bourlmzsio.mp4
+bpwzipqtxf.mp4
+bpxckdzddv.mp4
+bqdjzqhcft.mp4
+bqeiblbxtl.mp4
+bqhtpqmmqp.mp4
+bqkdbcqjvb.mp4
+bqnymlsayl.mp4
+bqqpbzjgup.mp4
+bqtuuwzdtr.mp4
+brhalypwoo.mp4
+brvqtabyxj.mp4
+bseamdrpbj.mp4
+bsfmwclnqy.mp4
+bsqgziaylx.mp4
+btiysiskpf.mp4
+btjlfpzbdu.mp4
+btjwbtsgln.mp4
+btmsngnqhv.mp4
+btohlidmru.mp4
+btugrnoton.mp4
+btunxncpjh.mp4
+btxlttbpkj.mp4
+bvgwelbeof.mp4
+bvzjkezkms.mp4
+bweezhfpzp.mp4
+bwuwstvsbw.mp4
+bydaidkpdp.mp4
+byfenovjnf.mp4
+byijojkdba.mp4
+byofowlkki.mp4
+byqzyxifza.mp4
+byunigvnay.mp4
+byyqectxqa.mp4
+bzmdrafeex.mp4
+caqbrkogkb.mp4
+cbbibzcoih.mp4
+cbltdtxglo.mp4
+ccmonzqfrz.mp4
+cdaxixbosp.mp4
+cdbsbdymzd.mp4
+cdphtzqrvp.mp4
+cdyakrxkia.mp4
+cepxysienc.mp4
+cettndmvzl.mp4
+ceymbecxnj.mp4
+cferslmfwh.mp4
+cffffbcywc.mp4
+cfyduhpbps.mp4
+cglxirfaey.mp4
+cgvrgibpfo.mp4
+chzieimrwu.mp4
+ckbdwedgmc.mp4
+cknyxaqouy.mp4
+cksanfsjhc.mp4
+clihsshdkq.mp4
+cmxcfkrjiv.mp4
+cnilkgvfei.mp4
+coadfnerlk.mp4
+covdcysmbi.mp4
+cqfugiqupm.mp4
+cqhngvpgyi.mp4
+cqrskwiqng.mp4
+crktehraph.mp4
+crzfebnfgb.mp4
+cthdnahrkh.mp4
+ctpqeykqdp.mp4
+cttqtsjvgn.mp4
+ctzmavwror.mp4
+curpwogllm.mp4
+cuzrgrbvil.mp4
+cvaksbpssm.mp4
+cwbacdwrzo.mp4
+cwqlvzefpg.mp4
+cwrtyzndpx.mp4
+cwsbspfzck.mp4
+cwwandrkus.mp4
+cxfujlvsuw.mp4
+cxrfacemmq.mp4
+cxttmymlbn.mp4
+cyboodqqyr.mp4
+cycacemkmt.mp4
+cyclgfjdrv.mp4
+czfunozvwp.mp4
+czkdanyadc.mp4
+czmqpxrqoh.mp4
+dafhtipaml.mp4
+dakqwktlbi.mp4
+dbhoxkblzx.mp4
+dbhrpizyeq.mp4
+dboxtiehng.mp4
+dbzcqmxzaj.mp4
+dbzpcjntve.mp4
+dcamvmuors.mp4
+dcuiiorugd.mp4
+ddhfabwpuz.mp4
+ddjggcasdw.mp4
+ddpvuimigj.mp4
+ddqccgmtka.mp4
+degpbqvcay.mp4
+deywhkarol.mp4
+deyyistcrd.mp4
+dfbpceeaox.mp4
+dgmevclvzy.mp4
+dgxrqjdomn.mp4
+dgzklxjmix.mp4
+dhcselezer.mp4
+dhevettufk.mp4
+dhjmzhrcav.mp4
+dhkwmjxwrn.mp4
+dhoqofwoxa.mp4
+diomeixhrg.mp4
+diopzaywor.mp4
+diqraixiov.mp4
+diuzrpqjli.mp4
+djvtbgwdcc.mp4
+djvutyvaio.mp4
+dkdwxmtpuo.mp4
+dkhlttuvmx.mp4
+dkrvorliqc.mp4
+dkwjwbwgey.mp4
+dlrsbscitn.mp4
+dnexlwbcxq.mp4
+dnhvalzvrt.mp4
+dntkzzzcdh.mp4
+dnyvfblxpm.mp4
+doanjploai.mp4
+dofusvhnib.mp4
+dozyddhild.mp4
+dptbnjnkdg.mp4
+dptrzdvwpg.mp4
+dqnyszdong.mp4
+dqppxmoqdl.mp4
+dqqtjcryjv.mp4
+dqswpjoepo.mp4
+dqzreruvje.mp4
+drgjzlxzxj.mp4
+drsakwyvqv.mp4
+drtbksnpol.mp4
+dsdoseflas.mp4
+dsgpbgsrdm.mp4
+dsndhujjjb.mp4
+dtbpmdqvao.mp4
+dtocdfbwca.mp4
+dubiroskqn.mp4
+dulanfulol.mp4
+duvyaxbzvp.mp4
+duzuusuajr.mp4
+dvakowbgbt.mp4
+dvumqqhoac.mp4
+dwediigjit.mp4
+dxuliowugt.mp4
+dxuplhwvig.mp4
+dzieklokdr.mp4
+dzqwgqewhu.mp4
+dzvyfiarrq.mp4
+dzwkmcwkwl.mp4
+eahlqmfvtj.mp4
+eajlrktemq.mp4
+ebchwmwayp.mp4
+ebebgmtlcu.mp4
+ebeknhudxq.mp4
+ebkzwjgjhq.mp4
+ebywfrmhtd.mp4
+ecnihjlfyt.mp4
+ecuvtoltue.mp4
+ecwaxgutkc.mp4
+eczrseixwq.mp4
+eebrkicpry.mp4
+eebserckhh.mp4
+eejswgycjc.mp4
+eekozbeafq.mp4
+eepezmygaq.mp4
+eeyhxisdfh.mp4
+efdyrflcpg.mp4
+egbbcxcuqy.mp4
+ehbnclaukr.mp4
+ehdkmxgtxh.mp4
+ehevsxtecd.mp4
+ehfiekigla.mp4
+ehieahnhte.mp4
+eiriyukqqy.mp4
+eivxffliio.mp4
+eiwopxzjfn.mp4
+eixwxvxbbn.mp4
+ejkqesyvam.mp4
+ekhacizpah.mp4
+ekkdjkirzq.mp4
+elginszwtk.mp4
+elvvackpjh.mp4
+emaalmsonj.mp4
+emfbhytfhc.mp4
+emgjphonqb.mp4
+ensyyivobf.mp4
+eoewqcpbgt.mp4
+eprybmbpba.mp4
+epymyyiblu.mp4
+eqjscdagiv.mp4
+eqvuznuwsa.mp4
+erqgqacbqe.mp4
+errocgcham.mp4
+esckbnkkvb.mp4
+esgftaficx.mp4
+esnntzzajv.mp4
+esxrvsgpvb.mp4
+esyhwdfnxs.mp4
+esyrimvzsa.mp4
+etdcqxabww.mp4
+etejaapnxh.mp4
+etmcruaihe.mp4
+etohcvnzbj.mp4
+eukvucdetx.mp4

REAL.txt

@@ -0,0 +1,77 @@
+abarnvbtwb.mp4
+aelfnikyqj.mp4
+afoovlsmtx.mp4
+agrmhtjdlk.mp4
+ahqqqilsxt.mp4
+ajqslcypsw.mp4
+anpuvshzoo.mp4
+asaxgevnnp.mp4
+atkdltyyen.mp4
+atvmxvwyns.mp4
+avmjormvsx.mp4
+axntxmycwd.mp4
+aybgughjxh.mp4
+aybumesmpk.mp4
+aytzyidmgs.mp4
+bddjdhzfze.mp4
+bdnaqemxmr.mp4
+beboztfcme.mp4
+bejhvclboh.mp4
+beyebyhrph.mp4
+bffwsjxghk.mp4
+bgvhtpzknn.mp4
+bgwmmujlmc.mp4
+bilnggbxgu.mp4
+bmjzrlszhi.mp4
+bpapbctoao.mp4
+brwrlczjvi.mp4
+bulkxhhknf.mp4
+bwhlgysghg.mp4
+bwipwzzxxu.mp4
+bxzakyopjf.mp4
+bzythlfnhq.mp4
+caifxvsozs.mp4
+ccfoszqabv.mp4
+cfxkpiweqt.mp4
+chtapglbcj.mp4
+chviwxsfhg.mp4
+ciyoudyhly.mp4
+cizlkenljw.mp4
+ckjaibzfxa.mp4
+ckkuyewywx.mp4
+clrycekyst.mp4
+cmbzllswnl.mp4
+cobjrlugvp.mp4
+cpjxareypw.mp4
+cppdvdejkc.mp4
+cprhtltsjp.mp4
+crezycjqyk.mp4
+cyxlcuyznd.mp4
+dakiztgtnw.mp4
+dbnygxtwek.mp4
+dbtbbhakdv.mp4
+ddepeddixj.mp4
+dhcndnuwta.mp4
+dhxctgyoqj.mp4
+djxdyjopjd.mp4
+dkuayagnmc.mp4
+dkzvdrzcnr.mp4
+dlpoieqvfb.mp4
+drcyabprvt.mp4
+dsjbknkujw.mp4
+duycddgtrl.mp4
+dxbqjxrhin.mp4
+dzyuwjkjui.mp4
+eckvhdusax.mp4
+ecujsjhscd.mp4
+edyncaijwx.mp4
+efwfxwwlbw.mp4
+eggbjzxnmg.mp4
+egghxjjmfg.mp4
+ehccixxzoe.mp4
+ehtdtkmmli.mp4
+ekcrtigpab.mp4
+ellavthztb.mp4
+eqnoqyfquo.mp4
+erlvuvjsjf.mp4
+eudeqjhdfd.mp4

arrange.py

@@ -0,0 +1,59 @@
+import json
+import os
+import glob
+
+
+# Ensure the REAL and FAKE directories exist
+real_dir = r"REAL"
+fake_dir = r"FAKE"
+
+if not os.path.exists(real_dir):
+    os.makedirs(real_dir)
+
+if not os.path.exists(fake_dir):
+    os.makedirs(fake_dir)
+
+t = 0
+
+real = []
+fake = []
+l =  glob.glob("train_sample_videos/*.json")
+for i in l:
+    with open(i, "r") as f:
+        x = json.load(f)
+
+    for file in x:
+        if x[file]["label"] == "REAL":
+            real.append(file)
+        else:
+            fake.append(file)
+
+print("Real: ", real)
+print("Fake: ", fake)
+
+with open("REAL.txt", "w") as f:
+    for i in real:
+        f.write(i + "\n")
+
+with open("FAKE.txt", "w") as f:
+    for i in fake:
+        f.write(i + "\n")   
+
+# for file in x:
+#     try:
+#         if x[file]["label"] == "REAL":
+#             os.rename(
+#                 f"C:\\Users\\vaibh\\OneDrive\\Desktop\\deepfake_project\\train_sample_videos\\{file}",
+#                 f"{real_dir}\\{file}",
+#             )
+#     except Exception as e:
+#         print(f"Error moving REAL video {file}: {e}")
+
+#     try:
+#         if x[file]["label"] == "FAKE":
+#             os.rename(
+#                 f"C:\\Users\\vaibh\\OneDrive\\Desktop\\deepfake_project\\train_sample_videos\\{file}",  # Corrected path
+#                 f"{fake_dir}\\{file}",
+#             )
+#     except Exception as e:
+#         print(f"Error moving FAKE video {file}: {e}")

dl_training.ipynb

@@ -0,0 +1,957 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import librosa\n",
+    "import io\n",
+    "import soundfile as sf\n",
+    "from moviepy.editor import VideoFileClip\n",
+    "from tqdm import tqdm\n",
+    "import pickle as pk\n",
+    "import os\n",
+    "import tensorflow as tf\n",
+    "# from tensorflow.keras.saving import register_keras_serializable\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.metrics import classification_report, confusion_matrix\n",
+    "from tensorflow.keras import layers, models\n",
+    "from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# real_audio_dir = (\n",
+    "#     r\"H:\\.shortcut-targets-by-id\\1jH_pc6mMj0Iu8wLS1r0vggMWpVElJvOU\\SIH2024_DATASET\\REAL\"\n",
+    "# )\n",
+    "# fake_audio_dir = (\n",
+    "#     r\"H:\\.shortcut-targets-by-id\\1jH_pc6mMj0Iu8wLS1r0vggMWpVElJvOU\\SIH2024_DATASET\\FAKE\"\n",
+    "# )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# with open(\n",
+    "#     r\"H:\\.shortcut-targets-by-id\\1jH_pc6mMj0Iu8wLS1r0vggMWpVElJvOU\\SIH2024_DATASET\\real_files.pkl\",\n",
+    "#     \"rb\",\n",
+    "# ) as f:\n",
+    "#     real_files = pk.load(f)\n",
+    "\n",
+    "# with open(\n",
+    "#     r\"H:\\.shortcut-targets-by-id\\1jH_pc6mMj0Iu8wLS1r0vggMWpVElJvOU\\SIH2024_DATASET\\fake_files.pkl\",\n",
+    "#     \"rb\",\n",
+    "# ) as f:\n",
+    "#     fake_files = pk.load(f)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# len(real_files), len(fake_files)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# real_files = real_files[:2000]\n",
+    "# fake_files = fake_files[:2000]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# fake_files = fake_files[: len(real_files)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# len(real_files), len(fake_files)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# def extract_features(file_path):\n",
+    "#     try:\n",
+    "#         # Load the video file\n",
+    "#         video_clip = VideoFileClip(file_path)\n",
+    "#         audio = video_clip.audio\n",
+    "#         fps = audio.fps\n",
+    "#         audio_samples = np.array(\n",
+    "#             list(audio.iter_frames(fps=fps, dtype=\"float32\"))\n",
+    "#         ).flatten()\n",
+    "#         buffer = io.BytesIO()\n",
+    "#         sf.write(buffer, audio_samples, fps, format=\"wav\")\n",
+    "#         buffer.seek(0)\n",
+    "#         x, sr = librosa.load(buffer, sr=None)\n",
+    "#         mfccs = librosa.feature.mfcc(y=x, sr=sr, n_mfcc=20)\n",
+    "\n",
+    "#         return mfccs\n",
+    "\n",
+    "#     except Exception as e:\n",
+    "#         print(f\"Error encountered while parsing file: {file_path}, {e}\")\n",
+    "#         return None\n",
+    "\n",
+    "\n",
+    "# def load_data(real_dir, fake_dir):\n",
+    "#     labels = []\n",
+    "#     features = []\n",
+    "\n",
+    "#     # Load real audios\n",
+    "#     for file_name in real_files:\n",
+    "#         file_path = os.path.join(real_dir, file_name)\n",
+    "#         mfccs = extract_features(file_path)\n",
+    "#         if mfccs is not None:\n",
+    "#             features.append(mfccs)\n",
+    "#             labels.append(0)  # 0 for REAL\n",
+    "\n",
+    "#     # Load fake audios\n",
+    "#     for file_name in fake_files:\n",
+    "#         file_path = os.path.join(fake_dir, file_name)\n",
+    "#         mfccs = extract_features(file_path)\n",
+    "#         if mfccs is not None:\n",
+    "#             features.append(mfccs)\n",
+    "#             labels.append(1)  # 1 for FAKE\n",
+    "\n",
+    "#     return np.array(features), np.array(labels)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# def extract_frame_features(file_path, frame_duration=1.0):\n",
+    "#     try:\n",
+    "#         video_clip = VideoFileClip(file_path)\n",
+    "#         audio = video_clip.audio\n",
+    "#         fps = audio.fps\n",
+    "#         audio_samples = np.array(\n",
+    "#             list(audio.iter_frames(fps=fps, dtype=\"float32\"))\n",
+    "#         ).flatten()\n",
+    "#         buffer = io.BytesIO()\n",
+    "#         sf.write(buffer, audio_samples, fps, format=\"wav\")\n",
+    "#         buffer.seek(0)\n",
+    "#         x, sr = librosa.load(buffer, sr=None)\n",
+    "\n",
+    "#         # Split audio into frames of 'frame_duration' seconds\n",
+    "#         frame_length = int(frame_duration * sr)\n",
+    "#         frames = [\n",
+    "#             librosa.feature.mfcc(y=x[i : i + frame_length], sr=sr, n_mfcc=20)\n",
+    "#             for i in range(0, len(x), frame_length)\n",
+    "#             if i + frame_length <= len(x)\n",
+    "#         ]\n",
+    "\n",
+    "#         return frames  # Returns list of MFCCs for each frame\n",
+    "\n",
+    "#     except Exception as e:\n",
+    "#         print(f\"Error processing file {file_path}: {e}\")\n",
+    "#         return None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def extract_frame_features(file_path, frame_duration=1.0):\n",
+    "    video_clip = VideoFileClip(file_path)\n",
+    "    audio = video_clip.audio\n",
+    "    fps = audio.fps\n",
+    "    audio_samples = np.array(\n",
+    "        list(audio.iter_frames(fps=fps, dtype=\"float32\"))\n",
+    "    ).flatten()\n",
+    "    buffer = io.BytesIO()\n",
+    "    sf.write(buffer, audio_samples, fps, format=\"wav\")\n",
+    "    buffer.seek(0)\n",
+    "    x, sr = librosa.load(buffer, sr=None)\n",
+    "\n",
+    "    # Split audio into frames of 'frame_duration' seconds\n",
+    "    frame_length = int(frame_duration * sr)\n",
+    "    frames = []\n",
+    "    timestamps = []\n",
+    "\n",
+    "    for i in range(0, len(x), frame_length):\n",
+    "        if i + frame_length <= len(x):\n",
+    "            # Extract MFCCs for each frame and store the timestamp\n",
+    "            frame_mfcc = librosa.feature.mfcc(y=x[i: i + frame_length], sr=sr, n_mfcc=20)\n",
+    "            frames.append(frame_mfcc)\n",
+    "            timestamp = i / sr  # Convert index to seconds\n",
+    "            timestamps.append(timestamp)\n",
+    "\n",
+    "    return frames, timestamps"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# def load_data(real_dir, fake_dir, real_files, fake_files):\n",
+    "#     labels, features = [], []\n",
+    "\n",
+    "#     # Load real audio frames with progress bar\n",
+    "#     print(\"Loading real audio files:\")\n",
+    "#     for file_name in tqdm(real_files, desc=\"Processing Real Files\"):\n",
+    "#         file_path = os.path.join(real_dir, file_name)\n",
+    "#         frame_features, timestamps = extract_frame_features(file_path)\n",
+    "#         if frame_features:\n",
+    "#             features.extend(frame_features)\n",
+    "#             labels.extend([0] * len(frame_features))  # Label 0 for REAL\n",
+    "\n",
+    "#     # Load fake audio frames with progress bar\n",
+    "#     print(\"Loading fake audio files:\")\n",
+    "#     for file_name in tqdm(fake_files, desc=\"Processing Fake Files\"):\n",
+    "#         file_path = os.path.join(fake_dir, file_name)\n",
+    "#         frame_features = extract_frame_features(file_path)\n",
+    "#         if frame_features:\n",
+    "#             features.extend(frame_features)\n",
+    "#             labels.extend([1] * len(frame_features))  # Label 1 for FAKE\n",
+    "\n",
+    "#     # Convert to numpy arrays\n",
+    "#     features = np.array(features)\n",
+    "#     labels = np.array(labels)\n",
+    "\n",
+    "#     # Shuffle the data\n",
+    "#     indices = np.arange(len(features))\n",
+    "#     np.random.shuffle(indices)\n",
+    "#     features = features[indices]\n",
+    "#     labels = labels[indices]\n",
+    "\n",
+    "#     return features, labels"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# X, y = load_data(real_audio_dir, fake_audio_dir, real_files, fake_files)\n",
+    "# X = X[..., np.newaxis]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# with open(\"X_for_dl_2000.pkl\", \"wb\") as f:\n",
+    "#     pk.dump(X, f)\n",
+    "# with open(\"y_for_dl_2000.pkl\", \"wb\") as f:\n",
+    "#     pk.dump(y, f)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"X_for_dl_2000.pkl\", \"rb\") as f:\n",
+    "    X = pk.load(f)\n",
+    "with open(\"y_for_dl_2000.pkl\", \"rb\") as f:\n",
+    "    y = pk.load(f)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(\n",
+    "    X, y, test_size=0.2, random_state=30\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## TCN"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# model = models.Sequential(\n",
+    "#     [\n",
+    "#         layers.Conv1D(\n",
+    "#             64,\n",
+    "#             kernel_size=3,\n",
+    "#             dilation_rate=1,\n",
+    "#             padding=\"causal\",\n",
+    "#             activation=\"relu\",\n",
+    "#             input_shape=(X.shape[1], X.shape[2]),\n",
+    "#         ),\n",
+    "#         layers.Conv1D(\n",
+    "#             128, kernel_size=3, dilation_rate=2, padding=\"causal\", activation=\"relu\"\n",
+    "#         ),\n",
+    "#         layers.Conv1D(\n",
+    "#             256, kernel_size=3, dilation_rate=4, padding=\"causal\", activation=\"relu\"\n",
+    "#         ),\n",
+    "#         layers.GlobalAveragePooling1D(),\n",
+    "#         layers.Dropout(0.5),\n",
+    "#         layers.Dense(64, activation=\"relu\"),\n",
+    "#         layers.Dense(2, activation=\"softmax\"),\n",
+    "#     ]\n",
+    "# )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tensorflow.keras import models, layers\n",
+    "\n",
+    "model = models.Sequential(\n",
+    "    [\n",
+    "        layers.Conv1D(\n",
+    "            64,\n",
+    "            kernel_size=3,\n",
+    "            dilation_rate=1,\n",
+    "            padding=\"causal\",\n",
+    "            activation=\"relu\",\n",
+    "            input_shape=(X.shape[1], X.shape[2]),\n",
+    "        ),\n",
+    "        layers.BatchNormalization(),\n",
+    "        layers.Conv1D(\n",
+    "            128, kernel_size=3, dilation_rate=2, padding=\"causal\", activation=\"relu\"\n",
+    "        ),\n",
+    "        layers.BatchNormalization(),\n",
+    "        layers.Conv1D(\n",
+    "            256, kernel_size=3, dilation_rate=4, padding=\"causal\", activation=\"relu\"\n",
+    "        ),\n",
+    "        layers.BatchNormalization(),\n",
+    "        layers.GlobalAveragePooling1D(),\n",
+    "        layers.Dropout(0.5),\n",
+    "        layers.Dense(128, activation=\"relu\"),\n",
+    "        layers.Dropout(0.3),\n",
+    "        layers.Dense(2, activation=\"softmax\"),\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.compile(\n",
+    "    optimizer=\"adam\", loss=\"sparse_categorical_crossentropy\", metrics=[\"accuracy\"]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "checkpoint = ModelCheckpoint(\n",
+    "    \"model/best_model.keras\", monitor=\"val_loss\", save_best_only=True\n",
+    ")\n",
+    "early_stopping = EarlyStopping(monitor=\"val_loss\", patience=3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1mModel: \"sequential\"\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+       "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+       "│ conv1d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv1D</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">20</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)         │        <span style=\"color: #00af00; text-decoration-color: #00af00\">16,768</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ batch_normalization             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">20</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)         │           <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span> │\n",
+       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv1d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv1D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">20</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)        │        <span style=\"color: #00af00; text-decoration-color: #00af00\">24,704</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ batch_normalization_1           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">20</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)        │           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n",
+       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv1d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv1D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">20</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)        │        <span style=\"color: #00af00; text-decoration-color: #00af00\">98,560</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ batch_normalization_2           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">20</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)        │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,024</span> │\n",
+       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ global_average_pooling1d        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">GlobalAveragePooling1D</span>)        │                        │               │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">32,896</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">258</span> │\n",
+       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+       "│ conv1d (\u001b[38;5;33mConv1D\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m20\u001b[0m, \u001b[38;5;34m64\u001b[0m)         │        \u001b[38;5;34m16,768\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ batch_normalization             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m20\u001b[0m, \u001b[38;5;34m64\u001b[0m)         │           \u001b[38;5;34m256\u001b[0m │\n",
+       "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv1d_1 (\u001b[38;5;33mConv1D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m20\u001b[0m, \u001b[38;5;34m128\u001b[0m)        │        \u001b[38;5;34m24,704\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ batch_normalization_1           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m20\u001b[0m, \u001b[38;5;34m128\u001b[0m)        │           \u001b[38;5;34m512\u001b[0m │\n",
+       "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv1d_2 (\u001b[38;5;33mConv1D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m20\u001b[0m, \u001b[38;5;34m256\u001b[0m)        │        \u001b[38;5;34m98,560\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ batch_normalization_2           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m20\u001b[0m, \u001b[38;5;34m256\u001b[0m)        │         \u001b[38;5;34m1,024\u001b[0m │\n",
+       "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
+       "├──────���──────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ global_average_pooling1d        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
+       "│ (\u001b[38;5;33mGlobalAveragePooling1D\u001b[0m)        │                        │               │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m32,896\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m)              │           \u001b[38;5;34m258\u001b[0m │\n",
+       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">174,978</span> (683.51 KB)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m174,978\u001b[0m (683.51 KB)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">174,082</span> (680.01 KB)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m174,082\u001b[0m (680.01 KB)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">896</span> (3.50 KB)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m896\u001b[0m (3.50 KB)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "model.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 4ms/step - accuracy: 0.6385 - loss: 0.6350 - val_accuracy: 0.6710 - val_loss: 0.6011\n",
+      "Epoch 2/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m17s\u001b[0m 4ms/step - accuracy: 0.6680 - loss: 0.6062 - val_accuracy: 0.6838 - val_loss: 0.5800\n",
+      "Epoch 3/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━��━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m16s\u001b[0m 4ms/step - accuracy: 0.6856 - loss: 0.5882 - val_accuracy: 0.7069 - val_loss: 0.5591\n",
+      "Epoch 4/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.6969 - loss: 0.5731 - val_accuracy: 0.7187 - val_loss: 0.5497\n",
+      "Epoch 5/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7038 - loss: 0.5649 - val_accuracy: 0.7303 - val_loss: 0.5353\n",
+      "Epoch 6/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7127 - loss: 0.5569 - val_accuracy: 0.7343 - val_loss: 0.5330\n",
+      "Epoch 7/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7198 - loss: 0.5478 - val_accuracy: 0.7102 - val_loss: 0.5598\n",
+      "Epoch 8/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7239 - loss: 0.5452 - val_accuracy: 0.7404 - val_loss: 0.5247\n",
+      "Epoch 9/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7271 - loss: 0.5389 - val_accuracy: 0.7310 - val_loss: 0.5310\n",
+      "Epoch 10/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7301 - loss: 0.5323 - val_accuracy: 0.7369 - val_loss: 0.5335\n",
+      "Epoch 11/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7358 - loss: 0.5272 - val_accuracy: 0.7529 - val_loss: 0.5058\n",
+      "Epoch 12/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7363 - loss: 0.5263 - val_accuracy: 0.7451 - val_loss: 0.5065\n",
+      "Epoch 13/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m14s\u001b[0m 4ms/step - accuracy: 0.7379 - loss: 0.5212 - val_accuracy: 0.7451 - val_loss: 0.5055\n",
+      "Epoch 14/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7454 - loss: 0.5105 - val_accuracy: 0.7447 - val_loss: 0.5048\n",
+      "Epoch 15/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7478 - loss: 0.5100 - val_accuracy: 0.7554 - val_loss: 0.4946\n",
+      "Epoch 16/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7442 - loss: 0.5087 - val_accuracy: 0.7533 - val_loss: 0.5004\n",
+      "Epoch 17/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m14s\u001b[0m 4ms/step - accuracy: 0.7513 - loss: 0.5005 - val_accuracy: 0.7469 - val_loss: 0.5045\n",
+      "Epoch 18/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m14s\u001b[0m 4ms/step - accuracy: 0.7507 - loss: 0.4992 - val_accuracy: 0.7519 - val_loss: 0.4980\n",
+      "Epoch 19/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m14s\u001b[0m 4ms/step - accuracy: 0.7528 - loss: 0.4976 - val_accuracy: 0.7553 - val_loss: 0.4930\n",
+      "Epoch 20/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7582 - loss: 0.4947 - val_accuracy: 0.7637 - val_loss: 0.4833\n",
+      "Epoch 21/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7561 - loss: 0.4986 - val_accuracy: 0.7668 - val_loss: 0.4831\n",
+      "Epoch 22/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m���━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7593 - loss: 0.4891 - val_accuracy: 0.7671 - val_loss: 0.4819\n",
+      "Epoch 23/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m14s\u001b[0m 4ms/step - accuracy: 0.7578 - loss: 0.4900 - val_accuracy: 0.7671 - val_loss: 0.4808\n",
+      "Epoch 24/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7628 - loss: 0.4851 - val_accuracy: 0.7586 - val_loss: 0.5014\n",
+      "Epoch 25/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m14s\u001b[0m 4ms/step - accuracy: 0.7609 - loss: 0.4850 - val_accuracy: 0.7563 - val_loss: 0.4884\n",
+      "Epoch 26/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7647 - loss: 0.4826 - val_accuracy: 0.7679 - val_loss: 0.4788\n",
+      "Epoch 27/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7623 - loss: 0.4848 - val_accuracy: 0.7476 - val_loss: 0.5020\n",
+      "Epoch 28/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7665 - loss: 0.4792 - val_accuracy: 0.7659 - val_loss: 0.4835\n",
+      "Epoch 29/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7658 - loss: 0.4796 - val_accuracy: 0.7688 - val_loss: 0.4923\n",
+      "Epoch 30/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7688 - loss: 0.4759 - val_accuracy: 0.7709 - val_loss: 0.4781\n",
+      "Epoch 31/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7702 - loss: 0.4755 - val_accuracy: 0.7553 - val_loss: 0.4968\n",
+      "Epoch 32/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7703 - loss: 0.4728 - val_accuracy: 0.7692 - val_loss: 0.4744\n",
+      "Epoch 33/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7703 - loss: 0.4716 - val_accuracy: 0.7613 - val_loss: 0.4869\n",
+      "Epoch 34/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7728 - loss: 0.4707 - val_accuracy: 0.7648 - val_loss: 0.4952\n",
+      "Epoch 35/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7699 - loss: 0.4720 - val_accuracy: 0.7648 - val_loss: 0.4968\n",
+      "Epoch 36/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7727 - loss: 0.4688 - val_accuracy: 0.7643 - val_loss: 0.5095\n",
+      "Epoch 37/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7730 - loss: 0.4670 - val_accuracy: 0.7674 - val_loss: 0.4827\n",
+      "Epoch 38/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7749 - loss: 0.4659 - val_accuracy: 0.7728 - val_loss: 0.4697\n",
+      "Epoch 39/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m16s\u001b[0m 4ms/step - accuracy: 0.7772 - loss: 0.4618 - val_accuracy: 0.7753 - val_loss: 0.4774\n",
+      "Epoch 40/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m16s\u001b[0m 4ms/step - accuracy: 0.7795 - loss: 0.4587 - val_accuracy: 0.7663 - val_loss: 0.4824\n",
+      "Epoch 41/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 5ms/step - accuracy: 0.7765 - loss: 0.4638 - val_accuracy: 0.7561 - val_loss: 0.4910\n",
+      "Epoch 42/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 4ms/step - accuracy: 0.7768 - loss: 0.4616 - val_accuracy: 0.7749 - val_loss: 0.4737\n",
+      "Epoch 43/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 5ms/step - accuracy: 0.7800 - loss: 0.4554 - val_accuracy: 0.7698 - val_loss: 0.4747\n",
+      "Epoch 44/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 5ms/step - accuracy: 0.7816 - loss: 0.4528 - val_accuracy: 0.7476 - val_loss: 0.4988\n",
+      "Epoch 45/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 5ms/step - accuracy: 0.7819 - loss: 0.4553 - val_accuracy: 0.7630 - val_loss: 0.4820\n",
+      "Epoch 46/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 5ms/step - accuracy: 0.7780 - loss: 0.4587 - val_accuracy: 0.7554 - val_loss: 0.4887\n",
+      "Epoch 47/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 5ms/step - accuracy: 0.7832 - loss: 0.4555 - val_accuracy: 0.7773 - val_loss: 0.4709\n",
+      "Epoch 48/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 5ms/step - accuracy: 0.7831 - loss: 0.4511 - val_accuracy: 0.7667 - val_loss: 0.4760\n",
+      "Epoch 49/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m17s\u001b[0m 4ms/step - accuracy: 0.7831 - loss: 0.4513 - val_accuracy: 0.7731 - val_loss: 0.4812\n",
+      "Epoch 50/50\n",
+      "\u001b[1m3998/3998\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 4ms/step - accuracy: 0.7837 - loss: 0.4550 - val_accuracy: 0.7775 - val_loss: 0.4859\n"
+     ]
+    }
+   ],
+   "source": [
+    "history = model.fit(\n",
+    "    X_train,\n",
+    "    y_train,\n",
+    "    epochs=50,\n",
+    "    batch_size=16,\n",
+    "    validation_data=(X_test, y_test),\n",
+    "    callbacks=[checkpoint],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = tf.keras.models.load_model(\"model/TCN.keras\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1m500/500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "        REAL       0.89      0.62      0.73      7920\n",
+      "        FAKE       0.71      0.92      0.80      8072\n",
+      "\n",
+      "    accuracy                           0.77     15992\n",
+      "   macro avg       0.80      0.77      0.77     15992\n",
+      "weighted avg       0.80      0.77      0.77     15992\n",
+      "\n",
+      "[[4910 3010]\n",
+      " [ 623 7449]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# model = tf.keras.models.load_model(\"model/best_model.keras\")\n",
+    "y_pred = model.predict(X_test)\n",
+    "y_pred_labels = np.argmax(y_pred, axis=1)\n",
+    "\n",
+    "# Print classification report\n",
+    "print(classification_report(y_test, y_pred_labels, target_names=[\"REAL\", \"FAKE\"]))\n",
+    "print(confusion_matrix(y_test, y_pred_labels))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 169ms/step\n",
+      "Found 8 deepfake frames:\n",
+      "Frame 1 at 0.00s: FAKE\n",
+      "Frame 2 at 1.00s: FAKE\n",
+      "Frame 3 at 2.00s: FAKE\n",
+      "Frame 4 at 3.00s: FAKE\n",
+      "Frame 5 at 4.00s: FAKE\n",
+      "Frame 8 at 7.00s: FAKE\n",
+      "Frame 11 at 10.00s: FAKE\n",
+      "Frame 15 at 14.00s: FAKE\n"
+     ]
+    }
+   ],
+   "source": [
+    "def test_on_video(file_path, frame_duration=1.0):\n",
+    "    # Load the trained model\n",
+    "    model = tf.keras.models.load_model(\"model/TCN.keras\")\n",
+    "\n",
+    "    # Extract features and timestamps for each frame in the new video\n",
+    "    frames, timestamps = extract_frame_features(file_path, frame_duration)\n",
+    "\n",
+    "    if frames is None or timestamps is None:\n",
+    "        print(\"No frames extracted.\")\n",
+    "        return\n",
+    "\n",
+    "    # Reshape frames for model input\n",
+    "    frames = np.array(frames)[..., np.newaxis]\n",
+    "\n",
+    "    # Predict on each frame\n",
+    "    predictions = model.predict(frames)\n",
+    "    pred_labels = np.argmax(predictions, axis=1)\n",
+    "\n",
+    "    # Store deepfake frames, their timestamps, and frame indices\n",
+    "    deepfake_frames = []\n",
+    "    deepfake_timestamps = []\n",
+    "    deepfake_indices = []\n",
+    "\n",
+    "    # Identify deepfake frames\n",
+    "    for i, label in enumerate(pred_labels):\n",
+    "        if label == 1:  # If the label is FAKE\n",
+    "            deepfake_frames.append(frames[i])\n",
+    "            deepfake_timestamps.append(timestamps[i])\n",
+    "            deepfake_indices.append(i)\n",
+    "\n",
+    "    if not deepfake_frames:\n",
+    "        print(\"No deepfake frames detected in the video.\")\n",
+    "        return\n",
+    "\n",
+    "    # Analyze deepfake frames\n",
+    "    print(f\"Found {len(deepfake_frames)} deepfake frames:\")\n",
+    "    for i, (timestamp, index) in enumerate(zip(deepfake_timestamps, deepfake_indices)):\n",
+    "        print(f\"Frame {index + 1} at {timestamp:.2f}s: FAKE\")\n",
+    "\n",
+    "\n",
+    "# Example usage\n",
+    "test_video_path = r\"REAL\\ajqslcypsw.mp4\"  # Replace with your test video path\n",
+    "test_on_video(test_video_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# def test_on_video(file_path, frame_duration=1.0):\n",
+    "#     # Load the trained model\n",
+    "#     model = tf.keras.models.load_model(\"model/best_model.keras\")\n",
+    "\n",
+    "#     # Extract features for each frame in the new video\n",
+    "#     frames = extract_frame_features(file_path, frame_duration)\n",
+    "\n",
+    "#     if frames is None:\n",
+    "#         print(\"No frames extracted.\")\n",
+    "#         return\n",
+    "\n",
+    "#     # Reshape frames for model input\n",
+    "#     frames = np.array(frames)[..., np.newaxis]\n",
+    "\n",
+    "#     # Predict on each frame\n",
+    "#     predictions = model.predict(frames)\n",
+    "#     pred_labels = np.argmax(predictions, axis=1)\n",
+    "\n",
+    "#     # Output results for each frame\n",
+    "#     for i, label in enumerate(pred_labels):\n",
+    "#         status = \"REAL\" if label == 0 else \"FAKE\"\n",
+    "#         print(f\"Frame {i+1}: {status}\")\n",
+    "\n",
+    "\n",
+    "# # Example usage\n",
+    "# test_video_path = r\"REAL\\bddjdhzfze.mp4\"  # Replace with your test video path\n",
+    "# test_on_video(test_video_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# @register_keras_serializable()\n",
+    "# class AudioModel(tf.keras.Model):\n",
+    "#     def __init__(self, input_shape):\n",
+    "#         super(AudioModel, self).__init__()\n",
+    "#         self.input_shape = input_shape  # Store the input shape\n",
+    "#         # Define the model layers\n",
+    "#         self.conv1 = layers.Conv2D(\n",
+    "#             32, kernel_size=(3, 3), activation=\"relu\", input_shape=input_shape\n",
+    "#         )\n",
+    "#         self.conv2 = layers.Conv2D(64, kernel_size=(3, 3), activation=\"relu\")\n",
+    "#         self.pool = layers.MaxPooling2D(pool_size=(2, 2))\n",
+    "#         self.dropout1 = layers.Dropout(0.25)\n",
+    "\n",
+    "#         self.reshape = layers.Reshape((64, -1))\n",
+    "#         self.gru = layers.Bidirectional(layers.GRU(128, return_sequences=False))\n",
+    "\n",
+    "#         self.dense1 = layers.Dense(128, activation=\"relu\")\n",
+    "#         self.dropout2 = layers.Dropout(0.5)\n",
+    "#         self.dense2 = layers.Dense(2, activation=\"softmax\")\n",
+    "\n",
+    "#     def call(self, inputs):\n",
+    "#         # Forward pass through the layers\n",
+    "#         x = self.conv1(inputs)\n",
+    "#         x = self.conv2(x)\n",
+    "#         x = self.pool(x)\n",
+    "#         x = self.dropout1(x)\n",
+    "\n",
+    "#         x = self.reshape(x)\n",
+    "#         x = self.gru(x)\n",
+    "\n",
+    "#         x = self.dense1(x)\n",
+    "#         x = self.dropout2(x)\n",
+    "#         return self.dense2(x)\n",
+    "\n",
+    "#     def get_config(self):\n",
+    "#         config = super(AudioModel, self).get_config()\n",
+    "#         config.update(\n",
+    "#             {\"input_shape\": self.input_shape}  # Include input shape in config\n",
+    "#         )\n",
+    "#         return config\n",
+    "\n",
+    "#     @classmethod\n",
+    "#     def from_config(cls, config):\n",
+    "#         # Create a model instance from the config\n",
+    "#         input_shape = config.pop(\"input_shape\")  # Extract input_shape from config\n",
+    "#         return cls(input_shape)  # Create an instance of the model\n",
+    "\n",
+    "\n",
+    "# # Function to create and compile the model\n",
+    "# def create_model(input_shape):\n",
+    "#     model = AudioModel(input_shape)\n",
+    "#     model.compile(\n",
+    "#         optimizer=\"adam\", loss=\"sparse_categorical_crossentropy\", metrics=[\"accuracy\"]\n",
+    "#     )\n",
+    "#     return model\n",
+    "\n",
+    "\n",
+    "# # Example usage\n",
+    "# input_shape = (\n",
+    "#     64,\n",
+    "#     40,\n",
+    "#     1,\n",
+    "# )  # Adjust based on your data (e.g., (n_mfccs, time_steps, channels))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# model = create_model(input_shape)\n",
+    "# model.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# checkpoint = ModelCheckpoint(r\"models/dl_model.keras\", monitor=\"val_loss\", save_best_only=True, verbose=1)\n",
+    "# early_stopping = EarlyStopping(monitor=\"val_loss\", patience=5, verbose=1)\n",
+    "\n",
+    "# history = model.fit(\n",
+    "#     X_train, y_train, epochs=10, batch_size=16, validation_data=(X_test, y_test), callbacks=[checkpoint, early_stopping]\n",
+    "# )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# model.save(r\"models/dl_model.keras\", overwrite=True)\n",
+    "# print(\"Model saved successfully.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# # Ensure to import keras properly\n",
+    "# import tensorflow as tf\n",
+    "# from tensorflow import keras\n",
+    "\n",
+    "\n",
+    "# # Function to load the model\n",
+    "# def load_model(model_path):\n",
+    "#     try:\n",
+    "#         # Load the model from the specified path\n",
+    "#         model = keras.models.load_model(model_path)\n",
+    "#         print(\"Model loaded successfully.\")\n",
+    "#         return model\n",
+    "#     except Exception as e:\n",
+    "#         print(f\"Error loading model: {e}\")\n",
+    "#         return None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# model_path = r\"models/dl_model.keras\"\n",
+    "\n",
+    "# # Load the model\n",
+    "# loaded_model = load_model(model_path)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

fast_feature_extraction.ipynb

@@ -0,0 +1,580 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "H3eVgsMsJVRY",
+    "outputId": "30e4d553-6ce2-4b44-8217-21d0f1875d8b"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda\n"
+     ]
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "import cupy as cp\n",
+    "from moviepy.editor import VideoFileClip\n",
+    "import pandas as pd\n",
+    "import librosa\n",
+    "import scipy.stats\n",
+    "import soundfile as sf\n",
+    "import io\n",
+    "import os\n",
+    "from tqdm import tqdm\n",
+    "import pickle as pk\n",
+    "\n",
+    "# Set device to GPU if available\n",
+    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
+    "print(device)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "3A9iF-QXJVRZ"
+   },
+   "source": [
+    "Statistical Features  \n",
+    "A first easy step is to compute the mean, standard deviation, minimum, maximum, median and quartiles of the frequencies of each signal. This can be done using Numpy and it always brings value to our feature extraction."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "id": "ibnbShbMJVRa"
+   },
+   "outputs": [],
+   "source": [
+    "def describe_freq(freqs):\n",
+    "    freqs = cp.array(freqs)  # Convert to CuPy array for GPU computation\n",
+    "    mean = cp.mean(freqs)\n",
+    "    std = cp.std(freqs)\n",
+    "    maxv = cp.amax(freqs)\n",
+    "    minv = cp.amin(freqs)\n",
+    "    median = cp.median(freqs)\n",
+    "    skew = scipy.stats.skew(cp.asnumpy(freqs))  # Skew not directly supported in CuPy\n",
+    "    kurt = scipy.stats.kurtosis(cp.asnumpy(freqs))  # Kurtosis not directly supported in CuPy\n",
+    "    q1 = cp.quantile(freqs, 0.25)\n",
+    "    q3 = cp.quantile(freqs, 0.75)\n",
+    "    mode = scipy.stats.mode(cp.asnumpy(freqs))[0][0]  # Mode not directly supported in CuPy\n",
+    "    iqr = cp.subtract(q3, q1)\n",
+    "\n",
+    "    return [mean.get(), std.get(), maxv.get(), minv.get(), median.get(), skew, kurt, q1.get(), q3.get(), mode, iqr.get()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "id": "nNifSVyDJVRa"
+   },
+   "outputs": [],
+   "source": [
+    "def get_features(x, sr):\n",
+    "    x = torch.tensor(x, device=device)  # Send to GPU\n",
+    "    rmse = torch.mean(torch.tensor(librosa.feature.rms(y=x.cpu().numpy())[0], device=device))\n",
+    "    zcr = torch.mean(torch.tensor(librosa.feature.zero_crossing_rate(x.cpu().numpy())[0], device=device))\n",
+    "    tempo = torch.tensor(librosa.beat.tempo(y=x.cpu().numpy(), sr=sr)[0], device=device)\n",
+    "    mfcc = torch.mean(torch.tensor(librosa.feature.mfcc(y=x.cpu().numpy(), sr=sr), device=device), axis=1)\n",
+    "    spec_cen = torch.mean(torch.tensor(librosa.feature.spectral_centroid(y=x.cpu().numpy(), sr=sr), device=device))\n",
+    "    spectral_bandwidth = torch.mean(torch.tensor(librosa.feature.spectral_bandwidth(y=x.cpu().numpy(), sr=sr), device=device))\n",
+    "    spectral_contrast = torch.mean(torch.tensor(librosa.feature.spectral_contrast(y=x.cpu().numpy(), sr=sr), device=device))\n",
+    "    spectral_flatness = torch.mean(torch.tensor(librosa.feature.spectral_flatness(y=x.cpu().numpy()), device=device))\n",
+    "    spectral_rolloff = torch.mean(torch.tensor(librosa.feature.spectral_rolloff(y=x.cpu().numpy(), sr=sr), device=device))\n",
+    "\n",
+    "    features = [rmse, zcr, tempo, spec_cen, spectral_bandwidth, spectral_contrast, spectral_flatness, spectral_rolloff]\n",
+    "    features = [f.item() for f in features] + [mfcc[i].item() for i in range(mfcc.size(0))]  # Convert to list\n",
+    "    return features"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "id": "6p0CSM2I_qGY"
+   },
+   "outputs": [],
+   "source": [
+    "def extract_features(file_path):\n",
+    "    try:\n",
+    "        # Load video file\n",
+    "        video_clip = VideoFileClip(file_path)\n",
+    "        audio = video_clip.audio\n",
+    "        fps = audio.fps\n",
+    "        audio_samples = cp.array(list(audio.iter_frames(fps=fps, dtype=\"float32\"))).flatten()\n",
+    "        buffer = io.BytesIO()\n",
+    "        sf.write(buffer, cp.asnumpy(audio_samples), fps, format=\"wav\")\n",
+    "        buffer.seek(0)\n",
+    "        x, sr = librosa.load(buffer, sr=None)\n",
+    "        video_clip.close()\n",
+    "        features = get_features(x, sr)\n",
+    "        return features\n",
+    "\n",
+    "    except Exception as e:\n",
+    "        print(f\"Error encountered while parsing file: {file_path}, {e}\")\n",
+    "        return None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "id": "fiFT26TK_tA_"
+   },
+   "outputs": [],
+   "source": [
+    "def load_data(real_dir, fake_dir, real_files, fake_files):\n",
+    "    data = []\n",
+    "    columns = [\"rmse\", \"zcr\", \"tempo\", \"spectral_centroid\", \"spectral_bandwidth\",\n",
+    "               \"spectral_contrast\", \"spectral_flatness\", \"spectral_rolloff\"] + \\\n",
+    "              [f\"mfcc{i}\" for i in range(1, 21)] + [\"label\"]\n",
+    "\n",
+    "    # Set up progress bar\n",
+    "    total_files = len(real_files) + len(fake_files)\n",
+    "    pbar = tqdm(total=total_files, desc=\"Processing files\", unit=\"file\")\n",
+    "\n",
+    "    # Process real audio files\n",
+    "    for file_name in real_files:\n",
+    "        file_path = os.path.join(real_dir, file_name)\n",
+    "        features = extract_features(file_path)\n",
+    "        if features is not None:\n",
+    "            features.append(0)  # Label: 0 for REAL\n",
+    "            data.append(features)\n",
+    "        pbar.update(1)\n",
+    "\n",
+    "    # Process fake audio files\n",
+    "    for file_name in fake_files:\n",
+    "        file_path = os.path.join(fake_dir, file_name)\n",
+    "        features = extract_features(file_path)\n",
+    "        if features is not None:\n",
+    "            features.append(1)  # Label: 1 for FAKE\n",
+    "            data.append(features)\n",
+    "        pbar.update(1)\n",
+    "\n",
+    "    pbar.close()\n",
+    "    df = pd.DataFrame(data, columns=columns)\n",
+    "    return df\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "id": "nL9J7Vp9JVRa"
+   },
+   "outputs": [],
+   "source": [
+    "real_audio_dir = r\"H:\\.shortcut-targets-by-id\\1jH_pc6mMj0Iu8wLS1r0vggMWpVElJvOU\\SIH2024_DATASET\\REAL\"\n",
+    "fake_audio_dir = r\"H:\\.shortcut-targets-by-id\\1jH_pc6mMj0Iu8wLS1r0vggMWpVElJvOU\\SIH2024_DATASET\\FAKE\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "gfwu2Ct2E5aQ"
+   },
+   "outputs": [],
+   "source": [
+    "with open(\n",
+    "    r\"H:\\.shortcut-targets-by-id\\1jH_pc6mMj0Iu8wLS1r0vggMWpVElJvOU\\SIH2024_DATASET\\real_files.pkl\",\n",
+    "    \"rb\",\n",
+    ") as f:\n",
+    "    real_files = pk.load(f)\n",
+    "\n",
+    "with open(\n",
+    "    r\"H:\\.shortcut-targets-by-id\\1jH_pc6mMj0Iu8wLS1r0vggMWpVElJvOU\\SIH2024_DATASET\\fake_files.pkl\",\n",
+    "    \"rb\",\n",
+    ") as f:\n",
+    "    fake_files = pk.load(f)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(19154, 99992)"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(real_files), len(fake_files)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fake_files = fake_files[:len(real_files)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(19154, 19154)"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(real_files), len(fake_files)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "BUS-nOHOJVRb",
+    "outputId": "8eee5356-bbdb-4941-a6a8-023a552db603"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Processing files:  17%|█▋        | 671/4000 [1:19:37<4:35:56,  4.97s/file] "
+     ]
+    }
+   ],
+   "source": [
+    "df = load_data(real_audio_dir, fake_audio_dir, real_files[:2000], fake_files[:2000])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "3tLFhSuVJVRc"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>rmse</th>\n",
+       "      <th>zcr</th>\n",
+       "      <th>tempo</th>\n",
+       "      <th>spectral_centroid</th>\n",
+       "      <th>spectral_bandwidth</th>\n",
+       "      <th>spectral_contrast</th>\n",
+       "      <th>spectral_flatness</th>\n",
+       "      <th>spectral_rolloff</th>\n",
+       "      <th>mfcc1</th>\n",
+       "      <th>mfcc2</th>\n",
+       "      <th>...</th>\n",
+       "      <th>mfcc12</th>\n",
+       "      <th>mfcc13</th>\n",
+       "      <th>mfcc14</th>\n",
+       "      <th>mfcc15</th>\n",
+       "      <th>mfcc16</th>\n",
+       "      <th>mfcc17</th>\n",
+       "      <th>mfcc18</th>\n",
+       "      <th>mfcc19</th>\n",
+       "      <th>mfcc20</th>\n",
+       "      <th>label</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>0.004624</td>\n",
+       "      <td>0.025053</td>\n",
+       "      <td>129.199219</td>\n",
+       "      <td>2725.983254</td>\n",
+       "      <td>5010.822943</td>\n",
+       "      <td>14.822473</td>\n",
+       "      <td>0.002854</td>\n",
+       "      <td>4820.494920</td>\n",
+       "      <td>-534.778259</td>\n",
+       "      <td>154.150742</td>\n",
+       "      <td>...</td>\n",
+       "      <td>8.461435</td>\n",
+       "      <td>-5.363853</td>\n",
+       "      <td>1.651735</td>\n",
+       "      <td>1.570598</td>\n",
+       "      <td>-6.969818</td>\n",
+       "      <td>-1.332273</td>\n",
+       "      <td>-7.264575</td>\n",
+       "      <td>-2.166896</td>\n",
+       "      <td>-5.390424</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>0.012205</td>\n",
+       "      <td>0.040296</td>\n",
+       "      <td>123.046875</td>\n",
+       "      <td>3647.104615</td>\n",
+       "      <td>5343.519738</td>\n",
+       "      <td>16.671819</td>\n",
+       "      <td>0.007903</td>\n",
+       "      <td>8357.563553</td>\n",
+       "      <td>-421.535065</td>\n",
+       "      <td>121.641014</td>\n",
+       "      <td>...</td>\n",
+       "      <td>16.492485</td>\n",
+       "      <td>-15.264863</td>\n",
+       "      <td>5.351438</td>\n",
+       "      <td>-6.834963</td>\n",
+       "      <td>-6.844149</td>\n",
+       "      <td>2.524184</td>\n",
+       "      <td>-9.907133</td>\n",
+       "      <td>2.443203</td>\n",
+       "      <td>-3.203485</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>0.000486</td>\n",
+       "      <td>0.065730</td>\n",
+       "      <td>123.046875</td>\n",
+       "      <td>4911.118560</td>\n",
+       "      <td>5816.154610</td>\n",
+       "      <td>13.167884</td>\n",
+       "      <td>0.020470</td>\n",
+       "      <td>12992.775671</td>\n",
+       "      <td>-651.358948</td>\n",
+       "      <td>105.408440</td>\n",
+       "      <td>...</td>\n",
+       "      <td>22.212151</td>\n",
+       "      <td>-8.999311</td>\n",
+       "      <td>9.159810</td>\n",
+       "      <td>-1.134552</td>\n",
+       "      <td>0.878308</td>\n",
+       "      <td>-4.592861</td>\n",
+       "      <td>6.159277</td>\n",
+       "      <td>-8.804791</td>\n",
+       "      <td>4.221607</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>0.010587</td>\n",
+       "      <td>0.044573</td>\n",
+       "      <td>126.048018</td>\n",
+       "      <td>3769.014655</td>\n",
+       "      <td>5425.975753</td>\n",
+       "      <td>16.238748</td>\n",
+       "      <td>0.008020</td>\n",
+       "      <td>8702.531203</td>\n",
+       "      <td>-423.674591</td>\n",
+       "      <td>125.309708</td>\n",
+       "      <td>...</td>\n",
+       "      <td>17.190102</td>\n",
+       "      <td>-19.386557</td>\n",
+       "      <td>2.690195</td>\n",
+       "      <td>-8.972520</td>\n",
+       "      <td>-8.547749</td>\n",
+       "      <td>3.633717</td>\n",
+       "      <td>-7.594123</td>\n",
+       "      <td>5.063034</td>\n",
+       "      <td>-3.646331</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>0.001556</td>\n",
+       "      <td>0.048985</td>\n",
+       "      <td>126.048018</td>\n",
+       "      <td>3916.497123</td>\n",
+       "      <td>5451.384648</td>\n",
+       "      <td>14.959555</td>\n",
+       "      <td>0.011601</td>\n",
+       "      <td>8986.764496</td>\n",
+       "      <td>-614.185364</td>\n",
+       "      <td>123.651947</td>\n",
+       "      <td>...</td>\n",
+       "      <td>16.776917</td>\n",
+       "      <td>-9.418891</td>\n",
+       "      <td>1.858516</td>\n",
+       "      <td>-3.961122</td>\n",
+       "      <td>-3.926236</td>\n",
+       "      <td>-5.990383</td>\n",
+       "      <td>3.210501</td>\n",
+       "      <td>-8.581244</td>\n",
+       "      <td>4.236759</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 29 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       rmse       zcr       tempo  spectral_centroid  spectral_bandwidth  \\\n",
+       "5  0.004624  0.025053  129.199219        2725.983254         5010.822943   \n",
+       "6  0.012205  0.040296  123.046875        3647.104615         5343.519738   \n",
+       "7  0.000486  0.065730  123.046875        4911.118560         5816.154610   \n",
+       "8  0.010587  0.044573  126.048018        3769.014655         5425.975753   \n",
+       "9  0.001556  0.048985  126.048018        3916.497123         5451.384648   \n",
+       "\n",
+       "   spectral_contrast  spectral_flatness  spectral_rolloff       mfcc1  \\\n",
+       "5          14.822473           0.002854       4820.494920 -534.778259   \n",
+       "6          16.671819           0.007903       8357.563553 -421.535065   \n",
+       "7          13.167884           0.020470      12992.775671 -651.358948   \n",
+       "8          16.238748           0.008020       8702.531203 -423.674591   \n",
+       "9          14.959555           0.011601       8986.764496 -614.185364   \n",
+       "\n",
+       "        mfcc2  ...     mfcc12     mfcc13    mfcc14    mfcc15    mfcc16  \\\n",
+       "5  154.150742  ...   8.461435  -5.363853  1.651735  1.570598 -6.969818   \n",
+       "6  121.641014  ...  16.492485 -15.264863  5.351438 -6.834963 -6.844149   \n",
+       "7  105.408440  ...  22.212151  -8.999311  9.159810 -1.134552  0.878308   \n",
+       "8  125.309708  ...  17.190102 -19.386557  2.690195 -8.972520 -8.547749   \n",
+       "9  123.651947  ...  16.776917  -9.418891  1.858516 -3.961122 -3.926236   \n",
+       "\n",
+       "     mfcc17    mfcc18    mfcc19    mfcc20  label  \n",
+       "5 -1.332273 -7.264575 -2.166896 -5.390424      1  \n",
+       "6  2.524184 -9.907133  2.443203 -3.203485      1  \n",
+       "7 -4.592861  6.159277 -8.804791  4.221607      1  \n",
+       "8  3.633717 -7.594123  5.063034 -3.646331      1  \n",
+       "9 -5.990383  3.210501 -8.581244  4.236759      1  \n",
+       "\n",
+       "[5 rows x 29 columns]"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.tail()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "zMej7SKRJVRc"
+   },
+   "outputs": [],
+   "source": [
+    "# for file in file_names:\n",
+    "\n",
+    "#     clean_file = file.split(\"/\")[-1]\n",
+    "#     video_clip = VideoFileClip(file)\n",
+    "#     audio = video_clip.audio\n",
+    "#     fps = audio.fps\n",
+    "#     audio_samples = np.array(list(audio.iter_frames(fps=fps, dtype=\"float32\"))).flatten()\n",
+    "#     buffer = io.BytesIO()\n",
+    "#     sf.write(buffer, audio_samples, fps, format='wav')\n",
+    "#     buffer.seek(0)\n",
+    "#     x, sr = librosa.load(buffer, sr=None)\n",
+    "#     label = json.load(open(\"train_sample_videos/metadata.json\"))[clean_file]['label']\n",
+    "#     new_row = pd.DataFrame([[clean_file] + get_features(x, sr) + [label]], columns=column_ames)\n",
+    "#     df = pd.concat([df, new_row], ignore_index=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "BxacOcTrJVRc"
+   },
+   "outputs": [
+    {
+     "ename": "OSError",
+     "evalue": "Cannot save file into a non-existent directory: '\\content\\drive\\MyDrive\\SIH2024_DATASET'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mOSError\u001b[0m                                   Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[14], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[43mdf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/content/drive/MyDrive/SIH2024_DATASET/full_features.csv\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mindex\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32md:\\Python\\Lib\\site-packages\\pandas\\util\\_decorators.py:333\u001b[0m, in \u001b[0;36mdeprecate_nonkeyword_arguments.<locals>.decorate.<locals>.wrapper\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m    327\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(args) \u001b[38;5;241m>\u001b[39m num_allow_args:\n\u001b[0;32m    328\u001b[0m     warnings\u001b[38;5;241m.\u001b[39mwarn(\n\u001b[0;32m    329\u001b[0m         msg\u001b[38;5;241m.\u001b[39mformat(arguments\u001b[38;5;241m=\u001b[39m_format_argument_list(allow_args)),\n\u001b[0;32m    330\u001b[0m         \u001b[38;5;167;01mFutureWarning\u001b[39;00m,\n\u001b[0;32m    331\u001b[0m         stacklevel\u001b[38;5;241m=\u001b[39mfind_stack_level(),\n\u001b[0;32m    332\u001b[0m     )\n\u001b[1;32m--> 333\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32md:\\Python\\Lib\\site-packages\\pandas\\core\\generic.py:3964\u001b[0m, in \u001b[0;36mNDFrame.to_csv\u001b[1;34m(self, path_or_buf, sep, na_rep, float_format, columns, header, index, index_label, mode, encoding, compression, quoting, quotechar, lineterminator, chunksize, date_format, doublequote, escapechar, decimal, errors, storage_options)\u001b[0m\n\u001b[0;32m   3953\u001b[0m df \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m, ABCDataFrame) \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mto_frame()\n\u001b[0;32m   3955\u001b[0m formatter \u001b[38;5;241m=\u001b[39m DataFrameFormatter(\n\u001b[0;32m   3956\u001b[0m     frame\u001b[38;5;241m=\u001b[39mdf,\n\u001b[0;32m   3957\u001b[0m     header\u001b[38;5;241m=\u001b[39mheader,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   3961\u001b[0m     decimal\u001b[38;5;241m=\u001b[39mdecimal,\n\u001b[0;32m   3962\u001b[0m )\n\u001b[1;32m-> 3964\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mDataFrameRenderer\u001b[49m\u001b[43m(\u001b[49m\u001b[43mformatter\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto_csv\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   3965\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpath_or_buf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3966\u001b[0m \u001b[43m    \u001b[49m\u001b[43mlineterminator\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlineterminator\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3967\u001b[0m \u001b[43m    \u001b[49m\u001b[43msep\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msep\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3968\u001b[0m \u001b[43m    \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3969\u001b[0m \u001b[43m    \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3970\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcompression\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcompression\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3971\u001b[0m \u001b[43m    \u001b[49m\u001b[43mquoting\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mquoting\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3972\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcolumns\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcolumns\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3973\u001b[0m \u001b[43m    \u001b[49m\u001b[43mindex_label\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mindex_label\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3974\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3975\u001b[0m \u001b[43m    \u001b[49m\u001b[43mchunksize\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mchunksize\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3976\u001b[0m \u001b[43m    \u001b[49m\u001b[43mquotechar\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mquotechar\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3977\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdate_format\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdate_format\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3978\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdoublequote\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdoublequote\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3979\u001b[0m \u001b[43m    \u001b[49m\u001b[43mescapechar\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mescapechar\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3980\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstorage_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3981\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32md:\\Python\\Lib\\site-packages\\pandas\\io\\formats\\format.py:1014\u001b[0m, in \u001b[0;36mDataFrameRenderer.to_csv\u001b[1;34m(self, path_or_buf, encoding, sep, columns, index_label, mode, compression, quoting, quotechar, lineterminator, chunksize, date_format, doublequote, escapechar, errors, storage_options)\u001b[0m\n\u001b[0;32m    993\u001b[0m     created_buffer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[0;32m    995\u001b[0m csv_formatter \u001b[38;5;241m=\u001b[39m CSVFormatter(\n\u001b[0;32m    996\u001b[0m     path_or_buf\u001b[38;5;241m=\u001b[39mpath_or_buf,\n\u001b[0;32m    997\u001b[0m     lineterminator\u001b[38;5;241m=\u001b[39mlineterminator,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   1012\u001b[0m     formatter\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfmt,\n\u001b[0;32m   1013\u001b[0m )\n\u001b[1;32m-> 1014\u001b[0m \u001b[43mcsv_formatter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msave\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1016\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m created_buffer:\n\u001b[0;32m   1017\u001b[0m     \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(path_or_buf, StringIO)\n",
+      "File \u001b[1;32md:\\Python\\Lib\\site-packages\\pandas\\io\\formats\\csvs.py:251\u001b[0m, in \u001b[0;36mCSVFormatter.save\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    247\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    248\u001b[0m \u001b[38;5;124;03mCreate the writer & save.\u001b[39;00m\n\u001b[0;32m    249\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    250\u001b[0m \u001b[38;5;66;03m# apply compression and byte/text conversion\u001b[39;00m\n\u001b[1;32m--> 251\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[43mget_handle\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    252\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    253\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    254\u001b[0m \u001b[43m    \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    255\u001b[0m \u001b[43m    \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    256\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcompression\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcompression\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    257\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstorage_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    258\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mas\u001b[39;00m handles:\n\u001b[0;32m    259\u001b[0m     \u001b[38;5;66;03m# Note: self.encoding is irrelevant here\u001b[39;00m\n\u001b[0;32m    260\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mwriter \u001b[38;5;241m=\u001b[39m csvlib\u001b[38;5;241m.\u001b[39mwriter(\n\u001b[0;32m    261\u001b[0m         handles\u001b[38;5;241m.\u001b[39mhandle,\n\u001b[0;32m    262\u001b[0m         lineterminator\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlineterminator,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    267\u001b[0m         quotechar\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mquotechar,\n\u001b[0;32m    268\u001b[0m     )\n\u001b[0;32m    270\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_save()\n",
+      "File \u001b[1;32md:\\Python\\Lib\\site-packages\\pandas\\io\\common.py:749\u001b[0m, in \u001b[0;36mget_handle\u001b[1;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[0;32m    747\u001b[0m \u001b[38;5;66;03m# Only for write methods\u001b[39;00m\n\u001b[0;32m    748\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mr\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m mode \u001b[38;5;129;01mand\u001b[39;00m is_path:\n\u001b[1;32m--> 749\u001b[0m     \u001b[43mcheck_parent_directory\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mstr\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mhandle\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    751\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m compression:\n\u001b[0;32m    752\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m compression \u001b[38;5;241m!=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mzstd\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[0;32m    753\u001b[0m         \u001b[38;5;66;03m# compression libraries do not like an explicit text-mode\u001b[39;00m\n",
+      "File \u001b[1;32md:\\Python\\Lib\\site-packages\\pandas\\io\\common.py:616\u001b[0m, in \u001b[0;36mcheck_parent_directory\u001b[1;34m(path)\u001b[0m\n\u001b[0;32m    614\u001b[0m parent \u001b[38;5;241m=\u001b[39m Path(path)\u001b[38;5;241m.\u001b[39mparent\n\u001b[0;32m    615\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m parent\u001b[38;5;241m.\u001b[39mis_dir():\n\u001b[1;32m--> 616\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mOSError\u001b[39;00m(\u001b[38;5;124mrf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCannot save file into a non-existent directory: \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mparent\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+      "\u001b[1;31mOSError\u001b[0m: Cannot save file into a non-existent directory: '\\content\\drive\\MyDrive\\SIH2024_DATASET'"
+     ]
+    }
+   ],
+   "source": [
+    "df.to_csv( \"full_features.csv\", index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "3PTTLrLhJVRc"
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "gpuType": "T4",
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

feature_extraction.ipynb

@@ -0,0 +1,429 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "H3eVgsMsJVRY",
+    "outputId": "daa7d2ac-02a4-4258-897f-2b1dbdfa7a28"
+   },
+   "outputs": [],
+   "source": [
+    "from moviepy.editor import VideoFileClip\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import scipy.stats\n",
+    "import pandas as pd\n",
+    "import glob\n",
+    "import json\n",
+    "import librosa\n",
+    "import soundfile as sf\n",
+    "import io\n",
+    "import os\n",
+    "from tqdm import tqdm\n",
+    "import pickle as pk"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "3A9iF-QXJVRZ"
+   },
+   "source": [
+    "Statistical Features  \n",
+    "A first easy step is to compute the mean, standard deviation, minimum, maximum, median and quartiles of the frequencies of each signal. This can be done using Numpy and it always brings value to our feature extraction."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "id": "ibnbShbMJVRa"
+   },
+   "outputs": [],
+   "source": [
+    "# freqs = np.fft.fftfreq(x.size)\n",
+    "\n",
+    "# def describe_freq(freqs):\n",
+    "#     mean = np.mean(freqs)\n",
+    "#     std = np.std(freqs)\n",
+    "#     maxv = np.amax(freqs)\n",
+    "#     minv = np.amin(freqs)\n",
+    "#     median = np.median(freqs)\n",
+    "#     skew = scipy.stats.skew(freqs)\n",
+    "#     kurt = scipy.stats.kurtosis(freqs)\n",
+    "#     q1 = np.quantile(freqs, 0.25)\n",
+    "#     q3 = np.quantile(freqs, 0.75)\n",
+    "#     mode = scipy.stats.mode(freqs)[0][0]\n",
+    "#     iqr = scipy.stats.iqr(freqs)\n",
+    "\n",
+    "#     return [mean, std, maxv, minv, median, skew, kurt, q1, q3, mode, iqr]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "id": "nNifSVyDJVRa"
+   },
+   "outputs": [],
+   "source": [
+    "# def get_features(x, sr):\n",
+    "#     rmse = np.mean(librosa.feature.rms(y=x)[0])\n",
+    "#     zcr = np.mean(librosa.feature.zero_crossing_rate(x)[0])\n",
+    "#     tempo = librosa.beat.tempo(y=x, sr=sr)[0]\n",
+    "#     mfcc = list(np.mean(librosa.feature.mfcc(y=x, sr=sr), axis=1))\n",
+    "#     spec_cen = np.mean(librosa.feature.spectral_centroid(y=x, sr=sr))\n",
+    "#     spectral_bandwidth = np.mean(librosa.feature.spectral_bandwidth(y=x, sr=sr))\n",
+    "#     spectral_contrast = np.mean(librosa.feature.spectral_contrast(y=x, sr=sr))\n",
+    "#     spectral_flatness = np.mean(librosa.feature.spectral_flatness(y=x))\n",
+    "#     spectral_rolloff = np.mean(librosa.feature.spectral_rolloff(y=x, sr=sr))\n",
+    "#     features = [rmse, zcr, tempo, spec_cen, spectral_bandwidth, spectral_contrast, spectral_flatness, spectral_rolloff]\n",
+    "#     return features + mfcc"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "id": "nL9J7Vp9JVRa"
+   },
+   "outputs": [],
+   "source": [
+    "fake_audio_dir = (\n",
+    "    r\"H:\\.shortcut-targets-by-id\\1jH_pc6mMj0Iu8wLS1r0vggMWpVElJvOU\\SIH2024_DATASET\\FAKE\"\n",
+    ")\n",
+    "real_audio_dir = (\n",
+    "    r\"H:\\.shortcut-targets-by-id\\1jH_pc6mMj0Iu8wLS1r0vggMWpVElJvOU\\SIH2024_DATASET\\REAL\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "real_files = os.listdir(real_audio_dir)\n",
+    "fake_files = os.listdir(fake_audio_dir)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\n",
+    "    r\"H:\\.shortcut-targets-by-id\\1jH_pc6mMj0Iu8wLS1r0vggMWpVElJvOU\\SIH2024_DATASET\\real_files.pkl\",\n",
+    "    \"wb\",\n",
+    ") as f:\n",
+    "    pk.dump(real_files, f)\n",
+    "\n",
+    "with open(\n",
+    "    r\"H:\\.shortcut-targets-by-id\\1jH_pc6mMj0Iu8wLS1r0vggMWpVElJvOU\\SIH2024_DATASET\\fake_files.pkl\",\n",
+    "    \"wb\",\n",
+    ") as f:\n",
+    "    pk.dump(fake_files, f)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\n",
+    "    r\"H:\\.shortcut-targets-by-id\\1jH_pc6mMj0Iu8wLS1r0vggMWpVElJvOU\\SIH2024_DATASET\\real_files.pkl\",\n",
+    "    \"rb\",\n",
+    ") as f:\n",
+    "    real_files = pk.load(f)\n",
+    "\n",
+    "with open(\n",
+    "    r\"H:\\.shortcut-targets-by-id\\1jH_pc6mMj0Iu8wLS1r0vggMWpVElJvOU\\SIH2024_DATASET\\fake_files.pkl\",\n",
+    "    \"rb\",\n",
+    ") as f:\n",
+    "    fake_files = pk.load(f)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "total_files = len(real_files) + len(fake_files)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "id": "BUS-nOHOJVRb"
+   },
+   "outputs": [],
+   "source": [
+    "def get_features(x, sr):\n",
+    "    \"\"\"Extract audio features from the audio signal.\"\"\"\n",
+    "    rmse = np.mean(librosa.feature.rms(y=x)[0])\n",
+    "    zcr = np.mean(librosa.feature.zero_crossing_rate(x)[0])\n",
+    "    tempo = librosa.beat.tempo(y=x, sr=sr)[0]\n",
+    "    mfcc = list(np.mean(librosa.feature.mfcc(y=x, sr=sr), axis=1))\n",
+    "    spec_cen = np.mean(librosa.feature.spectral_centroid(y=x, sr=sr))\n",
+    "    spectral_bandwidth = np.mean(librosa.feature.spectral_bandwidth(y=x, sr=sr))\n",
+    "    spectral_contrast = np.mean(librosa.feature.spectral_contrast(y=x, sr=sr))\n",
+    "    spectral_flatness = np.mean(librosa.feature.spectral_flatness(y=x))\n",
+    "    spectral_rolloff = np.mean(librosa.feature.spectral_rolloff(y=x, sr=sr))\n",
+    "    features = [\n",
+    "        rmse,\n",
+    "        zcr,\n",
+    "        tempo,\n",
+    "        spec_cen,\n",
+    "        spectral_bandwidth,\n",
+    "        spectral_contrast,\n",
+    "        spectral_flatness,\n",
+    "        spectral_rolloff,\n",
+    "    ]\n",
+    "    return features + mfcc\n",
+    "\n",
+    "\n",
+    "def extract_features(file_path):\n",
+    "    \"\"\"Extract features from a video file.\"\"\"\n",
+    "    try:\n",
+    "        # Load the video file\n",
+    "        video_clip = VideoFileClip(file_path)\n",
+    "        audio = video_clip.audio\n",
+    "        fps = audio.fps\n",
+    "        audio_samples = np.array(\n",
+    "            list(audio.iter_frames(fps=fps, dtype=\"float32\"))\n",
+    "        ).flatten()\n",
+    "        buffer = io.BytesIO()\n",
+    "        sf.write(buffer, audio_samples, fps, format=\"wav\")\n",
+    "        buffer.seek(0)\n",
+    "        x, sr = librosa.load(buffer, sr=None)\n",
+    "        video_clip.close()  # Close the video file\n",
+    "        features = get_features(x, sr)\n",
+    "        return features\n",
+    "\n",
+    "    except Exception as e:\n",
+    "        print(f\"Error encountered while parsing file: {file_path}, {e}\")\n",
+    "        return None\n",
+    "\n",
+    "\n",
+    "def load_data(real_dir, fake_dir, real_files, fake_files):\n",
+    "    \"\"\"Load and process audio files from real and fake directories.\"\"\"\n",
+    "    data = []\n",
+    "\n",
+    "    # Define column names\n",
+    "    columns = (\n",
+    "        [\n",
+    "            \"rmse\",\n",
+    "            \"zcr\",\n",
+    "            \"tempo\",\n",
+    "            \"spectral_centroid\",\n",
+    "            \"spectral_bandwidth\",\n",
+    "            \"spectral_contrast\",\n",
+    "            \"spectral_flatness\",\n",
+    "            \"spectral_rolloff\",\n",
+    "        ]\n",
+    "        + [f\"mfcc{i}\" for i in range(1, 21)]\n",
+    "        + [\"label\"]\n",
+    "    )\n",
+    "\n",
+    "    # Get total number of files for progress bar\n",
+    "    total_files = len(real_files) + len(fake_files)\n",
+    "\n",
+    "    # Create progress bar\n",
+    "    pbar = tqdm(total=total_files, desc=\"Processing files\", unit=\"file\")\n",
+    "\n",
+    "    # Process real audio files\n",
+    "    for file_name in real_files:\n",
+    "        file_path = os.path.join(real_dir, file_name)\n",
+    "        features = extract_features(file_path)\n",
+    "        if features is not None:\n",
+    "            features.append(0)  # 0 for REAL\n",
+    "            data.append(features)\n",
+    "        pbar.update(1)\n",
+    "        pbar.set_postfix({\"Current file\": file_name[:20]})\n",
+    "\n",
+    "    # Process fake audio files\n",
+    "    for file_name in fake_files:\n",
+    "        file_path = os.path.join(fake_dir, file_name)\n",
+    "        features = extract_features(file_path)\n",
+    "        if features is not None:\n",
+    "            features.append(1)  # 1 for FAKE\n",
+    "            data.append(features)\n",
+    "        pbar.update(1)\n",
+    "        pbar.set_postfix({\"Current file\": file_name[:20]})\n",
+    "\n",
+    "    pbar.close()\n",
+    "\n",
+    "    # Create DataFrame with the collected data\n",
+    "    df = pd.DataFrame(data, columns=columns)\n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "id": "1cxXpFqCJVRb"
+   },
+   "outputs": [],
+   "source": [
+    "df = pd.DataFrame(\n",
+    "    columns=[\n",
+    "        \"rmse\",\n",
+    "        \"zcr\",\n",
+    "        \"tempo\",\n",
+    "        \"spectral_centroid\",\n",
+    "        \"spectral_bandwidth\",\n",
+    "        \"spectral_contrast\",\n",
+    "        \"spectral_flatness\",\n",
+    "        \"spectral_rolloff\",\n",
+    "        \"mfcc1\",\n",
+    "        \"mfcc2\",\n",
+    "        \"mfcc3\",\n",
+    "        \"mfcc4\",\n",
+    "        \"mfcc5\",\n",
+    "        \"mfcc6\",\n",
+    "        \"mfcc7\",\n",
+    "        \"mfcc8\",\n",
+    "        \"mfcc9\",\n",
+    "        \"mfcc10\",\n",
+    "        \"mfcc11\",\n",
+    "        \"mfcc12\",\n",
+    "        \"mfcc13\",\n",
+    "        \"mfcc14\",\n",
+    "        \"mfcc15\",\n",
+    "        \"mfcc16\",\n",
+    "        \"mfcc17\",\n",
+    "        \"mfcc18\",\n",
+    "        \"mfcc19\",\n",
+    "        \"mfcc20\",\n",
+    "        \"label\",]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "id": "fSpp-6btJVRb"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Processing files:   0%|          | 15/119148 [01:07<176:25:02,  5.33s/file, Current file=ehgdzhkdvo.mp4]"
+     ]
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[11], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m df \u001b[38;5;241m=\u001b[39m \u001b[43mload_data\u001b[49m\u001b[43m(\u001b[49m\u001b[43mreal_audio_dir\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfake_audio_dir\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mreal_files\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfake_files\u001b[49m\u001b[43m)\u001b[49m\n",
+      "Cell \u001b[1;32mIn[9], line 77\u001b[0m, in \u001b[0;36mload_data\u001b[1;34m(real_dir, fake_dir, real_files, fake_files)\u001b[0m\n\u001b[0;32m     75\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m file_name \u001b[38;5;129;01min\u001b[39;00m real_files:\n\u001b[0;32m     76\u001b[0m     file_path \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(real_dir, file_name)\n\u001b[1;32m---> 77\u001b[0m     features \u001b[38;5;241m=\u001b[39m \u001b[43mextract_features\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfile_path\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     78\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m features \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m     79\u001b[0m         features\u001b[38;5;241m.\u001b[39mappend(\u001b[38;5;241m0\u001b[39m)  \u001b[38;5;66;03m# 0 for REAL\u001b[39;00m\n",
+      "Cell \u001b[1;32mIn[9], line 29\u001b[0m, in \u001b[0;36mextract_features\u001b[1;34m(file_path)\u001b[0m\n\u001b[0;32m     26\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Extract features from a video file.\"\"\"\u001b[39;00m\n\u001b[0;32m     27\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m     28\u001b[0m     \u001b[38;5;66;03m# Load the video file\u001b[39;00m\n\u001b[1;32m---> 29\u001b[0m     video_clip \u001b[38;5;241m=\u001b[39m \u001b[43mVideoFileClip\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfile_path\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     30\u001b[0m     audio \u001b[38;5;241m=\u001b[39m video_clip\u001b[38;5;241m.\u001b[39maudio\n\u001b[0;32m     31\u001b[0m     fps \u001b[38;5;241m=\u001b[39m audio\u001b[38;5;241m.\u001b[39mfps\n",
+      "File \u001b[1;32md:\\Python\\Lib\\site-packages\\moviepy\\video\\io\\VideoFileClip.py:88\u001b[0m, in \u001b[0;36mVideoFileClip.__init__\u001b[1;34m(self, filename, has_mask, audio, audio_buffersize, target_resolution, resize_algorithm, audio_fps, audio_nbytes, verbose, fps_source)\u001b[0m\n\u001b[0;32m     86\u001b[0m \u001b[38;5;66;03m# Make a reader\u001b[39;00m\n\u001b[0;32m     87\u001b[0m pix_fmt \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrgba\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m has_mask \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrgb24\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m---> 88\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mreader \u001b[38;5;241m=\u001b[39m \u001b[43mFFMPEG_VideoReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpix_fmt\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpix_fmt\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m     89\u001b[0m \u001b[43m                                 \u001b[49m\u001b[43mtarget_resolution\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtarget_resolution\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m     90\u001b[0m \u001b[43m                                 \u001b[49m\u001b[43mresize_algo\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresize_algorithm\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m     91\u001b[0m \u001b[43m                                 \u001b[49m\u001b[43mfps_source\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfps_source\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     93\u001b[0m \u001b[38;5;66;03m# Make some of the reader's attributes accessible from the clip\u001b[39;00m\n\u001b[0;32m     94\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mduration \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mreader\u001b[38;5;241m.\u001b[39mduration\n",
+      "File \u001b[1;32md:\\Python\\Lib\\site-packages\\moviepy\\video\\io\\ffmpeg_reader.py:35\u001b[0m, in \u001b[0;36mFFMPEG_VideoReader.__init__\u001b[1;34m(self, filename, print_infos, bufsize, pix_fmt, check_duration, target_resolution, resize_algo, fps_source)\u001b[0m\n\u001b[0;32m     33\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfilename \u001b[38;5;241m=\u001b[39m filename\n\u001b[0;32m     34\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mproc \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m---> 35\u001b[0m infos \u001b[38;5;241m=\u001b[39m \u001b[43mffmpeg_parse_infos\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mprint_infos\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcheck_duration\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m     36\u001b[0m \u001b[43m                           \u001b[49m\u001b[43mfps_source\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     37\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfps \u001b[38;5;241m=\u001b[39m infos[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mvideo_fps\u001b[39m\u001b[38;5;124m'\u001b[39m]\n\u001b[0;32m     38\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msize \u001b[38;5;241m=\u001b[39m infos[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mvideo_size\u001b[39m\u001b[38;5;124m'\u001b[39m]\n",
+      "File \u001b[1;32md:\\Python\\Lib\\site-packages\\moviepy\\video\\io\\ffmpeg_reader.py:258\u001b[0m, in \u001b[0;36mffmpeg_parse_infos\u001b[1;34m(filename, print_infos, check_duration, fps_source)\u001b[0m\n\u001b[0;32m    255\u001b[0m     popen_params[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcreationflags\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0x08000000\u001b[39m\n\u001b[0;32m    257\u001b[0m proc \u001b[38;5;241m=\u001b[39m sp\u001b[38;5;241m.\u001b[39mPopen(cmd, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mpopen_params)\n\u001b[1;32m--> 258\u001b[0m (output, error) \u001b[38;5;241m=\u001b[39m \u001b[43mproc\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcommunicate\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    259\u001b[0m infos \u001b[38;5;241m=\u001b[39m error\u001b[38;5;241m.\u001b[39mdecode(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mutf8\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m    261\u001b[0m \u001b[38;5;28;01mdel\u001b[39;00m proc\n",
+      "File \u001b[1;32md:\\Python\\Lib\\subprocess.py:1209\u001b[0m, in \u001b[0;36mPopen.communicate\u001b[1;34m(self, input, timeout)\u001b[0m\n\u001b[0;32m   1206\u001b[0m     endtime \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m   1208\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m-> 1209\u001b[0m     stdout, stderr \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_communicate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mendtime\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1210\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mKeyboardInterrupt\u001b[39;00m:\n\u001b[0;32m   1211\u001b[0m     \u001b[38;5;66;03m# https://bugs.python.org/issue25942\u001b[39;00m\n\u001b[0;32m   1212\u001b[0m     \u001b[38;5;66;03m# See the detailed comment in .wait().\u001b[39;00m\n\u001b[0;32m   1213\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m timeout \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
+      "File \u001b[1;32md:\\Python\\Lib\\subprocess.py:1626\u001b[0m, in \u001b[0;36mPopen._communicate\u001b[1;34m(self, input, endtime, orig_timeout)\u001b[0m\n\u001b[0;32m   1622\u001b[0m \u001b[38;5;66;03m# Wait for the reader threads, or time out.  If we time out, the\u001b[39;00m\n\u001b[0;32m   1623\u001b[0m \u001b[38;5;66;03m# threads remain reading and the fds left open in case the user\u001b[39;00m\n\u001b[0;32m   1624\u001b[0m \u001b[38;5;66;03m# calls communicate again.\u001b[39;00m\n\u001b[0;32m   1625\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstdout \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m-> 1626\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstdout_thread\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mjoin\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_remaining_time\u001b[49m\u001b[43m(\u001b[49m\u001b[43mendtime\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1627\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstdout_thread\u001b[38;5;241m.\u001b[39mis_alive():\n\u001b[0;32m   1628\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m TimeoutExpired(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs, orig_timeout)\n",
+      "File \u001b[1;32md:\\Python\\Lib\\threading.py:1147\u001b[0m, in \u001b[0;36mThread.join\u001b[1;34m(self, timeout)\u001b[0m\n\u001b[0;32m   1144\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcannot join current thread\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m   1146\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m timeout \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m-> 1147\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_wait_for_tstate_lock\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1148\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m   1149\u001b[0m     \u001b[38;5;66;03m# the behavior of a negative timeout isn't documented, but\u001b[39;00m\n\u001b[0;32m   1150\u001b[0m     \u001b[38;5;66;03m# historically .join(timeout=x) for x<0 has acted as if timeout=0\u001b[39;00m\n\u001b[0;32m   1151\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_wait_for_tstate_lock(timeout\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mmax\u001b[39m(timeout, \u001b[38;5;241m0\u001b[39m))\n",
+      "File \u001b[1;32md:\\Python\\Lib\\threading.py:1167\u001b[0m, in \u001b[0;36mThread._wait_for_tstate_lock\u001b[1;34m(self, block, timeout)\u001b[0m\n\u001b[0;32m   1164\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m\n\u001b[0;32m   1166\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m-> 1167\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[43mlock\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43macquire\u001b[49m\u001b[43m(\u001b[49m\u001b[43mblock\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m)\u001b[49m:\n\u001b[0;32m   1168\u001b[0m         lock\u001b[38;5;241m.\u001b[39mrelease()\n\u001b[0;32m   1169\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_stop()\n",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
+     ]
+    }
+   ],
+   "source": [
+    "df = load_data(real_audio_dir, fake_audio_dir, real_files, fake_files)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "3tLFhSuVJVRc"
+   },
+   "outputs": [],
+   "source": [
+    "df.tail()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "zMej7SKRJVRc"
+   },
+   "outputs": [],
+   "source": [
+    "# for file in file_names:\n",
+    "\n",
+    "#     clean_file = file.split(\"/\")[-1]\n",
+    "#     video_clip = VideoFileClip(file)\n",
+    "#     audio = video_clip.audio\n",
+    "#     fps = audio.fps\n",
+    "#     audio_samples = np.array(list(audio.iter_frames(fps=fps, dtype=\"float32\"))).flatten()\n",
+    "#     buffer = io.BytesIO()\n",
+    "#     sf.write(buffer, audio_samples, fps, format='wav')\n",
+    "#     buffer.seek(0)\n",
+    "#     x, sr = librosa.load(buffer, sr=None)\n",
+    "#     label = json.load(open(\"train_sample_videos/metadata.json\"))[clean_file]['label']\n",
+    "#     new_row = pd.DataFrame([[clean_file] + get_features(x, sr) + [label]], columns=column_ames)\n",
+    "#     df = pd.concat([df, new_row], ignore_index=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "BxacOcTrJVRc"
+   },
+   "outputs": [],
+   "source": [
+    "df.to_csv( \"/content/drive/MyDrive/SIH2024_DATASET/full_features.csv\", index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "3PTTLrLhJVRc"
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

test.py

@@ -0,0 +1,80 @@
+import numpy as np
+import soundfile as sf
+import librosa
+import io
+from moviepy.editor import VideoFileClip
+from tensorflow.keras.models import load_model
+
+def extract_frame_features(file_path, frame_duration=1.0):
+    video_clip = VideoFileClip(file_path)
+    audio = video_clip.audio
+    fps = audio.fps
+    audio_samples = np.array(
+        list(audio.iter_frames(fps=fps, dtype="float32"))
+    ).flatten()
+    buffer = io.BytesIO()
+    sf.write(buffer, audio_samples, fps, format="wav")
+    buffer.seek(0)
+    x, sr = librosa.load(buffer, sr=None)
+
+    # Split audio into frames of 'frame_duration' seconds
+    frame_length = int(frame_duration * sr)
+    frames = []
+    timestamps = []
+
+    for i in range(0, len(x), frame_length):
+        if i + frame_length <= len(x):
+            # Extract MFCCs for each frame and store the timestamp
+            frame_mfcc = librosa.feature.mfcc(
+                y=x[i : i + frame_length], sr=sr, n_mfcc=20
+            )
+            frames.append(frame_mfcc)
+            timestamp = i / sr  # Convert index to seconds
+            timestamps.append(timestamp)
+
+    return frames, timestamps
+
+
+def test_on_video(file_path, frame_duration=1.0):
+    # Load the trained model
+    model = load_model("model/TCN.keras")
+
+    # Extract features and timestamps for each frame in the new video
+    frames, timestamps = extract_frame_features(file_path, frame_duration)
+
+    if frames is None or timestamps is None:
+        print("No frames extracted.")
+        return
+
+    # Reshape frames for model input
+    frames = np.array(frames)[..., np.newaxis]
+
+    # Predict on each frame
+    predictions = model.predict(frames)
+    pred_labels = np.argmax(predictions, axis=1)
+
+    # Store deepfake frames, their timestamps, and frame indices
+    deepfake_frames = []
+    deepfake_timestamps = []
+    deepfake_indices = []
+
+    # Identify deepfake frames
+    for i, label in enumerate(pred_labels):
+        if label == 1:  # If the label is FAKE
+            deepfake_frames.append(frames[i])
+            deepfake_timestamps.append(timestamps[i])
+            deepfake_indices.append(i)
+
+    if not deepfake_frames:
+        print("No deepfake frames detected in the video.")
+        return
+
+    # Analyze deepfake frames
+    print(f"Found {len(deepfake_frames)} deepfake frames:")
+    for i, (timestamp, index) in enumerate(zip(deepfake_timestamps, deepfake_indices)):
+        print(f"Frame {index + 1} at {timestamp:.2f}s: FAKE")
+
+
+# Example usage
+test_video_path = r"FAKE\aapnvogymq.mp4"  # Replace with your test video path
+test_on_video(test_video_path)

y.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33f0a69b3bda0a6b9d709ebd3c298fcf70a5dc3637059ce3c992a698f7e9819
+size 11991

y_for_dl_2000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7547dbf58339beaafcb6600307cd8bbce204aa46c3a4edfa5864eb043ca232e8
+size 320002