File size: 10,313 Bytes
45b200f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
{
 "cells": [
  {
   "cell_type": "code",
   "id": "6369bdabdf59b658",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-06-10T20:28:20.833977Z",
     "start_time": "2025-06-10T20:28:14.932967Z"
    }
   },
   "source": [
    "from langchain.document_loaders import YoutubeLoader\n",
    "from langchain_yt_dlp.youtube_loader import YoutubeLoaderDL\n",
    "from globals import *\n",
    "import torch\n",
    "import torchaudio.transforms as T\n",
    "import pydub\n",
    "import numpy as np\n",
    "from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor"
   ],
   "outputs": [],
   "execution_count": 33
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-06-10T20:05:04.414620Z",
     "start_time": "2025-06-10T20:05:04.412354Z"
    }
   },
   "cell_type": "code",
   "source": "url = \"https://www.youtube.com/watch?v=1htKBjuUWec\"\n",
   "id": "666e521f8ecf3f47",
   "outputs": [],
   "execution_count": 14
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-06-10T20:26:57.491908Z",
     "start_time": "2025-06-10T20:26:57.489481Z"
    }
   },
   "cell_type": "code",
   "source": [
    "# Load transcript as LangChain Documents\n",
    "# loader = YoutubeLoader.from_youtube_url(url, add_video_info=False)\n",
    "# loader = YoutubeLoaderDL.from_youtube_url(\n",
    "#     url, add_video_info=True\n",
    "# )\n",
    "# docs = loader.load()\n",
    "#\n",
    "# # Print the transcript content\n",
    "# for doc in docs:\n",
    "#     print(doc.page_content)\n",
    "\n",
    "# Optionally, save to a file\n",
    "# with open(\"transcript.txt\", \"w\", encoding=\"utf-8\") as f:\n",
    "#     for doc in docs:\n",
    "#         f.write(doc.page_content)"
   ],
   "id": "initial_id",
   "outputs": [],
   "execution_count": 30
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-06-10T20:27:03.519450Z",
     "start_time": "2025-06-10T20:27:03.517474Z"
    }
   },
   "cell_type": "code",
   "source": [
    "# from pytube import YouTube\n",
    "#\n",
    "# yt = YouTube(url)\n",
    "#\n",
    "# # Download the audio stream (usually mp4)\n",
    "# stream = yt.streams.filter(only_audio=True).first()\n",
    "# stream.download(firstilename=f\"{yt.title}.mp3\")"
   ],
   "id": "ec4885c3a15d9a2b",
   "outputs": [],
   "execution_count": 31
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-06-10T20:04:18.601366Z",
     "start_time": "2025-06-10T20:04:18.597488Z"
    }
   },
   "cell_type": "code",
   "source": [
    "import ssl\n",
    "import certifi\n",
    "# Correct: assign a lambda (function) that returns a properly configured SSL context\n",
    "ssl._create_default_https_context = lambda: ssl.create_default_context(cafile=certifi.where())"
   ],
   "id": "167af702547c15e4",
   "outputs": [],
   "execution_count": 12
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-06-10T20:07:53.667018Z",
     "start_time": "2025-06-10T20:07:52.627871Z"
    }
   },
   "cell_type": "code",
   "source": [
    "\n",
    "from pytube import YouTube\n",
    "\n",
    "def download_video(url, output_path='.'):\n",
    "    try:\n",
    "        yt = YouTube(url)\n",
    "        print('here')\n",
    "        stream = yt.streams.get_highest_resolution()\n",
    "        print(f\"Downloading: {yt.title}\")\n",
    "        stream.download(output_path=output_path)\n",
    "        print(\"Download completed.\")\n",
    "    except Exception as e:\n",
    "        print(f\"Error: {e}\")\n",
    "\n",
    "# Example usage\n",
    "download_video(url)"
   ],
   "id": "289b9a4321ea487b",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "here\n",
      "Error: HTTP Error 400: Bad Request\n"
     ]
    }
   ],
   "execution_count": 23
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-06-10T20:08:47.590897Z",
     "start_time": "2025-06-10T20:08:44.115350Z"
    }
   },
   "cell_type": "code",
   "source": [
    "import yt_dlp\n",
    "\n",
    "ydl_opts = {\n",
    "    'format': 'best',  # or 'bestvideo+bestaudio'\n",
    "    'outtmpl': '%(title)s.%(ext)s',  # save as video title\n",
    "}\n",
    "\n",
    "with yt_dlp.YoutubeDL(ydl_opts) as ydl:\n",
    "    ydl.download([url])"
   ],
   "id": "4eb045792318e67a",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[youtube] Extracting URL: https://www.youtube.com/watch?v=1htKBjuUWec\n",
      "[youtube] 1htKBjuUWec: Downloading webpage\n",
      "[youtube] 1htKBjuUWec: Downloading tv client config\n",
      "[youtube] 1htKBjuUWec: Downloading tv player API JSON\n",
      "[youtube] 1htKBjuUWec: Downloading ios player API JSON\n",
      "[youtube] 1htKBjuUWec: Downloading m3u8 information\n",
      "[info] 1htKBjuUWec: Downloading 1 format(s): 18\n",
      "[download] Destination: Teal'c coffee first time.mp4\n",
      "[download] 100% of    1.19MiB in 00:00:01 at 1.09MiB/s   \n"
     ]
    }
   ],
   "execution_count": 24
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-06-10T20:22:32.706482Z",
     "start_time": "2025-06-10T20:22:29.843517Z"
    }
   },
   "cell_type": "code",
   "source": [
    "import yt_dlp\n",
    "\n",
    "file_name = 'my_audio_file'\n",
    "ydl_opts = {\n",
    "    'format': 'bestaudio/best',\n",
    "    'outtmpl': f'files/{file_name}.%(ext)s',  # <-- set your custom filename here\n",
    "    'postprocessors': [{\n",
    "        'key': 'FFmpegExtractAudio',\n",
    "        'preferredcodec': 'mp3',\n",
    "        'preferredquality': '192',\n",
    "    }],\n",
    "}\n",
    "\n",
    "with yt_dlp.YoutubeDL(ydl_opts) as ydl:\n",
    "    ydl.download([url])"
   ],
   "id": "68b51ca78254d8f",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[youtube] Extracting URL: https://www.youtube.com/watch?v=1htKBjuUWec\n",
      "[youtube] 1htKBjuUWec: Downloading webpage\n",
      "[youtube] 1htKBjuUWec: Downloading tv client config\n",
      "[youtube] 1htKBjuUWec: Downloading tv player API JSON\n",
      "[youtube] 1htKBjuUWec: Downloading ios player API JSON\n",
      "[youtube] 1htKBjuUWec: Downloading m3u8 information\n",
      "[info] 1htKBjuUWec: Downloading 1 format(s): 251\n",
      "[download] Destination: files/my_audio_file.webm\n",
      "[download] 100% of  444.93KiB in 00:00:00 at 3.41MiB/s     \n",
      "[ExtractAudio] Destination: files/my_audio_file.mp3\n",
      "Deleting original file files/my_audio_file.webm (pass -k to keep)\n"
     ]
    }
   ],
   "execution_count": 26
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-06-10T20:35:23.558866Z",
     "start_time": "2025-06-10T20:35:23.515883Z"
    }
   },
   "cell_type": "code",
   "source": [
    "audio_model_dir = './models_for_proj/wav2vec2-base-960h'\n",
    "model = Wav2Vec2ForCTC.from_pretrained(audio_model_dir)\n",
    "processor = Wav2Vec2Processor.from_pretrained(audio_model_dir)\n",
    "\n",
    "def read_mp3(f, normalized=False):\n",
    "    \"\"\"Read MP3 file to numpy array.\"\"\"\n",
    "    a = pydub.AudioSegment.from_mp3(f)\n",
    "    y = np.array(a.get_array_of_samples())\n",
    "    if a.channels == 2:\n",
    "        y = y.reshape((-1, 2))\n",
    "        # y = y.mean(axis=1)\n",
    "        y = y[:,1]\n",
    "    if normalized:\n",
    "        return a.frame_rate, np.float32(y) / 2**15\n",
    "    else:\n",
    "        return a.frame_rate, y\n",
    "\n",
    "def describe_audio_tool(file_name: str) -> str:\n",
    "    \"\"\"\n",
    "    This tool receives a file name of an audio, uploads the audio and returns a detailed description of the audio.\n",
    "    Inputs: file_name as str\n",
    "    Outputs: audio detailed description as str\n",
    "    \"\"\"\n",
    "    # --------------------------------------------------------------------------- #\n",
    "    file_dir = f'files/{file_name}'\n",
    "    print(f\"{file_dir=}\")\n",
    "    audio_input_sr, audio_input_np = read_mp3(file_dir)\n",
    "    audio_input_t = torch.tensor(audio_input_np, dtype=torch.float32)\n",
    "    target_sr = 16000\n",
    "    resampler = T.Resample(audio_input_sr, target_sr, dtype=audio_input_t.dtype)\n",
    "    resampled_audio_input_t: torch.Tensor = resampler(audio_input_t)\n",
    "    resampled_audio_input_np = resampled_audio_input_t.numpy()\n",
    "    # --------------------------------------------------------------------------- #\n",
    "    inputs = processor(resampled_audio_input_np, sampling_rate=16000, return_tensors=\"pt\", padding=True)\n",
    "    # Inference\n",
    "    with torch.no_grad():\n",
    "        logits = model(**inputs).logits\n",
    "    # Decode\n",
    "    predicted_ids = torch.argmax(logits, dim=-1)\n",
    "    transcription = processor.decode(predicted_ids[0])\n",
    "    return transcription"
   ],
   "id": "64f438af2b38765f",
   "outputs": [],
   "execution_count": 43
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-06-10T20:35:27.235493Z",
     "start_time": "2025-06-10T20:35:26.202459Z"
    }
   },
   "cell_type": "code",
   "source": "describe_audio_tool(file_name=f'{file_name}.mp3')",
   "id": "b4a6ae10e1cbbcae",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "file_dir='files/my_audio_file.mp3'\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"ALIS COFFEE'S GRAY WO IS JUST THINKING  YET HE TAT SOMESCHICKERY A CHIC TEK H IS NOT HOT EXTREMELY\""
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 44
  },
  {
   "metadata": {},
   "cell_type": "code",
   "outputs": [],
   "execution_count": null,
   "source": "",
   "id": "ce9aaf764346b7e4"
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}