Skip to content

Instantly share code, notes, and snippets.

@pszemraj

pszemraj/gpu-test.ipynb

Created January 27, 2022 20:21
Show Gist options
  • Save pszemraj/e582ff122af497970191c3f25fa316c8 to your computer and use it in GitHub Desktop.
Save pszemraj/e582ff122af497970191c3f25fa316c8 to your computer and use it in GitHub Desktop.
Download ZIP
GPU-test.ipynb
Display the source blob
Display the rendered blob
Raw
gpu-test.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "GPU-test.ipynb",
"provenance": [],
"collapsed_sections": [],
"toc_visible": true,
"authorship_tag": "ABX9TyPaS96Hs/evflA9q8+2lr9Q",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/pszemraj/e582ff122af497970191c3f25fa316c8/gpu-test.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"source": [
"# testing vid2cleantxt.git --branch add-hubert on GPU"
],
"metadata": {
"id": "hvQjrhmE2965"
}
},
{
"cell_type": "markdown",
"metadata": {
"id": "GEvkyRhsHXK_"
},
"source": [
"## system setups"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"cellView": "form",
"id": "846niMokUVnR",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "9c93e7a4-0342-4fa0-e2f8-99d2847453f8"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Thu Jan 27 19:21:20 2022 \n",
"+-----------------------------------------------------------------------------+\n",
"| NVIDIA-SMI 495.46 Driver Version: 460.32.03 CUDA Version: 11.2 |\n",
"|-------------------------------+----------------------+----------------------+\n",
"| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |\n",
"| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |\n",
"| | | MIG M. |\n",
"|===============================+======================+======================|\n",
"| 0 Tesla V100-SXM2... Off | 00000000:00:04.0 Off | 0 |\n",
"| N/A 36C P0 24W / 300W | 0MiB / 16160MiB | 0% Default |\n",
"| | | N/A |\n",
"+-------------------------------+----------------------+----------------------+\n",
" \n",
"+-----------------------------------------------------------------------------+\n",
"| Processes: |\n",
"| GPU GI CI PID Type Process name GPU Memory |\n",
"| ID ID Usage |\n",
"|=============================================================================|\n",
"| No running processes found |\n",
"+-----------------------------------------------------------------------------+\n"
]
}
],
"source": [
"#@title print GPU status\n",
"!nvidia-smi"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"cellView": "form",
"id": "vM8a4UHuKp_T"
},
"outputs": [],
"source": [
"#@markdown add auto-Colab formatting with `IPython.display`\n",
"from IPython.display import HTML, display\n",
"# colab formatting\n",
"def set_css():\n",
" display(\n",
" HTML(\n",
" \"\"\"\n",
" <style>\n",
" pre {\n",
" white-space: pre-wrap;\n",
" }\n",
" </style>\n",
" \"\"\"\n",
" )\n",
" )\n",
"\n",
"get_ipython().events.register(\"pre_run_cell\", set_css)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"cellView": "form",
"id": "HTRjl_eh2dUY",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 35
},
"outputId": "f92b3fd5-2587-449c-8c0d-0b6d869d99f8"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/html": [
"\n",
" <style>\n",
" pre {\n",
" white-space: pre-wrap;\n",
" }\n",
" </style>\n",
" "
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Runtime has 12.7 gigs of memory and 2 processors\n"
]
}
],
"source": [
"#@title print out the VM's CPU stats\n",
"from psutil import virtual_memory\n",
"import os\n",
"ram_gb = round(virtual_memory().total / (1024**3), 1)\n",
"print(f'Runtime has {ram_gb} gigs of memory and {os.cpu_count()} processors')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"id": "p3iOwI8kumJ3",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 160
},
"outputId": "4be15089-82c9-4484-82f9-e2e1066720ec"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/html": [
"\n",
" <style>\n",
" pre {\n",
" white-space: pre-wrap;\n",
" }\n",
" </style>\n",
" "
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Cloning into 'vid2cleantxt'...\n",
"remote: Enumerating objects: 88, done.\u001b[K\n",
"remote: Counting objects: 100% (88/88), done.\u001b[K\n",
"remote: Compressing objects: 100% (75/75), done.\u001b[K\n",
"remote: Total 88 (delta 13), reused 72 (delta 12), pack-reused 0\u001b[K\n",
"Unpacking objects: 100% (88/88), done.\n",
"colab_notebooks helper README.md\t vid2cleantxt\n",
"examples\t LICENSE requirements.txt\n"
]
}
],
"source": [
"!git clone https://github.com/pszemraj/vid2cleantxt.git --branch add-hubert --depth=1 \n",
"\n",
"import os\n",
"os.chdir('/content/vid2cleantxt')\n",
"!ls"
]
},
{
"cell_type": "code",
"source": [
"!pip install -r requirements.txt -q"
],
"metadata": {
"id": "LDapSQ15w_J2",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"outputId": "d3a6438d-5662-438b-ed2a-fb06d9159d78"
},
"execution_count": 5,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/html": [
"\n",
" <style>\n",
" pre {\n",
" white-space: pre-wrap;\n",
" }\n",
" </style>\n",
" "
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[K |████████████████████████████████| 13.7 MB 4.4 MB/s \n",
"\u001b[K |████████████████████████████████| 541 kB 4.3 MB/s \n",
"\u001b[K |████████████████████████████████| 296 kB 68.6 MB/s \n",
"\u001b[K |████████████████████████████████| 11.3 MB 61.4 MB/s \n",
"\u001b[K |████████████████████████████████| 388 kB 68.8 MB/s \n",
"\u001b[K |████████████████████████████████| 3.4 MB 51.4 MB/s \n",
"\u001b[K |████████████████████████████████| 15.7 MB 49.6 MB/s \n",
"\u001b[K |████████████████████████████████| 2.6 MB 64.2 MB/s \n",
"\u001b[K |████████████████████████████████| 303 kB 63.9 MB/s \n",
"\u001b[K |████████████████████████████████| 831.4 MB 6.7 kB/s \n",
"\u001b[K |████████████████████████████████| 59 kB 7.2 MB/s \n",
"\u001b[K |████████████████████████████████| 13.2 MB 32.9 MB/s \n",
"\u001b[K |████████████████████████████████| 60 kB 8.5 MB/s \n",
"\u001b[K |████████████████████████████████| 71 kB 11.4 MB/s \n",
"\u001b[K |████████████████████████████████| 98 kB 9.9 MB/s \n",
"\u001b[K |████████████████████████████████| 184 kB 77.1 MB/s \n",
"\u001b[K |████████████████████████████████| 242 kB 68.8 MB/s \n",
"\u001b[K |████████████████████████████████| 235 kB 68.4 MB/s \n",
"\u001b[K |████████████████████████████████| 6.0 MB 67.0 MB/s \n",
"\u001b[K |████████████████████████████████| 6.3 MB 23.4 MB/s \n",
"\u001b[K |████████████████████████████████| 3.3 MB 56.2 MB/s \n",
"\u001b[K |████████████████████████████████| 26.9 MB 1.2 MB/s \n",
"\u001b[K |████████████████████████████████| 596 kB 45.2 MB/s \n",
"\u001b[K |████████████████████████████████| 67 kB 6.4 MB/s \n",
"\u001b[K |████████████████████████████████| 3.3 MB 40.8 MB/s \n",
"\u001b[K |████████████████████████████████| 895 kB 70.4 MB/s \n",
"\u001b[K |████████████████████████████████| 125 kB 50.2 MB/s \n",
"\u001b[K |████████████████████████████████| 132 kB 39.8 MB/s \n",
"\u001b[K |████████████████████████████████| 123 kB 60.2 MB/s \n",
"\u001b[K |████████████████████████████████| 1.2 MB 63.8 MB/s \n",
"\u001b[K |████████████████████████████████| 628 kB 67.0 MB/s \n",
"\u001b[K |████████████████████████████████| 451 kB 63.4 MB/s \n",
"\u001b[K |████████████████████████████████| 10.1 MB 20.3 MB/s \n",
"\u001b[K |████████████████████████████████| 42 kB 1.7 MB/s \n",
"\u001b[K |████████████████████████████████| 4.3 MB 62.6 MB/s \n",
"\u001b[K |████████████████████████████████| 174 kB 70.6 MB/s \n",
"\u001b[K |████████████████████████████████| 64 kB 3.5 MB/s \n",
"\u001b[K |████████████████████████████████| 131 kB 61.0 MB/s \n",
"\u001b[K |████████████████████████████████| 79 kB 10.9 MB/s \n",
"\u001b[K |████████████████████████████████| 8.5 MB 71.4 MB/s \n",
"\u001b[K |████████████████████████████████| 127 kB 69.7 MB/s \n",
"\u001b[?25h Building wheel for en-core-web-sm (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Building wheel for wordninja (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Building wheel for moviepy (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Building wheel for GPUtil (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Building wheel for proglog (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Building wheel for retrying (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Building wheel for ftfy (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Building wheel for emoji (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Building wheel for jellyfish (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
"yellowbrick 1.3.post1 requires numpy<1.20,>=1.16.0, but you have numpy 1.21.5 which is incompatible.\n",
"torchvision 0.11.1+cu111 requires torch==1.10.0, but you have torch 1.9.1 which is incompatible.\n",
"torchtext 0.11.0 requires torch==1.10.0, but you have torch 1.9.1 which is incompatible.\n",
"torchaudio 0.10.0+cu111 requires torch==1.10.0, but you have torch 1.9.1 which is incompatible.\n",
"panel 0.12.1 requires tqdm>=4.48.0, but you have tqdm 4.43.0 which is incompatible.\n",
"google-colab 1.0.0 requires pandas~=1.1.0; python_version >= \"3.0\", but you have pandas 1.3.5 which is incompatible.\n",
"datascience 0.10.6 requires folium==0.2.1, but you have folium 0.8.3 which is incompatible.\n",
"albumentations 0.1.12 requires imgaug<0.2.7,>=0.2.5, but you have imgaug 0.2.9 which is incompatible.\u001b[0m\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"## testing"
],
"metadata": {
"id": "effNB9Su3Vzz"
}
},
{
"cell_type": "code",
"source": [
"#@markdown remove items already there for testing\n",
"!rm /content/vid2cleantxt/examples/TEST_folder_edition/console_printouts_large_model.md"
],
"metadata": {
"cellView": "form",
"id": "S-06O_vr3XQg",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 17
},
"outputId": "f981b3f2-d41e-41ac-e7aa-eaca36d6e9a6"
},
"execution_count": 6,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/html": [
"\n",
" <style>\n",
" pre {\n",
" white-space: pre-wrap;\n",
" }\n",
" </style>\n",
" "
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"source": [
"!python /content/vid2cleantxt/examples/TEST_folder_edition/dl_src_videos.py"
],
"metadata": {
"id": "sXlocBTyxWGI",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 750
},
"outputId": "206e15bd-e6a9-439f-86c6-a4f7c73b528b"
},
"execution_count": 7,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/html": [
"\n",
" <style>\n",
" pre {\n",
" white-space: pre-wrap;\n",
" }\n",
" </style>\n",
" "
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\rDownloading example videos: 0% 0/10 [00:00<?, ?it/s]\n",
"Downloading file...\n",
"\n",
"Download of MIT_MatricesSGD_000.mp4 complete.\n",
"Downloading example videos: 10% 1/10 [00:04<00:40, 4.55s/it]\n",
"Downloading file...\n",
"\n",
"Download of MIT_MatricesSGD_001.mp4 complete.\n",
"Downloading example videos: 20% 2/10 [00:11<00:42, 5.26s/it]\n",
"Downloading file...\n",
"\n",
"Download of MIT_MatricesSGD_002.mp4 complete.\n",
"Downloading example videos: 30% 3/10 [00:16<00:37, 5.32s/it]\n",
"Downloading file...\n",
"\n",
"Download of MIT_Signals_000.mp4 complete.\n",
"Downloading example videos: 40% 4/10 [00:24<00:35, 5.86s/it]\n",
"Downloading file...\n",
"\n",
"Download of MIT_Signals_001.mp4 complete.\n",
"Downloading example videos: 50% 5/10 [00:28<00:27, 5.43s/it]\n",
"Downloading file...\n",
"\n",
"Download of MIT_Signals_002.mp4 complete.\n",
"Downloading example videos: 60% 6/10 [00:32<00:19, 4.93s/it]\n",
"Downloading file...\n",
"\n",
"Download of MIT_VibrationsAndWaves000.mp4 complete.\n",
"Downloading example videos: 70% 7/10 [00:39<00:16, 5.48s/it]\n",
"Downloading file...\n",
"\n",
"Download of MIT_VibrationsAndWaves001.mp4 complete.\n",
"Downloading example videos: 80% 8/10 [00:44<00:11, 5.59s/it]\n",
"Downloading file...\n",
"\n",
"Download of MIT_VibrationsAndWaves002.mp4 complete.\n",
"Downloading example videos: 90% 9/10 [00:49<00:05, 5.38s/it]\n",
"Downloading file...\n",
"\n",
"Download of MIT_VibrationsAndWaves003.mp4 complete.\n",
"Downloading example videos: 100% 10/10 [00:55<00:00, 5.57s/it]\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!python vid2cleantxt/transcribe.py -i \"/content/vid2cleantxt/examples/TEST_folder_edition\" -cl 25"
],
"metadata": {
"id": "uv-ghyvjxjgL",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"outputId": "6b1e02cf-79e5-4ab3-85a8-49e3217c27c5"
},
"execution_count": 10,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/html": [
"\n",
" <style>\n",
" pre {\n",
" white-space: pre-wrap;\n",
" }\n",
" </style>\n",
" "
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"data folder is set to `/usr/local/lib/python3.7/dist-packages/neuspell/../data` script\n",
"\n",
"Loading models @ Jan-27-2022_-19-30-13 - may take some time...\n",
"if RT seems excessive, try --verbose flag or checking logfile\n",
"Loading hubert model - facebook/hubert-large-ls960-ft\n",
"\n",
"Found 10 audio or video files in /content/vid2cleantxt/examples/TEST_folder_edition\n",
"transcribing vids: 0% 0/10 [00:00<?, ?it/s]\n",
"Creating .wav audio clips: 0% 0/49 [00:00<?, ?it/s]\u001b[A\n",
"Creating .wav audio clips: 100% 49/49 [00:00<00:00, 271.27it/s]\n",
"\n",
"created audio chunks - Jan-27-2022_-19\n",
"Cuda availability (PyTorch) is True\n",
"\n",
"\n",
"Transcribing video: 0% 0/49 [00:00<?, ?it/s]\u001b[A\n",
"Gen RAM Free: 9.8 GB | Proc size: 7.6 GB | 2 CPUs loaded at 23.2 % |\n",
"\n",
"GPU RAM Free: 16158MB | Used: 2MB | Util 0% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 2% 1/49 [00:15<12:21, 15.45s/it]\u001b[A\n",
"Transcribing video: 4% 2/49 [00:16<08:44, 11.16s/it]\u001b[A\n",
"Transcribing video: 6% 3/49 [00:17<06:14, 8.15s/it]\u001b[A\n",
"Transcribing video: 8% 4/49 [00:18<04:31, 6.03s/it]\u001b[A\n",
"Transcribing video: 10% 5/49 [00:19<03:20, 4.56s/it]\u001b[A\n",
"Transcribing video: 12% 6/49 [00:21<02:32, 3.54s/it]\u001b[A\n",
"Transcribing video: 14% 7/49 [00:22<01:58, 2.81s/it]\u001b[A\n",
"Transcribing video: 16% 8/49 [00:23<01:34, 2.31s/it]\u001b[A\n",
"Transcribing video: 18% 9/49 [00:24<01:18, 1.95s/it]\u001b[A\n",
"Transcribing video: 20% 10/49 [00:25<01:06, 1.71s/it]\u001b[A\n",
"Transcribing video: 22% 11/49 [00:26<00:58, 1.53s/it]\u001b[A\n",
"Transcribing video: 24% 12/49 [00:27<00:52, 1.41s/it]\u001b[A\n",
"Transcribing video: 27% 13/49 [00:28<00:47, 1.33s/it]\u001b[A\n",
"Transcribing video: 29% 14/49 [00:30<00:44, 1.27s/it]\u001b[A\n",
"Transcribing video: 31% 15/49 [00:31<00:41, 1.23s/it]\u001b[A\n",
"Transcribing video: 33% 16/49 [00:32<00:39, 1.21s/it]\u001b[A\n",
"Transcribing video: 35% 17/49 [00:33<00:37, 1.18s/it]\u001b[A\n",
"Transcribing video: 37% 18/49 [00:34<00:36, 1.17s/it]\u001b[A\n",
"Transcribing video: 39% 19/49 [00:35<00:34, 1.16s/it]\u001b[A\n",
"Transcribing video: 41% 20/49 [00:36<00:33, 1.15s/it]\u001b[A\n",
"Transcribing video: 43% 21/49 [00:38<00:31, 1.14s/it]\u001b[A\n",
"Transcribing video: 45% 22/49 [00:39<00:30, 1.14s/it]\u001b[A\n",
"Transcribing video: 47% 23/49 [00:40<00:29, 1.13s/it]\u001b[A\n",
"Transcribing video: 49% 24/49 [00:41<00:28, 1.14s/it]\u001b[A\n",
"Transcribing video: 51% 25/49 [00:42<00:27, 1.14s/it]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 50.2 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 53% 26/49 [00:44<00:30, 1.34s/it]\u001b[A\n",
"Transcribing video: 55% 27/49 [00:45<00:27, 1.27s/it]\u001b[A\n",
"Transcribing video: 57% 28/49 [00:46<00:25, 1.22s/it]\u001b[A\n",
"Transcribing video: 59% 29/49 [00:47<00:23, 1.19s/it]\u001b[A\n",
"Transcribing video: 61% 30/49 [00:48<00:22, 1.17s/it]\u001b[A\n",
"Transcribing video: 63% 31/49 [00:49<00:20, 1.15s/it]\u001b[A\n",
"Transcribing video: 65% 32/49 [00:51<00:19, 1.14s/it]\u001b[A\n",
"Transcribing video: 67% 33/49 [00:52<00:18, 1.13s/it]\u001b[A\n",
"Transcribing video: 69% 34/49 [00:53<00:16, 1.13s/it]\u001b[A\n",
"Transcribing video: 71% 35/49 [00:54<00:15, 1.13s/it]\u001b[A\n",
"Transcribing video: 73% 36/49 [00:55<00:14, 1.13s/it]\u001b[A\n",
"Transcribing video: 76% 37/49 [00:56<00:13, 1.12s/it]\u001b[A\n",
"Transcribing video: 78% 38/49 [00:57<00:12, 1.12s/it]\u001b[A\n",
"Transcribing video: 80% 39/49 [00:58<00:11, 1.12s/it]\u001b[A\n",
"Transcribing video: 82% 40/49 [01:00<00:10, 1.12s/it]\u001b[A\n",
"Transcribing video: 84% 41/49 [01:01<00:08, 1.12s/it]\u001b[A\n",
"Transcribing video: 86% 42/49 [01:02<00:07, 1.12s/it]\u001b[A\n",
"Transcribing video: 88% 43/49 [01:03<00:06, 1.12s/it]\u001b[A\n",
"Transcribing video: 90% 44/49 [01:04<00:05, 1.11s/it]\u001b[A\n",
"Transcribing video: 92% 45/49 [01:05<00:04, 1.11s/it]\u001b[A\n",
"Transcribing video: 94% 46/49 [01:06<00:03, 1.11s/it]\u001b[A\n",
"Transcribing video: 96% 47/49 [01:07<00:02, 1.11s/it]\u001b[A\n",
"Transcribing video: 98% 48/49 [01:08<00:01, 1.11s/it]\u001b[A\n",
"Transcribing video: 100% 49/49 [01:09<00:00, 1.41s/it]\n",
"transcribing vids: 10% 1/10 [01:13<11:05, 73.95s/it]\n",
"Creating .wav audio clips: 0% 0/48 [00:00<?, ?it/s]\u001b[A\n",
"Creating .wav audio clips: 100% 48/48 [00:00<00:00, 411.39it/s]\n",
"\n",
"created audio chunks - Jan-27-2022_-19\n",
"Cuda availability (PyTorch) is True\n",
"\n",
"\n",
"Transcribing video: 0% 0/48 [00:00<?, ?it/s]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 54.2 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 2% 1/48 [00:01<01:25, 1.81s/it]\u001b[A\n",
"Transcribing video: 4% 2/48 [00:02<01:13, 1.61s/it]\u001b[A\n",
"Transcribing video: 6% 3/48 [00:04<01:05, 1.46s/it]\u001b[A\n",
"Transcribing video: 8% 4/48 [00:05<00:59, 1.36s/it]\u001b[A\n",
"Transcribing video: 10% 5/48 [00:06<00:55, 1.29s/it]\u001b[A\n",
"Transcribing video: 12% 6/48 [00:07<00:52, 1.24s/it]\u001b[A\n",
"Transcribing video: 15% 7/48 [00:08<00:49, 1.21s/it]\u001b[A\n",
"Transcribing video: 17% 8/48 [00:09<00:47, 1.19s/it]\u001b[A\n",
"Transcribing video: 19% 9/48 [00:10<00:45, 1.17s/it]\u001b[A\n",
"Transcribing video: 21% 10/48 [00:11<00:43, 1.16s/it]\u001b[A\n",
"Transcribing video: 23% 11/48 [00:13<00:42, 1.15s/it]\u001b[A\n",
"Transcribing video: 25% 12/48 [00:14<00:40, 1.14s/it]\u001b[A\n",
"Transcribing video: 27% 13/48 [00:15<00:39, 1.14s/it]\u001b[A\n",
"Transcribing video: 29% 14/48 [00:16<00:38, 1.13s/it]\u001b[A\n",
"Transcribing video: 31% 15/48 [00:17<00:37, 1.13s/it]\u001b[A\n",
"Transcribing video: 33% 16/48 [00:18<00:36, 1.13s/it]\u001b[A\n",
"Transcribing video: 35% 17/48 [00:19<00:34, 1.12s/it]\u001b[A\n",
"Transcribing video: 38% 18/48 [00:20<00:33, 1.13s/it]\u001b[A\n",
"Transcribing video: 40% 19/48 [00:22<00:32, 1.12s/it]\u001b[A\n",
"Transcribing video: 42% 20/48 [00:23<00:31, 1.12s/it]\u001b[A\n",
"Transcribing video: 44% 21/48 [00:24<00:30, 1.12s/it]\u001b[A\n",
"Transcribing video: 46% 22/48 [00:25<00:29, 1.12s/it]\u001b[A\n",
"Transcribing video: 48% 23/48 [00:26<00:28, 1.13s/it]\u001b[A\n",
"Transcribing video: 50% 24/48 [00:27<00:26, 1.12s/it]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 52.3 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 52% 25/48 [00:29<00:30, 1.32s/it]\u001b[A\n",
"Transcribing video: 54% 26/48 [00:30<00:27, 1.26s/it]\u001b[A\n",
"Transcribing video: 56% 27/48 [00:31<00:25, 1.22s/it]\u001b[A\n",
"Transcribing video: 58% 28/48 [00:32<00:23, 1.19s/it]\u001b[A\n",
"Transcribing video: 60% 29/48 [00:33<00:22, 1.18s/it]\u001b[A\n",
"Transcribing video: 62% 30/48 [00:35<00:20, 1.16s/it]\u001b[A\n",
"Transcribing video: 65% 31/48 [00:36<00:19, 1.15s/it]\u001b[A\n",
"Transcribing video: 67% 32/48 [00:37<00:18, 1.14s/it]\u001b[A\n",
"Transcribing video: 69% 33/48 [00:38<00:16, 1.13s/it]\u001b[A\n",
"Transcribing video: 71% 34/48 [00:39<00:15, 1.13s/it]\u001b[A\n",
"Transcribing video: 73% 35/48 [00:40<00:14, 1.13s/it]\u001b[A\n",
"Transcribing video: 75% 36/48 [00:41<00:13, 1.13s/it]\u001b[A\n",
"Transcribing video: 77% 37/48 [00:42<00:12, 1.12s/it]\u001b[A\n",
"Transcribing video: 79% 38/48 [00:44<00:11, 1.13s/it]\u001b[A\n",
"Transcribing video: 81% 39/48 [00:45<00:10, 1.13s/it]\u001b[A\n",
"Transcribing video: 83% 40/48 [00:46<00:08, 1.12s/it]\u001b[A\n",
"Transcribing video: 85% 41/48 [00:47<00:07, 1.12s/it]\u001b[A\n",
"Transcribing video: 88% 42/48 [00:48<00:06, 1.12s/it]\u001b[A\n",
"Transcribing video: 90% 43/48 [00:49<00:05, 1.12s/it]\u001b[A\n",
"Transcribing video: 92% 44/48 [00:50<00:04, 1.12s/it]\u001b[A\n",
"Transcribing video: 94% 45/48 [00:51<00:03, 1.12s/it]\u001b[A\n",
"Transcribing video: 96% 46/48 [00:53<00:02, 1.12s/it]\u001b[A\n",
"Transcribing video: 98% 47/48 [00:54<00:01, 1.12s/it]\u001b[A\n",
"Transcribing video: 100% 48/48 [00:55<00:00, 1.15s/it]\n",
"transcribing vids: 20% 2/10 [02:13<09:16, 69.55s/it]\n",
"Creating .wav audio clips: 100% 32/32 [00:00<00:00, 411.83it/s]\n",
"\n",
"created audio chunks - Jan-27-2022_-19\n",
"Cuda availability (PyTorch) is True\n",
"\n",
"\n",
"Transcribing video: 0% 0/32 [00:00<?, ?it/s]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 53.4 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 3% 1/32 [00:01<00:54, 1.77s/it]\u001b[A\n",
"Transcribing video: 6% 2/32 [00:02<00:47, 1.59s/it]\u001b[A\n",
"Transcribing video: 9% 3/32 [00:04<00:42, 1.46s/it]\u001b[A\n",
"Transcribing video: 12% 4/32 [00:05<00:38, 1.36s/it]\u001b[A\n",
"Transcribing video: 16% 5/32 [00:06<00:34, 1.29s/it]\u001b[A\n",
"Transcribing video: 19% 6/32 [00:07<00:32, 1.24s/it]\u001b[A\n",
"Transcribing video: 22% 7/32 [00:08<00:30, 1.23s/it]\u001b[A\n",
"Transcribing video: 25% 8/32 [00:09<00:29, 1.21s/it]\u001b[A\n",
"Transcribing video: 28% 9/32 [00:10<00:27, 1.19s/it]\u001b[A\n",
"Transcribing video: 31% 10/32 [00:12<00:25, 1.16s/it]\u001b[A\n",
"Transcribing video: 34% 11/32 [00:13<00:24, 1.16s/it]\u001b[A\n",
"Transcribing video: 38% 12/32 [00:14<00:23, 1.15s/it]\u001b[A\n",
"Transcribing video: 41% 13/32 [00:15<00:22, 1.17s/it]\u001b[A\n",
"Transcribing video: 44% 14/32 [00:16<00:21, 1.19s/it]\u001b[A\n",
"Transcribing video: 47% 15/32 [00:18<00:20, 1.20s/it]\u001b[A\n",
"Transcribing video: 50% 16/32 [00:19<00:19, 1.20s/it]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 52.6 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 53% 17/32 [00:21<00:20, 1.39s/it]\u001b[A\n",
"Transcribing video: 56% 18/32 [00:22<00:18, 1.32s/it]\u001b[A\n",
"Transcribing video: 59% 19/32 [00:23<00:16, 1.27s/it]\u001b[A\n",
"Transcribing video: 62% 20/32 [00:24<00:15, 1.25s/it]\u001b[A\n",
"Transcribing video: 66% 21/32 [00:25<00:13, 1.23s/it]\u001b[A\n",
"Transcribing video: 69% 22/32 [00:26<00:12, 1.21s/it]\u001b[A\n",
"Transcribing video: 72% 23/32 [00:28<00:10, 1.19s/it]\u001b[A\n",
"Transcribing video: 75% 24/32 [00:29<00:09, 1.18s/it]\u001b[A\n",
"Transcribing video: 78% 25/32 [00:30<00:08, 1.17s/it]\u001b[A\n",
"Transcribing video: 81% 26/32 [00:31<00:06, 1.17s/it]\u001b[A\n",
"Transcribing video: 84% 27/32 [00:32<00:05, 1.16s/it]\u001b[A\n",
"Transcribing video: 88% 28/32 [00:33<00:04, 1.16s/it]\u001b[A\n",
"Transcribing video: 91% 29/32 [00:34<00:03, 1.15s/it]\u001b[A\n",
"Transcribing video: 94% 30/32 [00:36<00:02, 1.16s/it]\u001b[A\n",
"Transcribing video: 97% 31/32 [00:37<00:01, 1.16s/it]\u001b[A\n",
"Transcribing video: 100% 32/32 [00:37<00:00, 1.17s/it]\n",
"transcribing vids: 30% 3/10 [02:54<07:06, 60.94s/it]\n",
"Creating .wav audio clips: 0% 0/49 [00:00<?, ?it/s]\u001b[A\n",
"Creating .wav audio clips: 100% 49/49 [00:00<00:00, 393.23it/s]\n",
"\n",
"created audio chunks - Jan-27-2022_-19\n",
"Cuda availability (PyTorch) is True\n",
"\n",
"\n",
"Transcribing video: 0% 0/49 [00:00<?, ?it/s]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 54.8 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 2% 1/49 [00:01<01:24, 1.77s/it]\u001b[A\n",
"Transcribing video: 4% 2/49 [00:02<01:14, 1.58s/it]\u001b[A\n",
"Transcribing video: 6% 3/49 [00:04<01:06, 1.44s/it]\u001b[A\n",
"Transcribing video: 8% 4/49 [00:05<01:00, 1.35s/it]\u001b[A\n",
"Transcribing video: 10% 5/49 [00:06<00:56, 1.28s/it]\u001b[A\n",
"Transcribing video: 12% 6/49 [00:07<00:53, 1.23s/it]\u001b[A\n",
"Transcribing video: 14% 7/49 [00:08<00:50, 1.21s/it]\u001b[A\n",
"Transcribing video: 16% 8/49 [00:09<00:48, 1.18s/it]\u001b[A\n",
"Transcribing video: 18% 9/49 [00:10<00:46, 1.16s/it]\u001b[A\n",
"Transcribing video: 20% 10/49 [00:11<00:44, 1.15s/it]\u001b[A\n",
"Transcribing video: 22% 11/49 [00:13<00:43, 1.14s/it]\u001b[A\n",
"Transcribing video: 24% 12/49 [00:14<00:41, 1.13s/it]\u001b[A\n",
"Transcribing video: 27% 13/49 [00:15<00:40, 1.14s/it]\u001b[A\n",
"Transcribing video: 29% 14/49 [00:16<00:39, 1.13s/it]\u001b[A\n",
"Transcribing video: 31% 15/49 [00:17<00:38, 1.13s/it]\u001b[A\n",
"Transcribing video: 33% 16/49 [00:18<00:37, 1.13s/it]\u001b[A\n",
"Transcribing video: 35% 17/49 [00:19<00:36, 1.13s/it]\u001b[A\n",
"Transcribing video: 37% 18/49 [00:20<00:34, 1.12s/it]\u001b[A\n",
"Transcribing video: 39% 19/49 [00:22<00:33, 1.13s/it]\u001b[A\n",
"Transcribing video: 41% 20/49 [00:23<00:32, 1.13s/it]\u001b[A\n",
"Transcribing video: 43% 21/49 [00:24<00:31, 1.13s/it]\u001b[A\n",
"Transcribing video: 45% 22/49 [00:25<00:30, 1.13s/it]\u001b[A\n",
"Transcribing video: 47% 23/49 [00:26<00:29, 1.13s/it]\u001b[A\n",
"Transcribing video: 49% 24/49 [00:27<00:28, 1.12s/it]\u001b[A\n",
"Transcribing video: 51% 25/49 [00:28<00:26, 1.12s/it]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 52.6 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 53% 26/49 [00:30<00:30, 1.32s/it]\u001b[A\n",
"Transcribing video: 55% 27/49 [00:31<00:27, 1.26s/it]\u001b[A\n",
"Transcribing video: 57% 28/49 [00:32<00:25, 1.22s/it]\u001b[A\n",
"Transcribing video: 59% 29/49 [00:33<00:23, 1.19s/it]\u001b[A\n",
"Transcribing video: 61% 30/49 [00:35<00:22, 1.17s/it]\u001b[A\n",
"Transcribing video: 63% 31/49 [00:36<00:20, 1.16s/it]\u001b[A\n",
"Transcribing video: 65% 32/49 [00:37<00:19, 1.14s/it]\u001b[A\n",
"Transcribing video: 67% 33/49 [00:38<00:18, 1.14s/it]\u001b[A\n",
"Transcribing video: 69% 34/49 [00:39<00:16, 1.13s/it]\u001b[A\n",
"Transcribing video: 71% 35/49 [00:40<00:15, 1.12s/it]\u001b[A\n",
"Transcribing video: 73% 36/49 [00:41<00:14, 1.12s/it]\u001b[A\n",
"Transcribing video: 76% 37/49 [00:42<00:13, 1.12s/it]\u001b[A\n",
"Transcribing video: 78% 38/49 [00:43<00:12, 1.12s/it]\u001b[A\n",
"Transcribing video: 80% 39/49 [00:45<00:11, 1.12s/it]\u001b[A\n",
"Transcribing video: 82% 40/49 [00:46<00:10, 1.12s/it]\u001b[A\n",
"Transcribing video: 84% 41/49 [00:47<00:08, 1.11s/it]\u001b[A\n",
"Transcribing video: 86% 42/49 [00:48<00:07, 1.11s/it]\u001b[A\n",
"Transcribing video: 88% 43/49 [00:49<00:06, 1.11s/it]\u001b[A\n",
"Transcribing video: 90% 44/49 [00:50<00:05, 1.12s/it]\u001b[A\n",
"Transcribing video: 92% 45/49 [00:51<00:04, 1.12s/it]\u001b[A\n",
"Transcribing video: 94% 46/49 [00:52<00:03, 1.12s/it]\u001b[A\n",
"Transcribing video: 96% 47/49 [00:54<00:02, 1.12s/it]\u001b[A\n",
"Transcribing video: 100% 49/49 [00:55<00:00, 1.13s/it]\n",
"transcribing vids: 40% 4/10 [03:53<06:02, 60.50s/it]\n",
"Creating .wav audio clips: 0% 0/49 [00:00<?, ?it/s]\u001b[A\n",
"Creating .wav audio clips: 100% 49/49 [00:00<00:00, 417.47it/s]\n",
"\n",
"created audio chunks - Jan-27-2022_-19\n",
"Cuda availability (PyTorch) is True\n",
"\n",
"\n",
"Transcribing video: 0% 0/49 [00:00<?, ?it/s]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 54.0 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 2% 1/49 [00:01<01:26, 1.80s/it]\u001b[A\n",
"Transcribing video: 4% 2/49 [00:02<01:15, 1.60s/it]\u001b[A\n",
"Transcribing video: 6% 3/49 [00:04<01:06, 1.45s/it]\u001b[A\n",
"Transcribing video: 8% 4/49 [00:05<01:00, 1.35s/it]\u001b[A\n",
"Transcribing video: 10% 5/49 [00:06<00:56, 1.28s/it]\u001b[A\n",
"Transcribing video: 12% 6/49 [00:07<00:52, 1.23s/it]\u001b[A\n",
"Transcribing video: 14% 7/49 [00:08<00:50, 1.21s/it]\u001b[A\n",
"Transcribing video: 16% 8/49 [00:09<00:48, 1.19s/it]\u001b[A\n",
"Transcribing video: 18% 9/49 [00:10<00:46, 1.17s/it]\u001b[A\n",
"Transcribing video: 20% 10/49 [00:11<00:45, 1.17s/it]\u001b[A\n",
"Transcribing video: 22% 11/49 [00:13<00:44, 1.16s/it]\u001b[A\n",
"Transcribing video: 24% 12/49 [00:14<00:42, 1.15s/it]\u001b[A\n",
"Transcribing video: 27% 13/49 [00:15<00:41, 1.15s/it]\u001b[A\n",
"Transcribing video: 29% 14/49 [00:16<00:39, 1.14s/it]\u001b[A\n",
"Transcribing video: 31% 15/49 [00:17<00:38, 1.13s/it]\u001b[A\n",
"Transcribing video: 33% 16/49 [00:18<00:37, 1.14s/it]\u001b[A\n",
"Transcribing video: 35% 17/49 [00:19<00:36, 1.13s/it]\u001b[A\n",
"Transcribing video: 37% 18/49 [00:21<00:34, 1.12s/it]\u001b[A\n",
"Transcribing video: 39% 19/49 [00:22<00:33, 1.13s/it]\u001b[A\n",
"Transcribing video: 41% 20/49 [00:23<00:32, 1.13s/it]\u001b[A\n",
"Transcribing video: 43% 21/49 [00:24<00:31, 1.13s/it]\u001b[A\n",
"Transcribing video: 45% 22/49 [00:25<00:30, 1.13s/it]\u001b[A\n",
"Transcribing video: 47% 23/49 [00:26<00:29, 1.14s/it]\u001b[A\n",
"Transcribing video: 49% 24/49 [00:27<00:28, 1.14s/it]\u001b[A\n",
"Transcribing video: 51% 25/49 [00:29<00:27, 1.14s/it]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 52.7 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 53% 26/49 [00:30<00:31, 1.35s/it]\u001b[A\n",
"Transcribing video: 55% 27/49 [00:31<00:28, 1.28s/it]\u001b[A\n",
"Transcribing video: 57% 28/49 [00:33<00:26, 1.24s/it]\u001b[A\n",
"Transcribing video: 59% 29/49 [00:34<00:24, 1.21s/it]\u001b[A\n",
"Transcribing video: 61% 30/49 [00:35<00:22, 1.18s/it]\u001b[A\n",
"Transcribing video: 63% 31/49 [00:36<00:20, 1.16s/it]\u001b[A\n",
"Transcribing video: 65% 32/49 [00:37<00:19, 1.16s/it]\u001b[A\n",
"Transcribing video: 67% 33/49 [00:38<00:18, 1.15s/it]\u001b[A\n",
"Transcribing video: 69% 34/49 [00:39<00:17, 1.15s/it]\u001b[A\n",
"Transcribing video: 71% 35/49 [00:41<00:16, 1.15s/it]\u001b[A\n",
"Transcribing video: 73% 36/49 [00:42<00:14, 1.14s/it]\u001b[A\n",
"Transcribing video: 76% 37/49 [00:43<00:13, 1.14s/it]\u001b[A\n",
"Transcribing video: 78% 38/49 [00:44<00:12, 1.14s/it]\u001b[A\n",
"Transcribing video: 80% 39/49 [00:45<00:11, 1.13s/it]\u001b[A\n",
"Transcribing video: 82% 40/49 [00:46<00:10, 1.13s/it]\u001b[A\n",
"Transcribing video: 84% 41/49 [00:47<00:08, 1.12s/it]\u001b[A\n",
"Transcribing video: 86% 42/49 [00:48<00:07, 1.12s/it]\u001b[A\n",
"Transcribing video: 88% 43/49 [00:50<00:06, 1.12s/it]\u001b[A\n",
"Transcribing video: 90% 44/49 [00:51<00:05, 1.13s/it]\u001b[A\n",
"Transcribing video: 92% 45/49 [00:52<00:04, 1.14s/it]\u001b[A\n",
"Transcribing video: 94% 46/49 [00:53<00:03, 1.14s/it]\u001b[A\n",
"Transcribing video: 96% 47/49 [00:54<00:02, 1.14s/it]\u001b[A\n",
"Transcribing video: 98% 48/49 [00:55<00:01, 1.14s/it]\u001b[A\n",
"Transcribing video: 100% 49/49 [00:56<00:00, 1.15s/it]\n",
"transcribing vids: 50% 5/10 [04:53<05:02, 60.43s/it]\n",
"Creating .wav audio clips: 100% 13/13 [00:00<00:00, 414.78it/s]\n",
"\n",
"created audio chunks - Jan-27-2022_-19\n",
"Cuda availability (PyTorch) is True\n",
"\n",
"\n",
"Transcribing video: 0% 0/13 [00:00<?, ?it/s]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 52.9 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 8% 1/13 [00:01<00:22, 1.84s/it]\u001b[A\n",
"Transcribing video: 15% 2/13 [00:03<00:18, 1.64s/it]\u001b[A\n",
"Transcribing video: 23% 3/13 [00:04<00:14, 1.50s/it]\u001b[A\n",
"Transcribing video: 31% 4/13 [00:05<00:12, 1.38s/it]\u001b[A\n",
"Transcribing video: 38% 5/13 [00:06<00:10, 1.31s/it]\u001b[A\n",
"Transcribing video: 46% 6/13 [00:07<00:08, 1.25s/it]\u001b[A\n",
"Transcribing video: 54% 7/13 [00:08<00:07, 1.22s/it]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 53.1 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 62% 8/13 [00:10<00:06, 1.39s/it]\u001b[A\n",
"Transcribing video: 69% 9/13 [00:11<00:05, 1.31s/it]\u001b[A\n",
"Transcribing video: 77% 10/13 [00:12<00:03, 1.26s/it]\u001b[A\n",
"Transcribing video: 85% 11/13 [00:13<00:02, 1.22s/it]\u001b[A\n",
"Transcribing video: 92% 12/13 [00:14<00:01, 1.18s/it]\u001b[A\n",
"Transcribing video: 100% 13/13 [00:15<00:00, 1.17s/it]\n",
"transcribing vids: 60% 6/10 [05:10<03:09, 47.43s/it]\n",
"Creating .wav audio clips: 0% 0/49 [00:00<?, ?it/s]\u001b[A\n",
"Creating .wav audio clips: 100% 49/49 [00:00<00:00, 377.49it/s]\n",
"\n",
"created audio chunks - Jan-27-2022_-19\n",
"Cuda availability (PyTorch) is True\n",
"\n",
"\n",
"Transcribing video: 0% 0/49 [00:00<?, ?it/s]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 57.4 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 2% 1/49 [00:01<01:26, 1.81s/it]\u001b[A\n",
"Transcribing video: 4% 2/49 [00:02<01:15, 1.61s/it]\u001b[A\n",
"Transcribing video: 6% 3/49 [00:04<01:07, 1.47s/it]\u001b[A\n",
"Transcribing video: 8% 4/49 [00:05<01:01, 1.38s/it]\u001b[A\n",
"Transcribing video: 10% 5/49 [00:06<00:57, 1.30s/it]\u001b[A\n",
"Transcribing video: 12% 6/49 [00:07<00:54, 1.26s/it]\u001b[A\n",
"Transcribing video: 14% 7/49 [00:08<00:51, 1.22s/it]\u001b[A\n",
"Transcribing video: 16% 8/49 [00:09<00:49, 1.20s/it]\u001b[A\n",
"Transcribing video: 18% 9/49 [00:10<00:47, 1.18s/it]\u001b[A\n",
"Transcribing video: 20% 10/49 [00:12<00:45, 1.16s/it]\u001b[A\n",
"Transcribing video: 22% 11/49 [00:13<00:43, 1.15s/it]\u001b[A\n",
"Transcribing video: 24% 12/49 [00:14<00:42, 1.15s/it]\u001b[A\n",
"Transcribing video: 27% 13/49 [00:15<00:41, 1.15s/it]\u001b[A\n",
"Transcribing video: 29% 14/49 [00:16<00:40, 1.15s/it]\u001b[A\n",
"Transcribing video: 31% 15/49 [00:17<00:38, 1.15s/it]\u001b[A\n",
"Transcribing video: 33% 16/49 [00:18<00:37, 1.13s/it]\u001b[A\n",
"Transcribing video: 35% 17/49 [00:20<00:36, 1.13s/it]\u001b[A\n",
"Transcribing video: 37% 18/49 [00:21<00:34, 1.13s/it]\u001b[A\n",
"Transcribing video: 39% 19/49 [00:22<00:33, 1.12s/it]\u001b[A\n",
"Transcribing video: 41% 20/49 [00:23<00:32, 1.12s/it]\u001b[A\n",
"Transcribing video: 43% 21/49 [00:24<00:31, 1.13s/it]\u001b[A\n",
"Transcribing video: 45% 22/49 [00:25<00:30, 1.13s/it]\u001b[A\n",
"Transcribing video: 47% 23/49 [00:26<00:29, 1.13s/it]\u001b[A\n",
"Transcribing video: 49% 24/49 [00:27<00:28, 1.13s/it]\u001b[A\n",
"Transcribing video: 51% 25/49 [00:29<00:27, 1.13s/it]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 52.6 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 53% 26/49 [00:30<00:30, 1.34s/it]\u001b[A\n",
"Transcribing video: 55% 27/49 [00:31<00:28, 1.28s/it]\u001b[A\n",
"Transcribing video: 57% 28/49 [00:33<00:25, 1.24s/it]\u001b[A\n",
"Transcribing video: 59% 29/49 [00:34<00:24, 1.21s/it]\u001b[A\n",
"Transcribing video: 61% 30/49 [00:35<00:22, 1.19s/it]\u001b[A\n",
"Transcribing video: 63% 31/49 [00:36<00:21, 1.17s/it]\u001b[A\n",
"Transcribing video: 65% 32/49 [00:37<00:19, 1.16s/it]\u001b[A\n",
"Transcribing video: 67% 33/49 [00:38<00:18, 1.16s/it]\u001b[A\n",
"Transcribing video: 69% 34/49 [00:39<00:17, 1.15s/it]\u001b[A\n",
"Transcribing video: 71% 35/49 [00:41<00:16, 1.15s/it]\u001b[A\n",
"Transcribing video: 73% 36/49 [00:42<00:14, 1.15s/it]\u001b[A\n",
"Transcribing video: 76% 37/49 [00:43<00:13, 1.14s/it]\u001b[A\n",
"Transcribing video: 78% 38/49 [00:44<00:12, 1.14s/it]\u001b[A\n",
"Transcribing video: 80% 39/49 [00:45<00:11, 1.13s/it]\u001b[A\n",
"Transcribing video: 82% 40/49 [00:46<00:10, 1.13s/it]\u001b[A\n",
"Transcribing video: 84% 41/49 [00:47<00:08, 1.12s/it]\u001b[A\n",
"Transcribing video: 86% 42/49 [00:48<00:07, 1.12s/it]\u001b[A\n",
"Transcribing video: 88% 43/49 [00:50<00:06, 1.12s/it]\u001b[A\n",
"Transcribing video: 90% 44/49 [00:51<00:05, 1.12s/it]\u001b[A\n",
"Transcribing video: 92% 45/49 [00:52<00:04, 1.13s/it]\u001b[A\n",
"Transcribing video: 94% 46/49 [00:53<00:03, 1.13s/it]\u001b[A\n",
"Transcribing video: 96% 47/49 [00:54<00:02, 1.14s/it]\u001b[A\n",
"Transcribing video: 98% 48/49 [00:55<00:01, 1.13s/it]\u001b[A\n",
"Transcribing video: 100% 49/49 [00:55<00:00, 1.14s/it]\n",
"transcribing vids: 70% 7/10 [06:11<02:33, 51.30s/it]\n",
"Creating .wav audio clips: 0% 0/49 [00:00<?, ?it/s]\u001b[A\n",
"Creating .wav audio clips: 100% 49/49 [00:00<00:00, 412.03it/s]\n",
"\n",
"created audio chunks - Jan-27-2022_-19\n",
"Cuda availability (PyTorch) is True\n",
"\n",
"\n",
"Transcribing video: 0% 0/49 [00:00<?, ?it/s]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 54.4 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 2% 1/49 [00:01<01:28, 1.83s/it]\u001b[A\n",
"Transcribing video: 4% 2/49 [00:02<01:16, 1.63s/it]\u001b[A\n",
"Transcribing video: 6% 3/49 [00:04<01:08, 1.48s/it]\u001b[A\n",
"Transcribing video: 8% 4/49 [00:05<01:01, 1.37s/it]\u001b[A\n",
"Transcribing video: 10% 5/49 [00:06<00:57, 1.30s/it]\u001b[A\n",
"Transcribing video: 12% 6/49 [00:07<00:53, 1.25s/it]\u001b[A\n",
"Transcribing video: 14% 7/49 [00:08<00:50, 1.21s/it]\u001b[A\n",
"Transcribing video: 16% 8/49 [00:09<00:48, 1.19s/it]\u001b[A\n",
"Transcribing video: 18% 9/49 [00:10<00:46, 1.17s/it]\u001b[A\n",
"Transcribing video: 20% 10/49 [00:11<00:44, 1.15s/it]\u001b[A\n",
"Transcribing video: 22% 11/49 [00:13<00:43, 1.13s/it]\u001b[A\n",
"Transcribing video: 24% 12/49 [00:14<00:41, 1.13s/it]\u001b[A\n",
"Transcribing video: 27% 13/49 [00:15<00:40, 1.12s/it]\u001b[A\n",
"Transcribing video: 29% 14/49 [00:16<00:39, 1.12s/it]\u001b[A\n",
"Transcribing video: 31% 15/49 [00:17<00:38, 1.13s/it]\u001b[A\n",
"Transcribing video: 33% 16/49 [00:18<00:37, 1.13s/it]\u001b[A\n",
"Transcribing video: 35% 17/49 [00:19<00:36, 1.13s/it]\u001b[A\n",
"Transcribing video: 37% 18/49 [00:20<00:35, 1.13s/it]\u001b[A\n",
"Transcribing video: 39% 19/49 [00:22<00:34, 1.14s/it]\u001b[A\n",
"Transcribing video: 41% 20/49 [00:23<00:33, 1.14s/it]\u001b[A\n",
"Transcribing video: 43% 21/49 [00:24<00:31, 1.14s/it]\u001b[A\n",
"Transcribing video: 45% 22/49 [00:25<00:30, 1.13s/it]\u001b[A\n",
"Transcribing video: 47% 23/49 [00:26<00:29, 1.13s/it]\u001b[A\n",
"Transcribing video: 49% 24/49 [00:27<00:28, 1.14s/it]\u001b[A\n",
"Transcribing video: 51% 25/49 [00:28<00:27, 1.14s/it]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 52.7 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 53% 26/49 [00:30<00:30, 1.34s/it]\u001b[A\n",
"Transcribing video: 55% 27/49 [00:31<00:28, 1.28s/it]\u001b[A\n",
"Transcribing video: 57% 28/49 [00:33<00:25, 1.23s/it]\u001b[A\n",
"Transcribing video: 59% 29/49 [00:34<00:24, 1.21s/it]\u001b[A\n",
"Transcribing video: 61% 30/49 [00:35<00:22, 1.18s/it]\u001b[A\n",
"Transcribing video: 63% 31/49 [00:36<00:20, 1.16s/it]\u001b[A\n",
"Transcribing video: 65% 32/49 [00:37<00:19, 1.14s/it]\u001b[A\n",
"Transcribing video: 67% 33/49 [00:38<00:18, 1.13s/it]\u001b[A\n",
"Transcribing video: 69% 34/49 [00:39<00:17, 1.13s/it]\u001b[A\n",
"Transcribing video: 71% 35/49 [00:40<00:15, 1.12s/it]\u001b[A\n",
"Transcribing video: 73% 36/49 [00:41<00:14, 1.13s/it]\u001b[A\n",
"Transcribing video: 76% 37/49 [00:43<00:13, 1.14s/it]\u001b[A\n",
"Transcribing video: 78% 38/49 [00:44<00:12, 1.14s/it]\u001b[A\n",
"Transcribing video: 80% 39/49 [00:45<00:11, 1.14s/it]\u001b[A\n",
"Transcribing video: 82% 40/49 [00:46<00:10, 1.14s/it]\u001b[A\n",
"Transcribing video: 84% 41/49 [00:47<00:09, 1.13s/it]\u001b[A\n",
"Transcribing video: 86% 42/49 [00:48<00:07, 1.14s/it]\u001b[A\n",
"Transcribing video: 88% 43/49 [00:49<00:06, 1.13s/it]\u001b[A\n",
"Transcribing video: 90% 44/49 [00:51<00:05, 1.13s/it]\u001b[A\n",
"Transcribing video: 92% 45/49 [00:52<00:04, 1.13s/it]\u001b[A\n",
"Transcribing video: 94% 46/49 [00:53<00:03, 1.13s/it]\u001b[A\n",
"Transcribing video: 96% 47/49 [00:54<00:02, 1.13s/it]\u001b[A\n",
"Transcribing video: 98% 48/49 [00:55<00:01, 1.12s/it]\u001b[A\n",
"Transcribing video: 100% 49/49 [00:55<00:00, 1.14s/it]\n",
"transcribing vids: 80% 8/10 [07:11<01:48, 54.03s/it]\n",
"Creating .wav audio clips: 0% 0/48 [00:00<?, ?it/s]\u001b[A\n",
"Creating .wav audio clips: 100% 48/48 [00:00<00:00, 402.87it/s]\n",
"\n",
"created audio chunks - Jan-27-2022_-19\n",
"Cuda availability (PyTorch) is True\n",
"\n",
"\n",
"Transcribing video: 0% 0/48 [00:00<?, ?it/s]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 54.5 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 2% 1/48 [00:01<01:24, 1.81s/it]\u001b[A\n",
"Transcribing video: 4% 2/48 [00:02<01:13, 1.60s/it]\u001b[A\n",
"Transcribing video: 6% 3/48 [00:04<01:05, 1.46s/it]\u001b[A\n",
"Transcribing video: 8% 4/48 [00:05<00:59, 1.36s/it]\u001b[A\n",
"Transcribing video: 10% 5/48 [00:06<00:55, 1.28s/it]\u001b[A\n",
"Transcribing video: 12% 6/48 [00:07<00:51, 1.23s/it]\u001b[A\n",
"Transcribing video: 15% 7/48 [00:08<00:49, 1.20s/it]\u001b[A\n",
"Transcribing video: 17% 8/48 [00:09<00:47, 1.18s/it]\u001b[A\n",
"Transcribing video: 19% 9/48 [00:10<00:46, 1.18s/it]\u001b[A\n",
"Transcribing video: 21% 10/48 [00:11<00:44, 1.17s/it]\u001b[A\n",
"Transcribing video: 23% 11/48 [00:13<00:42, 1.15s/it]\u001b[A\n",
"Transcribing video: 25% 12/48 [00:14<00:41, 1.15s/it]\u001b[A\n",
"Transcribing video: 27% 13/48 [00:15<00:39, 1.14s/it]\u001b[A\n",
"Transcribing video: 29% 14/48 [00:16<00:38, 1.14s/it]\u001b[A\n",
"Transcribing video: 31% 15/48 [00:17<00:37, 1.14s/it]\u001b[A\n",
"Transcribing video: 33% 16/48 [00:18<00:36, 1.13s/it]\u001b[A\n",
"Transcribing video: 35% 17/48 [00:19<00:35, 1.13s/it]\u001b[A\n",
"Transcribing video: 38% 18/48 [00:21<00:33, 1.13s/it]\u001b[A\n",
"Transcribing video: 40% 19/48 [00:22<00:32, 1.13s/it]\u001b[A\n",
"Transcribing video: 42% 20/48 [00:23<00:31, 1.14s/it]\u001b[A\n",
"Transcribing video: 44% 21/48 [00:24<00:30, 1.13s/it]\u001b[A\n",
"Transcribing video: 46% 22/48 [00:25<00:29, 1.13s/it]\u001b[A\n",
"Transcribing video: 48% 23/48 [00:26<00:28, 1.12s/it]\u001b[A\n",
"Transcribing video: 50% 24/48 [00:27<00:26, 1.12s/it]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 52.5 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 52% 25/48 [00:29<00:30, 1.31s/it]\u001b[A\n",
"Transcribing video: 54% 26/48 [00:30<00:27, 1.25s/it]\u001b[A\n",
"Transcribing video: 56% 27/48 [00:31<00:25, 1.20s/it]\u001b[A\n",
"Transcribing video: 58% 28/48 [00:32<00:23, 1.17s/it]\u001b[A\n",
"Transcribing video: 60% 29/48 [00:33<00:22, 1.17s/it]\u001b[A\n",
"Transcribing video: 62% 30/48 [00:35<00:20, 1.16s/it]\u001b[A\n",
"Transcribing video: 65% 31/48 [00:36<00:19, 1.15s/it]\u001b[A\n",
"Transcribing video: 67% 32/48 [00:37<00:18, 1.14s/it]\u001b[A\n",
"Transcribing video: 69% 33/48 [00:38<00:17, 1.14s/it]\u001b[A\n",
"Transcribing video: 71% 34/48 [00:39<00:15, 1.14s/it]\u001b[A\n",
"Transcribing video: 73% 35/48 [00:40<00:14, 1.14s/it]\u001b[A\n",
"Transcribing video: 75% 36/48 [00:41<00:13, 1.14s/it]\u001b[A\n",
"Transcribing video: 77% 37/48 [00:43<00:12, 1.13s/it]\u001b[A\n",
"Transcribing video: 79% 38/48 [00:44<00:11, 1.13s/it]\u001b[A\n",
"Transcribing video: 81% 39/48 [00:45<00:10, 1.13s/it]\u001b[A\n",
"Transcribing video: 83% 40/48 [00:46<00:09, 1.13s/it]\u001b[A\n",
"Transcribing video: 85% 41/48 [00:47<00:08, 1.14s/it]\u001b[A\n",
"Transcribing video: 88% 42/48 [00:48<00:06, 1.14s/it]\u001b[A\n",
"Transcribing video: 90% 43/48 [00:49<00:05, 1.14s/it]\u001b[A\n",
"Transcribing video: 92% 44/48 [00:50<00:04, 1.13s/it]\u001b[A\n",
"Transcribing video: 94% 45/48 [00:52<00:03, 1.14s/it]\u001b[A\n",
"Transcribing video: 96% 46/48 [00:53<00:02, 1.13s/it]\u001b[A\n",
"Transcribing video: 98% 47/48 [00:54<00:01, 1.12s/it]\u001b[A\n",
"Transcribing video: 100% 48/48 [00:55<00:00, 1.15s/it]\n",
"transcribing vids: 90% 9/10 [08:11<00:55, 55.75s/it]\n",
"Creating .wav audio clips: 100% 33/33 [00:00<00:00, 369.75it/s]\n",
"\n",
"created audio chunks - Jan-27-2022_-19\n",
"Cuda availability (PyTorch) is True\n",
"\n",
"\n",
"Transcribing video: 0% 0/33 [00:00<?, ?it/s]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 53.6 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 3% 1/33 [00:01<00:58, 1.82s/it]\u001b[A\n",
"Transcribing video: 6% 2/33 [00:02<00:50, 1.62s/it]\u001b[A\n",
"Transcribing video: 9% 3/33 [00:04<00:44, 1.47s/it]\u001b[A\n",
"Transcribing video: 12% 4/33 [00:05<00:39, 1.38s/it]\u001b[A\n",
"Transcribing video: 15% 5/33 [00:06<00:36, 1.32s/it]\u001b[A\n",
"Transcribing video: 18% 6/33 [00:07<00:34, 1.27s/it]\u001b[A\n",
"Transcribing video: 21% 7/33 [00:08<00:32, 1.23s/it]\u001b[A\n",
"Transcribing video: 24% 8/33 [00:09<00:30, 1.20s/it]\u001b[A\n",
"Transcribing video: 27% 9/33 [00:11<00:28, 1.18s/it]\u001b[A\n",
"Transcribing video: 30% 10/33 [00:12<00:27, 1.19s/it]\u001b[A\n",
"Transcribing video: 33% 11/33 [00:13<00:25, 1.18s/it]\u001b[A\n",
"Transcribing video: 36% 12/33 [00:14<00:24, 1.17s/it]\u001b[A\n",
"Transcribing video: 39% 13/33 [00:15<00:23, 1.17s/it]\u001b[A\n",
"Transcribing video: 42% 14/33 [00:16<00:22, 1.17s/it]\u001b[A\n",
"Transcribing video: 45% 15/33 [00:18<00:20, 1.16s/it]\u001b[A\n",
"Transcribing video: 48% 16/33 [00:19<00:19, 1.16s/it]\u001b[A\n",
"Transcribing video: 52% 17/33 [00:20<00:18, 1.16s/it]\u001b[A\n",
"Gen RAM Free: 11.0 GB | Proc size: 8.0 GB | 2 CPUs loaded at 52.7 % |\n",
"\n",
"GPU RAM Free: 13435MB | Used: 2725MB | Util 17% | Total 16160MB\n",
"\n",
"\n",
"Transcribing video: 55% 18/33 [00:22<00:20, 1.35s/it]\u001b[A\n",
"Transcribing video: 58% 19/33 [00:23<00:18, 1.29s/it]\u001b[A\n",
"Transcribing video: 61% 20/33 [00:24<00:16, 1.25s/it]\u001b[A\n",
"Transcribing video: 64% 21/33 [00:25<00:14, 1.23s/it]\u001b[A\n",
"Transcribing video: 67% 22/33 [00:26<00:13, 1.22s/it]\u001b[A\n",
"Transcribing video: 70% 23/33 [00:27<00:12, 1.21s/it]\u001b[A\n",
"Transcribing video: 73% 24/33 [00:29<00:10, 1.19s/it]\u001b[A\n",
"Transcribing video: 76% 25/33 [00:30<00:09, 1.18s/it]\u001b[A\n",
"Transcribing video: 79% 26/33 [00:31<00:08, 1.19s/it]\u001b[A\n",
"Transcribing video: 82% 27/33 [00:32<00:07, 1.18s/it]\u001b[A\n",
"Transcribing video: 85% 28/33 [00:33<00:05, 1.19s/it]\u001b[A\n",
"Transcribing video: 88% 29/33 [00:35<00:04, 1.19s/it]\u001b[A\n",
"Transcribing video: 91% 30/33 [00:36<00:03, 1.18s/it]\u001b[A\n",
"Transcribing video: 94% 31/33 [00:37<00:02, 1.18s/it]\u001b[A\n",
"Transcribing video: 100% 33/33 [00:38<00:00, 1.17s/it]\n",
"transcribing vids: 100% 10/10 [08:53<00:00, 53.33s/it]\n",
"SC_pipeline - transcribed audio: 0% 0/10 [00:00<?, ?it/s]\n",
"Top 10 Key Phrases from YAKE, with max n-gram length 3\n",
"['finite sum problem',\n",
" 'large skilled machine',\n",
" 'gradient descent',\n",
" 'image data set',\n",
" 'pretty big sum',\n",
" 'day machine learning',\n",
" 'end training data',\n",
" 'data logistic regression',\n",
" 'ancient optimisation methods',\n",
" 'deep neural networks']\n",
"SC_pipeline - transcribed audio: 10% 1/10 [00:53<08:05, 53.94s/it]\n",
"Top 10 Key Phrases from YAKE, with max n-gram length 3\n",
"['dimensional optimization problem',\n",
" 'stocastic gradient descent',\n",
" 'make rapid initial',\n",
" 'interesting thing happening',\n",
" 'individual component looked',\n",
" 'machine learning',\n",
" 'closed form solution',\n",
" 'millions toxic steps',\n",
" 'key mathematics idea',\n",
" 'making pretty good']\n",
"SC_pipeline - transcribed audio: 20% 2/10 [01:45<07:04, 53.12s/it]\n",
"Top 10 Key Phrases from YAKE, with max n-gram length 3\n",
"['training data point',\n",
" 'deep neuro networks',\n",
" 'big mini batch',\n",
" 'single starcastic gradient',\n",
" 'data unseen data',\n",
" 'theory big mini',\n",
" 'resembling gradient dissent',\n",
" 'reason people love',\n",
" 'dynasties large neuro',\n",
" 'practical challenges people']\n",
"SC_pipeline - transcribed audio: 30% 3/10 [02:21<05:37, 48.19s/it]\n",
"Top 10 Key Phrases from YAKE, with max n-gram length 3\n",
"['discreet time filter',\n",
" 'time frequency axis',\n",
" 'butterworth filter times',\n",
" 'continuous time',\n",
" 'frequency response public',\n",
" 'filter amusing capacity',\n",
" 'stop band tolerance',\n",
" 'allowable stop band',\n",
" 'parameter capacity equal',\n",
" 'setting simply corresponds']\n",
"SC_pipeline - transcribed audio: 40% 4/10 [03:07<04:44, 47.47s/it]\n",
"Top 10 Key Phrases from YAKE, with max n-gram length 3\n",
"['discreet time filter',\n",
" 'time frequency response',\n",
" 'filter continuous time',\n",
" 'continuous time frequencies',\n",
" 'tostable discreet time',\n",
" 'stop band specifications',\n",
" 'pick capital equal',\n",
" 'variant design procedure',\n",
" 'digital filter approximately',\n",
" 'transfer function capital']\n",
"SC_pipeline - transcribed audio: 50% 5/10 [03:52<03:53, 46.79s/it]\n",
"Top 10 Key Phrases from YAKE, with max n-gram length 3\n",
"['continuous time filter',\n",
" 'discreet time frequency',\n",
" 'linear frequency characteristic',\n",
" 'designing discreet time',\n",
" 'time filter equivalently',\n",
" 'acomputerated designed procedures',\n",
" 'bilineer transformation doesn',\n",
" 'totally avoids allowing',\n",
" 'pretty uncomfortable place',\n",
" 'mapping continuous']\n",
"SC_pipeline - transcribed audio: 60% 6/10 [04:05<02:26, 36.54s/it]\n",
"Top 10 Key Phrases from YAKE, with max n-gram length 3\n",
"['wave equation',\n",
" 'square pause',\n",
" 'progressing wave',\n",
" 'open corseware continue',\n",
" 'creative common license',\n",
" 'harmonic wave stay',\n",
" 'view additional materials',\n",
" 'case',\n",
" 'omega square',\n",
" 'string']\n",
"SC_pipeline - transcribed audio: 70% 7/10 [04:55<02:02, 40.74s/it]\n",
"Top 10 Key Phrases from YAKE, with max n-gram length 3\n",
"['square pause works',\n",
" 'harmonic pocasing wave',\n",
" 'add additional turn',\n",
" 'pacheti square equal',\n",
" 'progressing wave propugating',\n",
" 'question include question',\n",
" 'beat phenomena happens',\n",
" 'time quickly produce',\n",
" 'involve infinite number',\n",
" 'cancer frequency omega']\n",
"SC_pipeline - transcribed audio: 80% 8/10 [05:47<01:27, 43.88s/it]\n",
"Top 10 Key Phrases from YAKE, with max n-gram length 3\n",
"['face velocity',\n",
" 'omega',\n",
" 'roughly kick sheet',\n",
" 'velocity essentially faster',\n",
" 'case',\n",
" 'slope',\n",
" 'speed',\n",
" 'nondispersive medium',\n",
" 'point',\n",
" 'close small']\n",
"SC_pipeline - transcribed audio: 90% 9/10 [06:33<00:44, 44.60s/it]\n",
"Top 10 Key Phrases from YAKE, with max n-gram length 3\n",
"['equal lagrubulocity essentially',\n",
" 'boundary conditions',\n",
" 'dispersion relation omega',\n",
" 'structure essentially moving',\n",
" 'omega oubuquetis equal',\n",
" 'omega',\n",
" 'frequency omega depends',\n",
" 'face velocity',\n",
" 'equal',\n",
" 'original shape compared']\n",
"SC_pipeline - transcribed audio: 100% 10/10 [07:05<00:00, 42.50s/it]\n",
"\n",
"\n",
"Finished at: Jan-27-2022_-19. Total RT was 17.039 mins\n",
"relevant files for run are in: \n",
"/content/vid2cleantxt/examples/TEST_folder_edition/v2clntxt_transcriptions \n",
" and: \n",
"/content/vid2cleantxt/examples/TEST_folder_edition/v2clntxt_transc_metadata\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"#@title print out a finished file\n",
"!cat /content/vid2cleantxt/examples/TEST_folder_edition/v2clntxt_transcriptions/results_SC_pipeline/mit_signals_000_vid_2_txt_jan_27202219_full_NSC_SBD.txt"
],
"metadata": {
"cellView": "form",
"id": "XxWxj8IK8BiM",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"outputId": "80d3435e-f75c-4bab-ec5c-dcc921a86ba1"
},
"execution_count": 11,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/html": [
"\n",
" <style>\n",
" pre {\n",
" white-space: pre-wrap;\n",
" }\n",
" </style>\n",
" "
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"The following content is provided under a creative common license your support will help up if the open coarseware continue to offer high quality educational resources for free to make a donation or view additional materials from hundreds of many if the courses visit up if the open coarseware t o see w dot with i t dot e d s.\n",
"Ae pi a d eeeee e e we eeee we e e a care o a a ae a pi.\n",
"Last time we introduced the notion of mapping continuous time filters to discreet time filters and we developed impulse and variance as one useful technique for carrying out that type of mapping what I'd like to do in this lecture is illustrate.\n",
"Impulse and variance as a designed procedure in the context of one specific class of filters namely butterworth filters and then following that we'll proceed on to discuss another very important and useful mapping or designed procedure referred to as the bilineer transformation so to begin let me just would.\n",
"Cause briefly what the class of butterworth filters is that specifically the butterworth filters are defined through their frequency response or transfer function and i am using capital public to debate a butterworth filter and by definition the magnitude squared to the frequency response of a butterworth filter is given by this expression.\n",
"And for example if you were equal to one then this would simply correspond to the magnitude squared of the frequency response for a first order differential equation now if you look at the frequency response public of image for this class of painters I've illustrated that below and.\n",
"What we see is that the frequency response starts at unity because if that that's the way that it's normalized and it has a monotonic characteristic in the passband and in the stopband at a frequency equal to the perimeter omagus of see up here which is referred to as the cut off frequency the butterworth filter frequency response.\n",
"Always goes through the same point namely point seven to seven and as the order of the butterworth filter capital and increases the transition from the pass band to the stop band becomes sharper and sharper so far higher order filters than the frequency response is flatter in the pass band and drops off more.\n",
"Icly and attenuates more in the stop many now in designing butterworth filters what we will want to look at is the location of the poles of the system function and we can infer those from our definition of what the frequency response for the butterworth filter is in particular.\n",
"We have this expression for the magnitude squared of the frequency response and we recognize that of course as public of a omega times be of minus a image that's what the magnitude squared will be equal to and in order to convert this to an expression describing.\n",
"The system function or in terms of the more general replace transformed variable as what we recognize is that a image in the more general setting simply corresponds to the palace transformed variable as so this product in fact is the replace transform for a equal to do image more generally as.\n",
"On this is the result of evaluating public of s times public of minus s act s equals go image consequently comparing this expression with this statement leads us to the conclusion that the transfer function public of us of the butterworth filter times be of minus s is given by the expression that I find.\n",
"Care here simply replacing our image by us now what we want to look at are the poles of b of s that's what we'll want to get as we design a butterworth filter and we can recognize the poles of this product simply by looking at the roots of the denominator polynomil and.\n",
"Those roots are just taking account of this factor to on those roots are at a omagu six times the two on roots of minus one those roots in fact all lie on a circle and the consequence of that is that the poles of.\n",
"This expression is on a circle the circle is of radius omagus of sea and the poles are distributed around the circle so here I've illustrated the poles of public of a times by of minus s for the specific case where capital in is equal to three so there are a total of six poles around this circle.\n",
"And then for this specific case the poles are spaced by sixty degrees now we have be of s times by of minus us to get the system function for the butterworth filter we'd like to get be of s and the question now is how do we get that well the thing to recognize is that wherever this factor.\n",
"Has a route this factor has to have a route at the negative location so in fact when we look at these poles we compare them with this for example associated with public of us this associated with public of minus s and likewise we compare these two together likewise we compare these two together and so we can extract be of s.\n",
"From this product simply by taking one pole out of each of those pairs now a question of course is out of each pair which one do we associate with be of s and which do we associate with public of minus s and the answer drops out fairly simply if we recognize that if we want to design filters that are stable.\n",
"Then be of s the transfer function that we're designing must have all its poles in the left half of the s plane so in fact we would associate out of each of these pairs we would associate the left half plane pole with public of s and so the transfer function for the butterworth filter for this particular case where the parameters where.\n",
"This designates the parameter omagu sub sea and capital as is three namely a third order butterworth filter is this set of pole locations given those of course we can figure out simply through algebraic means what the transfer functioned by of sea all right so that's what butterworth filters are and now what I'd like to do is talk about.\n",
"The design of a digital butterworth filter using the design technique that we introduced last time namely impulse and variance and the context in which it will phrase the design is the context of mapping a continuous time signal to a discreet time signal shown.\n",
"Crying out filtering using the discreet time filter that we're designing and then mapping back so we're talking about now a discreet time filter that we want to design through impulse and invarience from butterworth filters from continuous time butterworth filters and we're going to get our design specifications in the context of have.\n",
"Considered discreet time processing of continuous time signals where we will map from a continuous time signal to a sequence carry out the filtering with the discreet time filter that we're going to design and then we will take the resulting filtered output.\n",
"And map it back to the continuous time signal but this discreet time filter is the one that we're talking about designing and for a choice of perimeter there's a sampling frequency of course involved in this process and the value that I'll pick for the sampling frequency is ten killaherts of all fairly.\n",
"Straightforward so far and so since we have a sampling rate of ten killeherts we want to first look at our specifications on the desired continuous time filter and then map those two appropriate specifications on the discreet time filter and.\n",
"What I'll pick for the desired specifications on the continuous time filter is that as one killer hurts i will ask that the continuous time frequency response be down by no more than one d be in comparison with.\n",
"Value at image equal zero so that in effect specifies the behaviour in the pass band or the specifications on the pass band and for the stop band I'll specify that the filter is down by fifteen d be by the time we've got into one and a half killerherts so we have essentially.\n",
"The beginning of the transition band the end of the pass band at one killehurts and the beginning of the stop band at one point five killehurts and since we're talking about designing a butterworth filter we know that the butterworth filter is monotonic in the pass band and stop band and so we'll have a filter specification something as I show here.\n",
"This represents the allowable past band tolerance this is the allowable stop band tolerance and if I can draw this without a getting myself into trouble essentially we're looking for a filter then then it always stays between the specified boundaries here.\n",
"Now what we have to figure out is what the corresponding specifications are for the digital filter and the strategy let me emphasize is that we have a situation where we're doing continuous time a discreet time processing of continuous time signals and we have a set of specifics.\n",
"Ones associated with that that imposes specifications on our discreet time filter and then we want to design the discreet time filter using impulse and variance and that's the discreet time filter that we'll use in the overall system right now we want specifications on the discreet time filter and.\n",
"We want the continuous overall equivalent system to have certain and meet certain specifications at certain frequencies related to continuous time frequencies recall that when we sample a continuous time signal there's a very specific mapping from the continuous time frequency access to the discreet time.\n",
"Frequency axis in particular the sampling frequency gets mapped to two pre well that means that our other critical frequencies get mapped in proportion to that so one killer hurts which is a tenth of the sampling frequency would then convert to a discreet time frequency of point to a.\n",
"And one and a half killeherts will convert to a discreet time frequency of point three pie so what this says is that for the discreet time filter we would like the same behaviour but at frequencies or the same specifications but at frequencies not.\n",
"Analyzed to the discreet time frequency axis that means that we want the discreet time frequency image frequency response magnitude to be greater than are equal to minus one d be at two tenths pie corresponding to the one killahurts in continuous time and for the beginning of the stop and.\n",
"That would occur at point three of at which point we want this less than are equal to minus fifteen so those are our discreet time specifications and we now want to design the discreet time filter using impulse and variance now in impulse and variance as you recall it corresponds to.\n",
"Sampling generating an impulse response which is a sampled version of the continuous time impulse response and there is a temptation naturally to think of this parameter capital it as necessarily identical to the sampling of the system.\n",
"In which the filter is going to be used now this is a fairly subtle complicated tongue twisting issue but the bottom line on it the essential point is that the permanent capital to that we use in impulse and variant design is a totally different unrelated and in fact as it turns out arbitrary parameters.\n",
"Which is not necessarily pegged to the sampling frequency and I think it would be difficult for me to totally clarify that during the lecture it's discussed more in the book and certainly you should take plenty of time to reflect on it right but let's now look them at where we are in our designed.\n",
"Procedure and specifically what it is that we need to do in order to design the digital butterworth filter now we have a set of specifications that we we've generated relating essentially to how we want the pass band of the digital filter and the stop end of the digital filter to be.\n",
"Have of course since this isn't an ideal filter it has some transition from husband to stop end and as we discussed last time there is a aliusing which we need to at least be aware of we've specified certain frequencies along this axis which are easily converted by.\n",
"Relating the two axes through this mapping are easily related back to the continuous time frequency axis as we have here and in particular now if we were to simply pick that perimeter in the impulse and variant design capital it as.\n",
"Equal to unity and I indicated just a minute ago that we can pick it arbitrarily if I pick it as unity then the procedure would consist of designing the continuous time butterworth filter with meeting the or exceeding the appropriate specifications and then going through the impulse and variant procedure.\n",
"All right so let's do that then we want the discreet time impulse response to be the continuous time impulse response sampled and for convenience I'm going to pick this parameter capacity equal to one that means that the frequency normalization between the.\n",
"Discreet time frequency axis and the continuous time frequency axis in fact is that those axes are scaled identically because capacity is equal to one and so now we want the analogue or continuous time specifications and so what we need to do then is design a butterworth filter amusing capacity.\n",
"Be here again to counter the frequency response to the butterworth filter the butterworth filter to have a magnitude which is greater than are equal to minus one d be prior to the frequency zero point to pie and less than are equal to minus fifteen at a frequency beyond zero point three pie and so snow.\n",
"What we need to do is determine capital in and image sub see in order to meet or exceed those specifications now if you go through the associated algebra in doing that let's say that you decide that you want a pick capital in and image sub see to exactly meet those inequalities at the two frequencies point.\n",
"Pine point three pie what you'll find after going through the algebra is that they're exactly met if capital n is five point right eight and omagus of a is point seven or four seven and this obviously can't isn't satisfactory as parameters for the butterworth filter why is that the reason is.\n",
"They case.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
""
],
"metadata": {
"id": "O3dq_xMR91_J"
},
"execution_count": 9,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment