{ "cells": [ { "cell_type": "code", "execution_count": 2, "id": "da8c9577", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Populating the interactive namespace from numpy and matplotlib\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/home/georg/venvs/ml/lib/python3.8/site-packages/IPython/core/magics/pylab.py:159: UserWarning: pylab import has clobbered these variables: ['f']\n", "`%matplotlib` prevents importing * from pylab and numpy\n", " warn(\"pylab import has clobbered these variables: %s\" % clobbered +\n" ] } ], "source": [ "%pylab inline" ] }, { "cell_type": "code", "execution_count": 3, "id": "7ad009ea", "metadata": {}, "outputs": [], "source": [ "import os\n", "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"\"" ] }, { "cell_type": "code", "execution_count": 4, "id": "f3b73488", "metadata": {}, "outputs": [], "source": [ "import time\n", "import os\n", "import tqdm\n", "import shutil\n", "import random\n", "import funcy\n", "import json\n", "import numpy as np\n", "import multiprocessing\n", "import pandas as pd\n", "from suno_utils.audio import Audio\n", "from suno_utils.utils.podcasts import load_podcast_db, get_title, get_description, load_rss_text" ] }, { "cell_type": "code", "execution_count": null, "id": "de886102", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "e4b9f660", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "244cfef4", "metadata": {}, "source": [ "## get hinglish sample" ] }, { "cell_type": "code", "execution_count": 10, "id": "ec54d72d", "metadata": {}, "outputs": [], "source": [ "RAW_RSS_DIR = \"/mnt/data-ssd-1/data/podcasts/bulk_rss_feeds/raw_files/\"\n", "podcast_df = load_podcast_db(\n", " \"/mnt/data-ssd-1/data/podcasts/meta/podcastindex_feeds.db\", \n", " english_only=True, \n", " anchor_only=True,\n", ")\n", "podcast_ids = podcast_df[\"id\"].tolist()\n", "url_map = podcast_df.set_index(\"id\")[\"link\"]\n", "n_episode_map = podcast_df.set_index(\"id\")[\"episode_count\"]" ] }, { "cell_type": "code", "execution_count": 11, "id": "0ea65636", "metadata": {}, "outputs": [], "source": [ "def _foo(podcast_id):\n", " try:\n", " rss_text = load_rss_text(RAW_RSS_DIR + \"{}.feed\".format(podcast_id))\n", " title = get_title(rss_text)\n", " description = get_description(rss_text)\n", " if \"hinglish\" in description.lower():\n", " return podcast_id, title, description\n", " except:\n", " pass\n", " return None" ] }, { "cell_type": "code", "execution_count": 12, "id": "7a6ac903", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "21 found\n", "took 0.3 mins\n" ] } ], "source": [ "p = multiprocessing.Pool(20)\n", "t0 = time.time()\n", "out = p.map(_foo, podcast_ids)\n", "t1 = time.time()\n", "out = [e for e in out if e is not None]\n", "p.close()\n", "p.join()\n", "print(len(out), \"found\")\n", "print(\"took\", round((t1 - t0) / 60, 1), \"mins\")" ] }, { "cell_type": "code", "execution_count": 14, "id": "85145297", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "126718 - https://anchor.fm/shwetaraj\n", "ALL HEART WITH SHWETA RAJ - ALL HEART IS A HINGLISH PODCAST which discusses RELEVANT topics with the aim of impacting anyone - girl/boy, old/young, doctor/house-help as they #StopScrolling and #StartListening with ALL HEART. If you have an interesting topic - reach out to me at mailallheart@gmail.com. Love, Shweta\n", "\n", "1791471 - https://anchor.fm/jasmeetsingh\n", "You Me DIGITAL - We discuss anything and everything related to Digital here. Beneficial for businesses, social organisations, students, home makers and everyone who’s interested in this space. Tune in to listen to perspectives from me and my friends in the industry on how ‘being digital’ is changing our lives. Language used will be Hinglish !\n", "\n", "1975494 - https://anchor.fm/controlA\n", "Control A - Welcome to Control All channel Here you can listion book summary in hindi or hinglish, startup interviews, motivational speed etc Cover art photo provided by Jeremy Galliani on Unsplash: https://unsplash.com/@jeremyforlife\n", "\n", "3010476 - https://anchor.fm/matthew-chan58\n", "Chinglish - Chinglish, Chinese and English. The life of an ABC.\n", "\n", "3236538 - https://anchor.fm/priyasharma\n", "Through Life with Priya - This 6 ep. short Hinglish podcast has bite sized episodes about meandering through life. Growing up, I always thought that I was the only one making mistakes. Now that I'm an adult, nothing much has changed, really. No one talks about mistakes and stupidities and heartbreaks. I think I kinda owe it to my younger self. This podcast is about everything that life is - a sweet friend. ❤️\n", "\n", "3631739 - https://anchor.fm/the-vetalks-podcast0\n", "The Vetalks Podcast - “The Vetalks Podcast” is a podcast that would be focusing on a range of topics which are entertaining and relatable. Language: Hinglish\n", "\n", "3710931 - https://anchor.fm/haggdeindia\n", "Hagg De India - Hagg de India is a hinglish comedy podcast covering a wide range of subjects, but mostly dick talk. If you are easily offended, don't listen\n", "\n", "4386236 - https://anchor.fm/bakarcast-podcast\n", "Bakarcast - Hinglish podcast with @daaku & @the100rabh We talk about cutting edge technology, tech reviews.\n", "\n", "4943337 - https://anchor.fm/sahil8097\n", "The Morning SGX - Language- Hinglish :) Interested in Markets- Tune in!!\n", "\n" ] } ], "source": [ "import re\n", "\n", "excluded_terms = [\n", " \"music\", \"song\", \"teach\", \"poem\", \"poetr\", \"learn\", \"storie\", \"story\"\n", "]\n", "\n", "eids = []\n", "for e in out:\n", " if re.search(r\"|\".join([re.escape(e.lower()) for e in excluded_terms]), e[2], flags=re.IGNORECASE):\n", " continue\n", " if n_episode_map[e[0]] < 3:\n", " continue\n", " eids.append(e[0])\n", " print(e[0], \"-\", url_map[e[0]])\n", " print(e[1], \"-\", e[2])\n", " print()" ] }, { "cell_type": "code", "execution_count": 63, "id": "7590ff10", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "126718 - https://anchor.fm/shwetaraj\n", "ALL HEART WITH SHWETA RAJ - ALL HEART IS A HINGLISH PODCAST which discusses RELEVANT topics with the aim of impacting anyone - girl/boy, old/young, doctor/house-help as they #StopScrolling and #StartListening with ALL HEART. If you have an interesting topic - reach out to me at mailallheart@gmail.com. Love, Shweta\n", "\n", "1791471 - https://anchor.fm/jasmeetsingh\n", "You Me DIGITAL - We discuss anything and everything related to Digital here. Beneficial for businesses, social organisations, students, home makers and everyone who’s interested in this space. Tune in to listen to perspectives from me and my friends in the industry on how ‘being digital’ is changing our lives. Language used will be Hinglish !\n", "\n", "1975494 - https://anchor.fm/controlA\n", "Control A - Welcome to Control All channel Here you can listion book summary in hindi or hinglish, startup interviews, motivational speed etc Cover art photo provided by Jeremy Galliani on Unsplash: https://unsplash.com/@jeremyforlife\n", "\n", "3236538 - https://anchor.fm/priyasharma\n", "Through Life with Priya - This 6 ep. short Hinglish podcast has bite sized episodes about meandering through life. Growing up, I always thought that I was the only one making mistakes. Now that I'm an adult, nothing much has changed, really. No one talks about mistakes and stupidities and heartbreaks. I think I kinda owe it to my younger self. This podcast is about everything that life is - a sweet friend. ❤️\n", "\n", "3631739 - https://anchor.fm/the-vetalks-podcast0\n", "The Vetalks Podcast - “The Vetalks Podcast” is a podcast that would be focusing on a range of topics which are entertaining and relatable. Language: Hinglish\n", "\n", "4386236 - https://anchor.fm/bakarcast-podcast\n", "Bakarcast - Hinglish podcast with @daaku & @the100rabh We talk about cutting edge technology, tech reviews.\n", "\n", "4943337 - https://anchor.fm/sahil8097\n", "The Morning SGX - Language- Hinglish :) Interested in Markets- Tune in!!\n", "\n", "917569 - https://anchor.fm/missprerna\n", "Mere Nazar Se With Prerna - My Podcast is going to cover different topics and will contain variety. Some will be in Hindi and others in the English language. It will be interesting, Give it a try. It's based on my personal journal and experiences or my perspectives about different topics. You can reach me on my account mere_nazar_se @Instagram\n", "\n", "960677 - https://anchor.fm/harshshekhawat\n", "Making Sense With Harsh Shekhawat | Youth Coaching and Personal Branding Podcast - Welcome to Making Sense With Harsh Shekhawat. Making Sense With Harsh Shekhawat is a Youth Coaching and Personal Branding Podcast in Hindi and English. A Podcast where I share my Knowledge and Experience of Youth Coaching, Personal Branding, and Owning a Digital Agency. Being a dropout and experimenting with almost all the businesses I could possibly do, Life has taught me a lot, hence more for you to grasp! Subscribe to my podcast to get Daily Insights on things to improve and know in LIFE and hence, allow me to help you realize your Worth on this Planet Earth :)\n", "\n" ] } ], "source": [ "interesting_ids = [\n", " 917569,\n", " 960677,\n", " 126718,\n", " 1791471,\n", " 1975494,\n", " 3236538,\n", " 3631739,\n", " 4386236,\n", " 4943337,\n", "]\n", "\n", "for e in out:\n", " if e[0] in set(interesting_ids):\n", " print(e[0], \"-\", url_map[e[0]])\n", " print(e[1], \"-\", e[2])\n", " print()" ] }, { "cell_type": "code", "execution_count": null, "id": "3db461d7", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "40c5e2ab", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "f1810def", "metadata": {}, "source": [ "### get episodes" ] }, { "cell_type": "code", "execution_count": 28, "id": "d7e74bf1", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'917569;960677;126718;1791471;1975494;3236538;3631739;4386236;4943337;251567'" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "hinlish_podcast_ids = [\n", " 917569,\n", " 960677,\n", " 126718,\n", " 1791471,\n", " 1975494,\n", " 3236538,\n", " 3631739,\n", " 4386236,\n", " 4943337,\n", " 251567,\n", "]\n", "\";\".join([str(e) for e in hinlish_podcast_ids])" ] }, { "cell_type": "code", "execution_count": null, "id": "3c53c099", "metadata": {}, "outputs": [], "source": [ "python /home/georg/code/glockenspiel/suno_utils/suno_utils/scripts/fetch_podcasts.py \\\n", " --podcast_db_filepath=\"/mnt/data-ssd-1/data/podcasts/meta/podcastindex_feeds.db\" \\\n", " --podcast_ids=\"917569;960677;126718;1791471;1975494;3236538;3631739;4386236;4943337;251567\" \\\n", " --output_dir=\"/mnt/data-ssd-1/data/podcasts/audio\" \\\n", " --last_n_episodes=3" ] }, { "cell_type": "code", "execution_count": null, "id": "79197496", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "9a97da87", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "30377f25", "metadata": {}, "source": [ "# make slices" ] }, { "cell_type": "code", "execution_count": 34, "id": "4b89af38", "metadata": {}, "outputs": [], "source": [ "from suno_utils.audio import Audio\n", "import numpy as np\n", "\n", "PODCAST_IDS = set([\n", " \"917569\", \"960677\", \"126718\", \"1791471\", \"1975494\", \"3236538\", \"3631739\", \"4386236\", \"4943337\", \"251567\"\n", "])\n", "\n", "PODCAST_AUDIO_DIR = \"/mnt/data-ssd-1/data/podcasts/audio/\"" ] }, { "cell_type": "code", "execution_count": 35, "id": "a6a1e365", "metadata": {}, "outputs": [], "source": [ "episode_metas = []\n", "for podcast_id in PODCAST_IDS:\n", " podcast_dir = os.path.join(PODCAST_AUDIO_DIR, podcast_id)\n", " for fn in os.listdir(podcast_dir):\n", " try:\n", " filepath = os.path.join(podcast_dir, fn)\n", " duration_s = Audio.get_details(filepath)[\"duration_s\"]\n", " if duration_s >= 3*60:\n", " episode_id = re.sub(r\"\\.[^\\.]+$\", \"\", fn)\n", " episode_metas.append({\n", " \"podcast_id\": podcast_id, \n", " \"episode_id\": episode_id, \n", " \"filepath\": filepath, \n", " \"duration_s\": np.min([duration_s, 10*60]),\n", " })\n", " except:\n", " pass\n", "for filepath in [\n", " \"/home/georg/notebooks/datasets/hinglish/tmp/esxqinru1r8lp9j463d8vgsmeot7.mp3\",\n", "]:\n", " duration_s = Audio.get_details(filepath)[\"duration_s\"]\n", " if duration_s >= 3*60:\n", " episode_id = re.sub(r\"\\.[^\\.]+$\", \"\", fn)\n", " episode_metas.append({\n", " \"podcast_id\": \"000\", \n", " \"episode_id\": \"0000\", \n", " \"filepath\": filepath, \n", " \"duration_s\": np.min([duration_s, 10*60]),\n", " })" ] }, { "cell_type": "code", "execution_count": 38, "id": "e7df0034", "metadata": {}, "outputs": [], "source": [ "shutil.rmtree(\"tmp/segments\", ignore_errors=True)\n", "os.makedirs(\"tmp/segments\", exist_ok=True)" ] }, { "cell_type": "code", "execution_count": 39, "id": "8d4ecc13", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|██████████████████████████████████████████████| 21/21 [05:29<00:00, 15.69s/it]\n" ] } ], "source": [ "import random\n", "import tqdm\n", "from suno_utils.utils.slicer import get_segments\n", "import uuid\n", "\n", "SEGMENT_DIR = \"/home/georg/notebooks/datasets/hinglish/tmp/segments/\"\n", "\n", "segment_metas = []\n", "for episode_meta in tqdm.tqdm(episode_metas):\n", " audio = Audio.from_file(episode_meta[\"filepath\"]).get_slice(to_s=episode_meta[\"duration_s\"])\n", " episode_segments = get_segments(\n", " audio,\n", " min_gap_s=0.05,\n", " vad_level=3,\n", " min_dur_s=10,\n", " max_dur_s=20,\n", " )\n", " for segment_audio, (start_s, end_s) in episode_segments:\n", " segment_id = str(uuid.uuid4())\n", " segment_filepath = os.path.join(SEGMENT_DIR, segment_id) + \".mp3\"\n", " segment_audio.to_mp3(segment_filepath)\n", " segment_metas.append({\n", " \"podcast_id\": episode_meta[\"podcast_id\"], \n", " \"episode_id\": episode_meta[\"episode_id\"], \n", " \"uuid\": segment_id,\n", " \"source_audio_offset_s\": start_s,\n", " \"filepath\": segment_filepath, \n", " \"duration_s\": end_s - start_s,\n", " })\n", "random.seed(6006)\n", "random.shuffle(segment_metas)" ] }, { "cell_type": "code", "execution_count": 40, "id": "cfb5d7d9", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[{'podcast_id': '960677',\n", " 'episode_id': 'eb89753e-d2e4-4852-a3ec-5d2a078a1f89',\n", " 'uuid': 'ac06d748-b212-4866-b30f-11977bee30ef',\n", " 'source_audio_offset_s': 467.25,\n", " 'filepath': '/home/georg/notebooks/datasets/hinglish/tmp/segments/ac06d748-b212-4866-b30f-11977bee30ef.mp3',\n", " 'duration_s': 18.0},\n", " {'podcast_id': '3631739',\n", " 'episode_id': '4ccff553-81da-4d29-9368-c5c8f01cc086',\n", " 'uuid': '9f80ce02-c8a3-45e5-8e93-9c47aeb88213',\n", " 'source_audio_offset_s': 183.23,\n", " 'filepath': '/home/georg/notebooks/datasets/hinglish/tmp/segments/9f80ce02-c8a3-45e5-8e93-9c47aeb88213.mp3',\n", " 'duration_s': 18.52000000000001}]" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "segment_metas[:2]" ] }, { "cell_type": "code", "execution_count": 44, "id": "c37fced8", "metadata": {}, "outputs": [], "source": [ "with open(\"samples_20.json\", \"w\") as f:\n", " json.dump(segment_metas, f)" ] }, { "cell_type": "code", "execution_count": null, "id": "8a2087ca", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 119, "id": "c32876d0", "metadata": {}, "outputs": [], "source": [ "l = [\n", " ('126718', 'd76bf592-8ec8-4985-b0f5-f0b2b06a6616'),\n", " ('1791471', '376e80bd-d038-4e0e-81fc-c5e76c6b4fb3'),\n", " ('3236538', '712f521a-614e-4e8a-a7a9-56a8ebf9a257'),\n", " ('3631739', '26f1f367-35a9-4a59-ab64-f429737e10de'),\n", " ('4386236', '459f9529-8ff4-4489-a165-fbe216c805fc'),\n", " ('4943337', '5c87c888-0b16-4153-849e-b616c1af2bcf'),\n", " ('917569', '60c57ab2-1a0b-4626-b1ca-463165fa343a'),\n", " ('960677', '3fa95889-69a4-4749-9462-556f300106cc'),\n", "]" ] }, { "cell_type": "code", "execution_count": null, "id": "346905ea", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 130, "id": "5b9a1e0b", "metadata": {}, "outputs": [], "source": [ "PODCAST_AUDIO_DIR = \"/mnt/data-ssd-1/data/podcasts/audio/\"" ] }, { "cell_type": "code", "execution_count": 132, "id": "88b6da85", "metadata": {}, "outputs": [], "source": [ "for e in l:\n", " d = PODCAST_AUDIO_DIR + str(e[0]) + \"/\"\n", " fn = [ee for ee in os.listdir(d) if e[-1] in ee][0]\n", " Audio.from_file(d + fn).get_slice(0, 15*60).to_mp3(\"samples_2h/\" + e[-1] + \".mp3\")" ] }, { "cell_type": "code", "execution_count": 133, "id": "8f24ca35", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "26f1f367-35a9-4a59-ab64-f429737e10de.mp3\r\n", "376e80bd-d038-4e0e-81fc-c5e76c6b4fb3.mp3\r\n", "3fa95889-69a4-4749-9462-556f300106cc.mp3\r\n", "459f9529-8ff4-4489-a165-fbe216c805fc.mp3\r\n", "5c87c888-0b16-4153-849e-b616c1af2bcf.mp3\r\n", "60c57ab2-1a0b-4626-b1ca-463165fa343a.mp3\r\n", "712f521a-614e-4e8a-a7a9-56a8ebf9a257.mp3\r\n", "d76bf592-8ec8-4985-b0f5-f0b2b06a6616.mp3\r\n" ] } ], "source": [ "!ls samples_2h" ] }, { "cell_type": "code", "execution_count": 135, "id": "1ef186e8", "metadata": {}, "outputs": [], "source": [ "!tar -czf samples_2h.tar.gz samples_2h" ] }, { "cell_type": "code", "execution_count": null, "id": "98b59747", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "4510bac5", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "9f460afe", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "be712ad1", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "36a20b75", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "17a53d8f", "metadata": {}, "source": [ "### Listen and select" ] }, { "cell_type": "code", "execution_count": 45, "id": "b290571d", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "537 segments\n" ] } ], "source": [ "with open(\"samples_20.json\") as f:\n", " segment_metas = json.load(f)\n", "print(len(segment_metas), \"segments\")" ] }, { "cell_type": "code", "execution_count": 50, "id": "f7629c91", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "4386236 - 68a18fce-9b53-4628-bb1c-0ae5aa63151f\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "126718 - c6646845-7daa-4f09-ad26-60496678a806\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "000 - f36bdfae-e4a5-4125-aa09-c39d05dc4ce2\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "4386236 - 15f36863-fa5b-42fe-be1e-4f3d5a878def\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "960677 - 73ee0b76-624d-4f1c-9a18-e430dbbdde84\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "3631739 - 66765eb6-3440-4f35-82fd-e21dc5c3923c\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "960677 - c76ea040-2c8d-48a0-aa1c-ef77b9a22a31\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "1791471 - dd609773-81bb-4482-a95e-98cdea419fa7\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "4386236 - ae214d06-f8d6-4271-a8ec-c4b6725cdf41\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "917569 - 72938abb-2943-4b68-a8e2-0f80bdf0baf0\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "917569 - 06cc9b8d-02aa-4151-b124-5b6377c15e2f\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "960677 - d284dd15-041a-47c2-bf72-0e0486bf2cef\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "960677 - 365386dc-2383-46cf-9e16-e84b0b23ebe1\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "960677 - 25001259-c9e3-49e6-a9f2-553d25e493dc\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "126718 - 52a3d988-db18-4a59-9144-604859f25fa8\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "1791471 - 4c1d86fc-4a28-41d8-8952-4728ab15b6bc\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "4386236 - 2fe940e3-8a7e-4220-9c78-e802da3586e9\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "4386236 - 20b1d4e1-62ac-478f-b11c-297572f011db\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "3631739 - 70e6f33c-2da1-4922-8c76-bee53a9b9387\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "917569 - 9a00506c-88a5-4f38-a494-f9f0320a1f00\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "000 - 85661fc2-6a3c-46bc-87a0-c587bc750053\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "960677 - e6b75669-1d5e-40ec-ab3d-481dcbc04022\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "3631739 - 846be21d-e522-403d-81d7-f534f04b9722\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "3236538 - 79200463-3dc7-413d-abfc-695e29161eeb\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "4943337 - 0caf18bf-d589-4921-a533-b7ba42e3020a\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "126718 - 4ebd9a00-f4ad-4cb5-8d8f-7ce5cdcaab0d\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "126718 - c458e798-e52f-4760-a482-02d35236bbf0\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "4386236 - b9fbc7e7-a8fe-474d-b9bf-8db14ce04c30\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "960677 - 4735fd78-51c8-4e8a-a23a-47e74145bb9f\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "3631739 - 8e1a510d-54f7-4d37-99e7-965230abba86\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "4943337 - 083d1049-3271-4e65-9a42-eae728135543\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "3631739 - 06ec2013-89ed-49cc-bedf-727b4d655782\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "4943337 - f5ea2a07-2515-4189-9d59-0706bc53409c\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "3236538 - b609a47b-a3df-409a-883e-ba9d9beb6139\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "4943337 - 0bf05df2-73af-4d04-a1b2-26084f96913e\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "3631739 - c284b82a-3b1a-43f4-b3da-e8f1d8823a6f\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "3631739 - f93dd5fd-9bd7-4428-8503-22e243d4f553\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "4386236 - abb0908c-6234-42d0-a956-927f1520c07d\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "3631739 - 99e2e24c-a1d6-4186-bb3d-486a85d2a9a4\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "960677 - 7db26df6-0584-4746-9a9c-98a1a29d62cf\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "126718 - 9a2f29a2-2829-4f45-876c-97deea0b10d2\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "917569 - 14c984f5-65f7-4822-b52d-40d3d99ced19\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "3631739 - 5214fe7b-57a7-4b08-b879-3aa7a63341ea\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "1791471 - 7e39e103-4d1b-4c4a-8d17-3efb96cb3495\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "960677 - a9d686b9-aa6d-4932-9b4e-d7f139236c87\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "126718 - b376f240-2b7c-407d-b625-906926dc9849\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "4386236 - 4272a4d1-049f-4386-9b09-0cdf537238c4\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "1791471 - dc8188c3-02ec-45c5-967e-aa26915d974d\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "4386236 - f9d7560f-c93a-4954-aa63-6228d24775f3\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n", "1791471 - 38f437c6-9dfc-4746-b0ab-305c1ef8209b\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "----------\n" ] } ], "source": [ "for e in segment_metas[50:100]:\n", " print(e[\"podcast_id\"], \"-\", e[\"uuid\"])\n", " Audio.from_file(e[\"filepath\"]).play()\n", " print(\"-\"*10)" ] }, { "cell_type": "code", "execution_count": null, "id": "4072455d", "metadata": {}, "outputs": [], "source": [ "# 960677 - 6afdc41e-aed9-46a0-94af-0a1b3f41dca2\n", "# 3631739 - bf8b4f3c-844a-46f1-bdcc-60c7fc2c4162\n", "# 960677 - ba1c544f-70d6-4041-aa78-014b77d7a1a8\n", "# 3631739 - 51228f13-95e4-4284-86c9-e6b41003b816\n", "# 960677 - f50a541c-0896-4275-9e5b-0308c737da14\n", "# 960677 - dc6ab15e-867f-4bda-a343-25cdf4edd88c\n", "# 4386236 - 3fa8f54c-f83f-4fa5-ba64-29403a396dd8\n", "# 126718 - f49e0abf-e46e-43d9-80c5-76378f50dc74\n", "# 960677 - a8e46d29-3ea1-4130-ba1c-e751b418f45a\n", "# 3631739 - 027b55b2-1d60-4fde-b6c9-8c975b5eb5e4\n", "\n", "# 000 - 3b9051a0-535c-4058-819f-3f099e0f75ae\n", "# 4386236 - 6e7aef6e-b4e0-4515-978f-c8915b4769a5\n", "# 3236538 - 9df53d15-b499-4dca-b7f4-101d680f2fc5\n", "# 4386236 - 9f397fc0-0dfb-4a05-8091-10b01ad1d8f2\n", "# 4386236 - cb065dcc-0fbc-47ae-9d88-996aa064bbe0\n", "# 000 - f36bdfae-e4a5-4125-aa09-c39d05dc4ce2\n", "# 960677 - 365386dc-2383-46cf-9e16-e84b0b23ebe1\n", "# 126718 - 4ebd9a00-f4ad-4cb5-8d8f-7ce5cdcaab0d\n", "# 3631739 - c284b82a-3b1a-43f4-b3da-e8f1d8823a6f\n", "# 126718 - 9a2f29a2-2829-4f45-876c-97deea0b10d2" ] }, { "cell_type": "code", "execution_count": 54, "id": "abcf26fd", "metadata": {}, "outputs": [], "source": [ "shutil.rmtree(\"sample_20\", ignore_errors=True)\n", "os.makedirs(\"sample_20\", exist_ok=True)" ] }, { "cell_type": "code", "execution_count": 57, "id": "faffba25", "metadata": {}, "outputs": [], "source": [ "l = [\n", " \"6afdc41e-aed9-46a0-94af-0a1b3f41dca2\",\n", " \"bf8b4f3c-844a-46f1-bdcc-60c7fc2c4162\",\n", " \"ba1c544f-70d6-4041-aa78-014b77d7a1a8\",\n", " \"51228f13-95e4-4284-86c9-e6b41003b816\",\n", " \"f50a541c-0896-4275-9e5b-0308c737da14\",\n", " \"dc6ab15e-867f-4bda-a343-25cdf4edd88c\",\n", " \"3fa8f54c-f83f-4fa5-ba64-29403a396dd8\",\n", " \"f49e0abf-e46e-43d9-80c5-76378f50dc74\",\n", " \"a8e46d29-3ea1-4130-ba1c-e751b418f45a\",\n", " \"027b55b2-1d60-4fde-b6c9-8c975b5eb5e4\",\n", " \n", " \"3b9051a0-535c-4058-819f-3f099e0f75ae\",\n", " \"6e7aef6e-b4e0-4515-978f-c8915b4769a5\",\n", " \"9df53d15-b499-4dca-b7f4-101d680f2fc5\",\n", " \"9f397fc0-0dfb-4a05-8091-10b01ad1d8f2\",\n", " \"cb065dcc-0fbc-47ae-9d88-996aa064bbe0\",\n", " \"f36bdfae-e4a5-4125-aa09-c39d05dc4ce2\",\n", " \"365386dc-2383-46cf-9e16-e84b0b23ebe1\",\n", " \"4ebd9a00-f4ad-4cb5-8d8f-7ce5cdcaab0d\",\n", " \"c284b82a-3b1a-43f4-b3da-e8f1d8823a6f\",\n", " \"9a2f29a2-2829-4f45-876c-97deea0b10d2\",\n", "]\n", "\n", "d = \"/home/georg/notebooks/datasets/hinglish/\"\n", "for e in l:\n", " from_fp = d + \"tmp/segments/\" + e + \".mp3\"\n", " to_fp = d + \"sample_20/\" + e + \".mp3\"\n", " shutil.copy(from_fp, to_fp)" ] }, { "cell_type": "code", "execution_count": 58, "id": "b75b3958", "metadata": {}, "outputs": [], "source": [ "!tar -czf hinglish_sample_20.tar.gz sample_20" ] }, { "cell_type": "code", "execution_count": null, "id": "a353f471", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "9b937f85", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "204979d2", "metadata": {}, "source": [ "## Analyze annotations" ] }, { "cell_type": "code", "execution_count": 70, "id": "f550c17b", "metadata": {}, "outputs": [], "source": [ "annotations_dir = \"/home/georg/notebooks/datasets/hinglish/annotations/\"\n", "\n", "hinglish_uids = [\n", " 'a8e46d29-3ea1-4130-ba1c-e751b418f45a',\n", " '6e7aef6e-b4e0-4515-978f-c8915b4769a5',\n", " '9a2f29a2-2829-4f45-876c-97deea0b10d2',\n", " 'ba1c544f-70d6-4041-aa78-014b77d7a1a8',\n", " 'bf8b4f3c-844a-46f1-bdcc-60c7fc2c4162',\n", " 'c284b82a-3b1a-43f4-b3da-e8f1d8823a6f',\n", " '9df53d15-b499-4dca-b7f4-101d680f2fc5',\n", " '51228f13-95e4-4284-86c9-e6b41003b816',\n", " '4ebd9a00-f4ad-4cb5-8d8f-7ce5cdcaab0d',\n", " '9f397fc0-0dfb-4a05-8091-10b01ad1d8f2',\n", " '027b55b2-1d60-4fde-b6c9-8c975b5eb5e4',\n", " '3fa8f54c-f83f-4fa5-ba64-29403a396dd8',\n", " '3b9051a0-535c-4058-819f-3f099e0f75ae',\n", " '365386dc-2383-46cf-9e16-e84b0b23ebe1',\n", " '6afdc41e-aed9-46a0-94af-0a1b3f41dca2',\n", "]" ] }, { "cell_type": "code", "execution_count": null, "id": "d5205c1c", "metadata": {}, "outputs": [], "source": [ "# timestamps are trash, whitespace is not preserved\n", "\n", "# काफ़ी अच्छे से। Ok चलो मेरा तो बात\n", "\n", "# Speaker_0+Speaker_1:\n", "\n", "# Speaker_0 :\n", "# inaffable to the extent.\n", "\n", "# I mean ni non of them matter\n", "\n", "# :\n", "\n", "# Speaker_0 : vs Speaker_1 :" ] }, { "cell_type": "code", "execution_count": 103, "id": "08c25dfc", "metadata": { "scrolled": true }, "outputs": [], "source": [ "# from suno_utils.audio import Tokens\n", "# for uid in hinglish_uids:\n", "# try:\n", "# audio = Audio.from_file(annotations_dir + uid + \".mp3\")\n", "# audio.play()\n", "# except:\n", "# print(\"audio not found\")\n", "# print(uid)\n", "# print()\n", "# with open(annotations_dir + uid + \".json\") as f:\n", "# annotation = json.load(f)\n", "# speaker_turns = []\n", "# for e in annotation[\"monologues\"]:\n", "# text = \"\"\n", "# for ee in e[\"terms\"]:\n", "# if ee[\"type\"] == \"WORD\":\n", "# text += \" \"\n", "# text += ee[\"text\"]\n", "# speaker_turns.append({\n", "# \"speaker_id\": e[\"speaker\"][\"id\"],\n", "# \"text\": text.strip(),\n", "# })\n", "# tokens = Tokens.from_speaker_turns(speaker_turns)\n", "# for turn in tokens.speaker_turns:\n", "# print(f\"{turn['speaker_id']}:\")\n", "# print(f\"{turn['text']}\")\n", "# print()\n", "# print(\"-\"*20)" ] }, { "cell_type": "code", "execution_count": 106, "id": "6bb0cac4", "metadata": {}, "outputs": [], "source": [ "# s = \"\"\"\n", "\n", "# Speaker_0:\n", "# Yeah.\n", "\n", "# --------------------\n", "# Speaker_0:\n", "# Ask them questions of what they want. Ask them how they would like to see your future. Show them that you value your opinion. You like, you know की you, you don't have to do what your parents है। तुम्हे वो करने की जरुरत नहीं जो तुम्हारे parents करे but at least उनके opinions की value दो। वो जो कह रहे है उस बात को सुनो अच्छे से बैठ के। उनसे पूछो की आप मेरा future कैसे देखना चाहते हो और उनके opinion की value दो। ठीक है? Right?\n", "\n", "# --------------------\n", "# Speaker_0:\n", "# क्योंकि लोग मुझे पूछते हैं की you know, आज कल काफ़ी questions more often आ रहे है मुझे की, I get these questions more often की like ये दो questions आते है की एक तो हो गया की भैया यार like अः how to deal with negative people? You know जो अप जो अपने को इतना criticize करते है। ठीक है।एक एक होता है constructive criticism जो जो लोग अपने भले, अपने अच्छे के लिए कहते है। उनका intention बुरा नहीं होता है वो ठीक है।.\n", "\n", "# \"\"\"\n", "\n", "# from suno_utils.utils.text import normalize_whitespace\n", "# fixed_annotation_data = {}\n", "# for e, uid in zip(s.strip().split(\"--------------------\"), hinglish_uids):\n", "# speaker_turns = []\n", "# cur_spk = None\n", "# for ee in e.split(\"\\n\"):\n", "# if \"Speaker\" in ee:\n", "# cur_spk = int(ee[:-1].split(\"_\")[-1])\n", "# continue\n", "# ee = ee.strip()\n", "# if len(ee) == 0:\n", "# continue\n", "# speaker_turns.append({\n", "# \"speaker_id\": cur_spk,\n", "# \"text\": normalize_whitespace(ee),\n", "# })\n", "# fixed_annotation_data[uid] = speaker_turns\n", "\n", "# with open(\"hinglish_sample_20_annotations.json\", \"w\") as f:\n", "# json.dump(fixed_annotation_data, f)" ] }, { "cell_type": "code", "execution_count": 108, "id": "f6cdf74b", "metadata": {}, "outputs": [], "source": [ "with open(\"hinglish_sample_20_annotations.json\") as f:\n", " fixed_annotation_data = json.load(f)" ] }, { "cell_type": "code", "execution_count": 109, "id": "ab65312d", "metadata": { "scrolled": false }, "outputs": [], "source": [ "# from suno_utils.audio import Tokens\n", "# for uid in hinglish_uids:\n", "# audio = Audio.from_file(annotations_dir + uid + \".mp3\")\n", "# audio.play()\n", "# print(uid)\n", "# print()\n", "# speaker_turns = fixed_annotation_data[uid]\n", "# tokens = Tokens.from_speaker_turns(speaker_turns)\n", "# for turn in tokens.speaker_turns:\n", "# print(f\"{turn['speaker_id']}:\")\n", "# print(f\"{turn['text']}\")\n", "# print()\n", "# print(\"-\"*20)" ] }, { "cell_type": "code", "execution_count": null, "id": "e88b6ea6", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "737bf7f9", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "df40e5d3", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "9220be88", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "c1ba59b4", "metadata": {}, "source": [ "## Other" ] }, { "cell_type": "code", "execution_count": 21, "id": "8e56a0e2", "metadata": {}, "outputs": [], "source": [ "podcast_df = load_podcast_db(\n", " \"/mnt/data-ssd-1/data/podcasts/meta/podcastindex_feeds.db\", \n", " english_only=False, \n", " anchor_only=False,\n", ")\n", "podcast_df[\"title\"] = podcast_df[\"title\"].str.lower()" ] }, { "cell_type": "code", "execution_count": 31, "id": "9f6efe58", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
idurltitlelast_updatelinklast_http_statusdeadcontent_typeitunes_idoriginal_url...oldest_item_pubdateepisode_countpopularity_scoreprioritycreated_onupdate_frequencychashhostnewest_enclosure_urlpodcast_guid
\n", "

0 rows × 28 columns

\n", "
" ], "text/plain": [ "Empty DataFrame\n", "Columns: [id, url, title, last_update, link, last_http_status, dead, content_type, itunes_id, original_url, itunes_author, itunes_owner_name, explicit, image_url, itunes_type, generator, newest_item_pubdate, language, oldest_item_pubdate, episode_count, popularity_score, priority, created_on, update_frequency, chash, host, newest_enclosure_url, podcast_guid]\n", "Index: []\n", "\n", "[0 rows x 28 columns]" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "s = podcast_df[podcast_df[\"title\"].str.contains(\"invest regardless of your income\")]\n", "s" ] }, { "cell_type": "code", "execution_count": null, "id": "f4729cf0", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "d428c0e8", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "6cf97563", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "c89c3ff3", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "589ab5f7", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.8.10" } }, "nbformat": 4, "nbformat_minor": 5 }