{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "34a68984", "metadata": {}, "outputs": [], "source": [ "import os\n", "import json\n", "# import pandas as pd\n", "import fireducks.pandas as pd\n", "from tqdm import tqdm, trange\n", "import matplotlib.pyplot as plt\n", "\n", "IMAGEDIR = r\"/scratch/IITB/ai-at-ieor/23m1521/datasets/Vaani/Images\" \n", "DATADIR = r\"/scratch/IITB/ai-at-ieor/23m1521/datasets/Vaani/Audios/English\"\n", "AUDIO_CSV = r\"/home/IITB/ai-at-ieor/23m1521/ashish/MTP/Vaani/Vaani-Audio-Image-English.csv\"\n", "METADATA_PATH = r\"/home/IITB/ai-at-ieor/23m1521/ashish/MTP/Vaani/Vaani-Images-Audio-MetaData.parquet\"\n", "JSON_PATH = r\"/home/IITB/ai-at-ieor/23m1521/datasets/Vaani/Vaani_IIsc_Artpark_Full_Data.json\"\n", "FINAL_META = r\"/home/IITB/ai-at-ieor/23m1521/ashish/MTP/Vaani/finalMETA.parquet\"" ] }, { "cell_type": "markdown", "id": "0585e79a", "metadata": {}, "source": [ "## Sample JSON" ] }, { "cell_type": "code", "execution_count": null, "id": "67149658", "metadata": {}, "outputs": [], "source": [ "# jsondf = pd.read_json(JSON_PATH)\n", "# jsondf" ] }, { "cell_type": "code", "execution_count": 3, "id": "a41b9610", "metadata": {}, "outputs": [], "source": [ "# jsondf.sample(10000).reset_index(drop=True).to_json('sampleJSON.json')\n", "# sampleJSON.to_csv(\"sampleJSON.csv\", index=False)" ] }, { "cell_type": "code", "execution_count": 2, "id": "55f2da5c", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | id | \n", "file_name | \n", "file_url | \n", "metadata | \n", "
---|---|---|---|---|
0 | \n", "4559554 | \n", "IISc_VaaniProject_M_KA_Chamrajn_31438116_11480... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "{'assertLanguage': 'Kannada', 'audioFileName':... | \n", "
1 | \n", "397718 | \n", "IISc_VaaniProject_S_Chhattisgarh_Rajnandgaon_9... | \n", "https://vaani.iisc.ac.in/Audios/Rajnandgaon/II... | \n", "{'assertLanguage': 'Hindi', 'audioFileName': '... | \n", "
2 | \n", "3301577 | \n", "IISc_VaaniProject_M_CG_Rajnandgaon_Neha92731_0... | \n", "https://vaani.iisc.ac.in/Audios/Rajnandgaon/II... | \n", "{'assertLanguage': 'Hindi', 'audioFileName': '... | \n", "
3 | \n", "6381495 | \n", "IISc_VaaniProject_M_CG_Bastar_Rash78414_094019... | \n", "https://vaani.iisc.ac.in//Audios/Bastar/IISc_V... | \n", "{'assertLanguage': 'Hindi', 'audioFileName': '... | \n", "
4 | \n", "7207446 | \n", "IISc_VaaniProject_M_UP_Ghazipur_Pari99416_0751... | \n", "https://vaani.iisc.ac.in//Audios/Ghazipur/IISc... | \n", "{'assertLanguage': 'Bhojpuri', 'audioFileName'... | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
9995 | \n", "4872641 | \n", "IISc_VaaniProject_M_WB_Kolkata_03053692_081546... | \n", "https://vaani.iisc.ac.in/Audios/Kolkata/IISc_V... | \n", "{'assertLanguage': 'Bengali', 'audioFileName':... | \n", "
9996 | \n", "3388038 | \n", "IISc_VaaniProject_M_BR_EastChamparan_Tosi80422... | \n", "https://vaani.iisc.ac.in/Audios/EastChamparan/... | \n", "{'assertLanguage': 'Hindi', 'audioFileName': '... | \n", "
9997 | \n", "6350558 | \n", "IISc_VaaniProject_M_WB_Malda_Tist95495_0337580... | \n", "https://vaani.iisc.ac.in//Audios/Malda/IISc_Va... | \n", "{'assertLanguage': 'Bengali', 'audioFileName':... | \n", "
9998 | \n", "3409498 | \n", "IISc_VaaniProject_M_WB_DakshinD_Avij58351_1040... | \n", "https://vaani.iisc.ac.in/Audios/DakshinD/IISc_... | \n", "{'assertLanguage': 'Bengali', 'audioFileName':... | \n", "
9999 | \n", "3521388 | \n", "IISc_VaaniProject_M_KA_Mysore_06073693_1254480... | \n", "https://vaani.iisc.ac.in/Audios/Mysore/IISc_Va... | \n", "{'assertLanguage': 'Kannada', 'audioFileName':... | \n", "
10000 rows × 4 columns
\n", "\n", " | id | \n", "file_name | \n", "file_url | \n", "assertLanguage | \n", "languagesSpoken | \n", "state | \n", "district | \n", "gender | \n", "audioFileName | \n", "imageFileName | \n", "pincode | \n", "speakerImageHash | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "4559554 | \n", "IISc_VaaniProject_M_KA_Chamrajn_31438116_11480... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada] | \n", "Karnataka | \n", "Chamarajanagar | \n", "male | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "571443 | \n", "(jm~q0iivq |JPWiCL]K^CTs=G~|80@|Avq/mi | \n", "
1 | \n", "397718 | \n", "IISc_VaaniProject_S_Chhattisgarh_Rajnandgaon_9... | \n", "https://vaani.iisc.ac.in/Audios/Rajnandgaon/II... | \n", "Hindi | \n", "[Hindi] | \n", "Chhattisgarh | \n", "Rajnandgaon | \n", "female | \n", "Audios/Rajnandgaon/IISc_VaaniProject_S_Chhatti... | \n", "Images/IISc_VaaniProject_GENERIC_0620.jpg | \n", "491881 | \n", "(io(w~jr 1<0~A3:Ai|s~ | \n", "
2 | \n", "3301577 | \n", "IISc_VaaniProject_M_CG_Rajnandgaon_Neha92731_0... | \n", "https://vaani.iisc.ac.in/Audios/Rajnandgaon/II... | \n", "Hindi | \n", "[Hindi] | \n", "Chhattisgarh | \n", "Rajnandgaon | \n", "female | \n", "Audios/Rajnandgaon/IISc_VaaniProject_M_CG_Rajn... | \n", "Images/IISc_VaaniProject_GENERIC_0812.jpg | \n", "491229 | \n", "~rm}s-iivq )~=/I+|Nq/jk | \n", "
3 | \n", "6381495 | \n", "IISc_VaaniProject_M_CG_Bastar_Rash78414_094019... | \n", "https://vaani.iisc.ac.in//Audios/Bastar/IISc_V... | \n", "Hindi | \n", "[Hindi] | \n", "Chhattisgarh | \n", "Bastar | \n", "female | \n", "/Audios/Bastar/IISc_VaaniProject_M_CG_Bastar_R... | \n", "Images/IISc_VaaniProject_GENERIC_0273.jpg | \n", "494115 | \n", "~rmvr0iivq )~=/I+|Nq)pl | \n", "
4 | \n", "7207446 | \n", "IISc_VaaniProject_M_UP_Ghazipur_Pari99416_0751... | \n", "https://vaani.iisc.ac.in//Audios/Ghazipur/IISc... | \n", "Bhojpuri | \n", "[Bhojpuri] | \n", "UttarPradesh | \n", "Ghazipur | \n", "female | \n", "/Audios/Ghazipur/IISc_VaaniProject_M_UP_Ghazip... | \n", "Images/IISc_VaaniProject_GENERIC_0531.jpg | \n", "232341 | \n", "~pnwv-iivq )~=/I+|Nq,lj | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
9995 | \n", "4872641 | \n", "IISc_VaaniProject_M_WB_Kolkata_03053692_081546... | \n", "https://vaani.iisc.ac.in/Audios/Kolkata/IISc_V... | \n", "Bengali | \n", "[Bengali] | \n", "WestBengal | \n", "Kolkata | \n", "male | \n", "Audios/Kolkata/IISc_VaaniProject_M_WB_Kolkata_... | \n", "Images/IISc_VaaniProject_Kolkata-SPECIFIC_0056... | \n", "700014 | \n", "~qj{u-iivq -Q[UXVCs=G~|80@|Avq,op | \n", "
9996 | \n", "3388038 | \n", "IISc_VaaniProject_M_BR_EastChamparan_Tosi80422... | \n", "https://vaani.iisc.ac.in/Audios/EastChamparan/... | \n", "Hindi | \n", "[Hindi] | \n", "Bihar | \n", "EastChamparan | \n", "male | \n", "Audios/EastChamparan/IISc_VaaniProject_M_BR_Ea... | \n", "Images/IISc_VaaniProject_EastChamparan-SPECIFI... | \n", "845401 | \n", "~qmws0iivq ~Cb^:JC\\ZXTC]nJ2~23=+|Nq~on} | \n", "
9997 | \n", "6350558 | \n", "IISc_VaaniProject_M_WB_Malda_Tist95495_0337580... | \n", "https://vaani.iisc.ac.in//Audios/Malda/IISc_Va... | \n", "Bengali | \n", "[Bengali] | \n", "WestBengal | \n", "Malda | \n", "female | \n", "/Audios/Malda/IISc_VaaniProject_M_WB_Malda_Tis... | \n", "Images/IISc_VaaniProject_Malda-SPECIFIC_01052.jpg | \n", "732140 | \n", "~ll}v/iivq /C[NXf5?/:+(8-Vijvv) | \n", "
9998 | \n", "3409498 | \n", "IISc_VaaniProject_M_WB_DakshinD_Avij58351_1040... | \n", "https://vaani.iisc.ac.in/Audios/DakshinD/IISc_... | \n", "Bengali | \n", "[Bengali] | \n", "WestBengal | \n", "DakshinDinajpur | \n", "male | \n", "Audios/DakshinD/IISc_VaaniProject_M_WB_Dakshin... | \n", "Images/IISc_VaaniProject_GENERIC_1078.jpg | \n", "733126 | \n", "(imvs+iivq )~=/I+|Nr~pq | \n", "
9999 | \n", "3521388 | \n", "IISc_VaaniProject_M_KA_Mysore_06073693_1254480... | \n", "https://vaani.iisc.ac.in/Audios/Mysore/IISc_Va... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Mysore | \n", "female | \n", "Audios/Mysore/IISc_VaaniProject_M_KA_Mysore_06... | \n", "Images/IISc_VaaniProject_Mysore-SPECIFIC_01800... | \n", "571311 | \n", "(knzu/iivq /[bYiGfB:<|+53:Aiwy~i | \n", "
10000 rows × 12 columns
\n", "\n", " | id | \n", "file_name | \n", "file_url | \n", "assertLanguage | \n", "languagesSpoken | \n", "state | \n", "district | \n", "gender | \n", "audioFileName | \n", "imageFileName | \n", "pincode | \n", "speakerImageHash | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "2 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "431105 | \n", "(iq~v-nq +lTC]QXDCSnJ2~23=+|Nq~nn( | \n", "
1 | \n", "3 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "431105 | \n", "(iq~v-qq +lTC]QXDCSnJ2~23=+|Nq~miz | \n", "
2 | \n", "4 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "431105 | \n", "(iq~v.pl +lTC]QXDCSnJ2~23=+|Nq~lo{ | \n", "
3 | \n", "5 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_GENERIC_0073.jpg | \n", "431105 | \n", "(iq~v+kl 1<0~A3:Aivx* | \n", "
4 | \n", "6 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "431105 | \n", "(iq~w+rk +lTC]QXDCSnJ2~23=+|Nq(knx | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
9584927 | \n", "9696433 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_16081... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_GENERIC_0554.jpg | \n", "571440 | \n", "(oi~r)iivq )~=/I+|Nq,nm | \n", "
9584928 | \n", "9696434 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_16053... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "571440 | \n", "(oi{t(iivq |JPWiCL]K^CTs=G~|80@|Avq)mp | \n", "
9584929 | \n", "9696435 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_12370... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "571440 | \n", "(kl}q-iivq |JPWiCL]K^CTs=G~|80@|Avr(kr | \n", "
9584930 | \n", "9696436 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_09272... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "571440 | \n", "~rk}s+iivq |JPWiCL]K^CTs=G~|80@|Avq*km | \n", "
9584931 | \n", "9696437 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_15323... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "571440 | \n", "(nlxt+iivq |JPWiCL]K^CTs=G~|80@|Avr,lq | \n", "
9584932 rows × 12 columns
\n", "\n", " | id | \n", "file_name | \n", "file_url | \n", "assertLanguage | \n", "languagesSpoken | \n", "state | \n", "district | \n", "gender | \n", "audioFileName | \n", "imageFileName | \n", "pincode | \n", "speakerImageHash | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "2 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "431105 | \n", "(iq~v-nq +lTC]QXDCSnJ2~23=+|Nq~nn( | \n", "
1 | \n", "3 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "431105 | \n", "(iq~v-qq +lTC]QXDCSnJ2~23=+|Nq~miz | \n", "
2 | \n", "4 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "431105 | \n", "(iq~v.pl +lTC]QXDCSnJ2~23=+|Nq~lo{ | \n", "
3 | \n", "5 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_GENERIC_0073.jpg | \n", "431105 | \n", "(iq~v+kl 1<0~A3:Aivx* | \n", "
4 | \n", "6 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "431105 | \n", "(iq~w+rk +lTC]QXDCSnJ2~23=+|Nq(knx | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
9584927 | \n", "9696433 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_16081... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_GENERIC_0554.jpg | \n", "571440 | \n", "(oi~r)iivq )~=/I+|Nq,nm | \n", "
9584928 | \n", "9696434 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_16053... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "571440 | \n", "(oi{t(iivq |JPWiCL]K^CTs=G~|80@|Avq)mp | \n", "
9584929 | \n", "9696435 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_12370... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "571440 | \n", "(kl}q-iivq |JPWiCL]K^CTs=G~|80@|Avr(kr | \n", "
9584930 | \n", "9696436 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_09272... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "571440 | \n", "~rk}s+iivq |JPWiCL]K^CTs=G~|80@|Avq*km | \n", "
9584931 | \n", "9696437 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_15323... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "571440 | \n", "(nlxt+iivq |JPWiCL]K^CTs=G~|80@|Avr,lq | \n", "
9584932 rows x 12 columns
\n", "\n", " | id | \n", "file_name | \n", "file_url | \n", "assertLanguage | \n", "languagesSpoken | \n", "state | \n", "district | \n", "gender | \n", "audioFileName | \n", "imageFileName | \n", "pincode | \n", "speakerImageHash | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "2 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "431105 | \n", "(iq~v-nq +lTC]QXDCSnJ2~23=+|Nq~nn( | \n", "
1 | \n", "3 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "431105 | \n", "(iq~v-qq +lTC]QXDCSnJ2~23=+|Nq~miz | \n", "
2 | \n", "4 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "431105 | \n", "(iq~v.pl +lTC]QXDCSnJ2~23=+|Nq~lo{ | \n", "
3 | \n", "5 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_GENERIC_0073.jpg | \n", "431105 | \n", "(iq~v+kl 1<0~A3:Aivx* | \n", "
4 | \n", "6 | \n", "IISc_VaaniProject_S_Maharashtra_Aurangabad_952... | \n", "https://vaani.iisc.ac.in/Audios/Aurangabad/IIS... | \n", "Marathi | \n", "[Marathi] | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "431105 | \n", "(iq~w+rk +lTC]QXDCSnJ2~23=+|Nq(knx | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
9584927 | \n", "9696433 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_16081... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_GENERIC_0554.jpg | \n", "571440 | \n", "(oi~r)iivq )~=/I+|Nq,nm | \n", "
9584928 | \n", "9696434 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_16053... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "571440 | \n", "(oi{t(iivq |JPWiCL]K^CTs=G~|80@|Avq)mp | \n", "
9584929 | \n", "9696435 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_12370... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "571440 | \n", "(kl}q-iivq |JPWiCL]K^CTs=G~|80@|Avr(kr | \n", "
9584930 | \n", "9696436 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_09272... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "571440 | \n", "~rk}s+iivq |JPWiCL]K^CTs=G~|80@|Avq*km | \n", "
9584931 | \n", "9696437 | \n", "IISc_VaaniProject_M_KA_Chamrajn_42017276_15323... | \n", "https://vaani.iisc.ac.in/Audios/Chamrajn/IISc_... | \n", "Kannada | \n", "[Kannada, English] | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "571440 | \n", "(nlxt+iivq |JPWiCL]K^CTs=G~|80@|Avr,lq | \n", "
9584932 rows x 12 columns
\n", "\n", " | id | \n", "file_name | \n", "file_url | \n", "assertLanguage | \n", "languagesSpoken | \n", "state | \n", "district | \n", "gender | \n", "audioFileName | \n", "imageFileName | \n", "pincode | \n", "speakerImageHash | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|
58211 | \n", "58213 | \n", "IISc_VaaniProject_S_Chhattisgarh_Rajnandgaon_1... | \n", "https://vaani.iisc.ac.in/Audios/Rajnandgaon/II... | \n", "English | \n", "[Hindi, English] | \n", "Chhattisgarh | \n", "Rajnandgaon | \n", "female | \n", "Audios/Rajnandgaon/IISc_VaaniProject_S_Chhatti... | \n", "Images/IISc_VaaniProject_GENERIC_0602.jpg | \n", "491441 | \n", "(krxx+nk 1<0~A3:Ai|q) | \n", "
58212 | \n", "58214 | \n", "IISc_VaaniProject_S_Chhattisgarh_Rajnandgaon_1... | \n", "https://vaani.iisc.ac.in/Audios/Rajnandgaon/II... | \n", "English | \n", "[Hindi, English] | \n", "Chhattisgarh | \n", "Rajnandgaon | \n", "female | \n", "Audios/Rajnandgaon/IISc_VaaniProject_S_Chhatti... | \n", "Images/IISc_VaaniProject_GENERIC_0717.jpg | \n", "491441 | \n", "(krxx0kr 1<0~A3:Ai}r. | \n", "
58213 | \n", "58215 | \n", "IISc_VaaniProject_S_Chhattisgarh_Rajnandgaon_1... | \n", "https://vaani.iisc.ac.in/Audios/Rajnandgaon/II... | \n", "English | \n", "[Hindi, English] | \n", "Chhattisgarh | \n", "Rajnandgaon | \n", "female | \n", "Audios/Rajnandgaon/IISc_VaaniProject_S_Chhatti... | \n", "Images/IISc_VaaniProject_GENERIC_0635.jpg | \n", "491441 | \n", "(kryq/io 1<0~A3:Ai|t, | \n", "
58214 | \n", "58216 | \n", "IISc_VaaniProject_S_Chhattisgarh_Rajnandgaon_1... | \n", "https://vaani.iisc.ac.in/Audios/Rajnandgaon/II... | \n", "English | \n", "[Hindi, English] | \n", "Chhattisgarh | \n", "Rajnandgaon | \n", "female | \n", "Audios/Rajnandgaon/IISc_VaaniProject_S_Chhatti... | \n", "Images/IISc_VaaniProject_GENERIC_1036.jpg | \n", "491441 | \n", "(krxv(pi 1<0~A3:Ajvt- | \n", "
58215 | \n", "58217 | \n", "IISc_VaaniProject_S_Chhattisgarh_Rajnandgaon_1... | \n", "https://vaani.iisc.ac.in/Audios/Rajnandgaon/II... | \n", "English | \n", "[Hindi, English] | \n", "Chhattisgarh | \n", "Rajnandgaon | \n", "female | \n", "Audios/Rajnandgaon/IISc_VaaniProject_S_Chhatti... | \n", "Images/IISc_VaaniProject_GENERIC_0623.jpg | \n", "491441 | \n", "(krys.rp 1<0~A3:Ai|s* | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
9501845 | \n", "9613351 | \n", "IISc_VaaniProject_S_Telengana_Karimnagar_10592... | \n", "https://vaani.iisc.ac.in//Audios/Karimnagar/II... | \n", "English | \n", "[Telugu, English] | \n", "Telangana | \n", "Karimnagar | \n", "female | \n", "/Audios/Karimnagar/IISc_VaaniProject_S_Telenga... | \n", "Images/IISc_VaaniProject_GENERIC_0317.jpg | \n", "505467 | \n", "(jlwq.nn 1<0~A3:Aiyr. | \n", "
9501846 | \n", "9613352 | \n", "IISc_VaaniProject_S_Telengana_Karimnagar_10592... | \n", "https://vaani.iisc.ac.in//Audios/Karimnagar/II... | \n", "English | \n", "[Telugu, English] | \n", "Telangana | \n", "Karimnagar | \n", "female | \n", "/Audios/Karimnagar/IISc_VaaniProject_S_Telenga... | \n", "Images/IISc_VaaniProject_GENERIC_0042.jpg | \n", "505467 | \n", "(jlwz(qo 1<0~A3:Aivu) | \n", "
9501847 | \n", "9613353 | \n", "IISc_VaaniProject_S_Telengana_Karimnagar_10592... | \n", "https://vaani.iisc.ac.in//Audios/Karimnagar/II... | \n", "English | \n", "[Telugu, English] | \n", "Telangana | \n", "Karimnagar | \n", "female | \n", "/Audios/Karimnagar/IISc_VaaniProject_S_Telenga... | \n", "Images/IISc_VaaniProject_GENERIC_0220.jpg | \n", "505467 | \n", "(jlwv~qo 1<0~A3:Aixs~ | \n", "
9501848 | \n", "9613354 | \n", "IISc_VaaniProject_S_Telengana_Karimnagar_10592... | \n", "https://vaani.iisc.ac.in//Audios/Karimnagar/II... | \n", "English | \n", "[Telugu, English] | \n", "Telangana | \n", "Karimnagar | \n", "female | \n", "/Audios/Karimnagar/IISc_VaaniProject_S_Telenga... | \n", "Images/IISc_VaaniProject_GENERIC_0309.jpg | \n", "505467 | \n", "(jlwx.im 1<0~A3:Aiyq0 | \n", "
9501849 | \n", "9613355 | \n", "IISc_VaaniProject_S_Telengana_Karimnagar_10592... | \n", "https://vaani.iisc.ac.in//Audios/Karimnagar/II... | \n", "English | \n", "[Telugu, English] | \n", "Telangana | \n", "Karimnagar | \n", "female | \n", "/Audios/Karimnagar/IISc_VaaniProject_S_Telenga... | \n", "Images/IISc_VaaniProject_GENERIC_0052.jpg | \n", "505467 | \n", "(jlwt*pm 1<0~A3:Aivv) | \n", "
925 rows x 12 columns
\n", "\n", " | image_name | \n", "state | \n", "district | \n", "gender | \n", "audio_language | \n", "audio_name | \n", "
---|---|---|---|---|---|---|
0 | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Marathi | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "
1 | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Marathi | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "
2 | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Marathi | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "
3 | \n", "Images/IISc_VaaniProject_GENERIC_0073.jpg | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Marathi | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "
4 | \n", "Images/IISc_VaaniProject_Aurangabad-SPECIFIC_0... | \n", "Maharashtra | \n", "Aurangabad | \n", "female | \n", "Marathi | \n", "Audios/Aurangabad/IISc_VaaniProject_S_Maharash... | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
9584927 | \n", "Images/IISc_VaaniProject_GENERIC_0554.jpg | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Kannada | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "
9584928 | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Kannada | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "
9584929 | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Kannada | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "
9584930 | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Kannada | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "
9584931 | \n", "Images/IISc_VaaniProject_Chamrajnagar-SPECIFIC... | \n", "Karnataka | \n", "Chamarajanagar | \n", "female | \n", "Kannada | \n", "Audios/Chamrajn/IISc_VaaniProject_M_KA_Chamraj... | \n", "
9584932 rows x 6 columns
\n", "\n", " | image_name | \n", "state | \n", "district | \n", "gender | \n", "audio_language | \n", "audio_name | \n", "
---|---|---|---|---|---|---|
0 | \n", "Images/IISc_VaaniProject_Gopalganj-SPECIFIC_00... | \n", "Bihar | \n", "Gopalganj | \n", "female | \n", "English | \n", "Audios/Gopalganj/IISc_VaaniProject_S_Bihar_Gop... | \n", "
1 | \n", "Images/IISc_VaaniProject_Gopalganj-SPECIFIC_00... | \n", "Bihar | \n", "Gopalganj | \n", "female | \n", "English | \n", "Audios/Gopalganj/IISc_VaaniProject_S_Bihar_Gop... | \n", "
2 | \n", "Images/IISc_VaaniProject_Gopalganj-SPECIFIC_00... | \n", "Bihar | \n", "Gopalganj | \n", "female | \n", "English | \n", "Audios/Gopalganj/IISc_VaaniProject_S_Bihar_Gop... | \n", "
3 | \n", "Images/IISc_VaaniProject_Gopalganj-SPECIFIC_00... | \n", "Bihar | \n", "Gopalganj | \n", "female | \n", "English | \n", "Audios/Gopalganj/IISc_VaaniProject_S_Bihar_Gop... | \n", "
4 | \n", "Images/IISc_VaaniProject_Gopalganj-SPECIFIC_00... | \n", "Bihar | \n", "Gopalganj | \n", "female | \n", "English | \n", "Audios/Gopalganj/IISc_VaaniProject_S_Bihar_Gop... | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
380938 | \n", "Images/IISc_VaaniProject_GENERIC_0746.jpg | \n", "AndhraPradesh | \n", "Vishakapattanam | \n", "male | \n", "English | \n", "/Audios/Vishakapattanam/IISc_VaaniProject_S_AP... | \n", "
380939 | \n", "Images/IISc_VaaniProject_GENERIC_0793.jpg | \n", "AndhraPradesh | \n", "Vishakapattanam | \n", "male | \n", "English | \n", "/Audios/Vishakapattanam/IISc_VaaniProject_S_AP... | \n", "
380940 | \n", "Images/IISc_VaaniProject_GENERIC_0793.jpg | \n", "AndhraPradesh | \n", "Vishakapattanam | \n", "male | \n", "English | \n", "/Audios/Vishakapattanam/IISc_VaaniProject_S_AP... | \n", "
380941 | \n", "Images/IISc_VaaniProject_GENERIC_0008.jpg | \n", "AndhraPradesh | \n", "Vishakapattanam | \n", "female | \n", "English | \n", "/Audios/Vishakapattanam/IISc_VaaniProject_S_AP... | \n", "
380942 | \n", "Images/IISc_VaaniProject_GENERIC_0008.jpg | \n", "AndhraPradesh | \n", "Vishakapattanam | \n", "female | \n", "English | \n", "/Audios/Vishakapattanam/IISc_VaaniProject_S_AP... | \n", "
380943 rows x 6 columns
\n", "\n", " | audio_path | \n", "referenceImage | \n", "gender | \n", "state | \n", "district | \n", "
---|---|---|---|---|---|
0 | \n", "IISc_VaaniProject_S_AP_Guntur_66656_9672685_BH... | \n", "Images/IISc_VaaniProject_GENERIC_0746.jpg | \n", "Male | \n", "AndhraPradesh | \n", "Guntur | \n", "
1 | \n", "IISc_VaaniProject_S_AP_Guntur_66656_9672685_BH... | \n", "Images/IISc_VaaniProject_GENERIC_0746.jpg | \n", "Male | \n", "AndhraPradesh | \n", "Guntur | \n", "
2 | \n", "IISc_VaaniProject_S_AP_Guntur_66656_9672947_BH... | \n", "Images/IISc_VaaniProject_GENERIC_0905.jpg | \n", "Male | \n", "AndhraPradesh | \n", "Guntur | \n", "
3 | \n", "IISc_VaaniProject_S_AP_Guntur_66656_9672947_BH... | \n", "Images/IISc_VaaniProject_GENERIC_0905.jpg | \n", "Male | \n", "AndhraPradesh | \n", "Guntur | \n", "
4 | \n", "IISc_VaaniProject_S_AP_Guntur_66656_9672947_BH... | \n", "Images/IISc_VaaniProject_GENERIC_0905.jpg | \n", "Male | \n", "AndhraPradesh | \n", "Guntur | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
920 | \n", "IISc_VaaniProject_S_Uttarpradesh_JyotibaPhuleN... | \n", "Images/IISc_VaaniProject_GENERIC_0761.jpg | \n", "Female | \n", "UttarPradesh | \n", "JyotibaPhuleNagar | \n", "
921 | \n", "IISc_VaaniProject_S_Uttarpradesh_JyotibaPhuleN... | \n", "Images/IISc_VaaniProject_JyotibaPhuleNagar-SPE... | \n", "Female | \n", "UttarPradesh | \n", "JyotibaPhuleNagar | \n", "
922 | \n", "IISc_VaaniProject_S_Uttarpradesh_JyotibaPhuleN... | \n", "Images/IISc_VaaniProject_JyotibaPhuleNagar-SPE... | \n", "Female | \n", "UttarPradesh | \n", "JyotibaPhuleNagar | \n", "
923 | \n", "IISc_VaaniProject_S_Uttarpradesh_JyotibaPhuleN... | \n", "Images/IISc_VaaniProject_JyotibaPhuleNagar-SPE... | \n", "Female | \n", "UttarPradesh | \n", "JyotibaPhuleNagar | \n", "
924 | \n", "IISc_VaaniProject_S_Uttarpradesh_JyotibaPhuleN... | \n", "Images/IISc_VaaniProject_JyotibaPhuleNagar-SPE... | \n", "Female | \n", "UttarPradesh | \n", "JyotibaPhuleNagar | \n", "
925 rows x 5 columns
\n", "