ArcheWriting¶
Documentation process for the project started at the New Material Imaginaries class.
Load data from Pandemic Archive of Voices¶
In [80]:
import requests
import json
r = requests.get('https://pandemic-archive-of-voices.herokuapp.com/api/data')
db_data = json.loads(r.text)
audios = db_data['audios']
print(db_data)
{'db': 'The Pandemic Archive of Voices', 'extracted_on': '2021-01-2319:21:50', 'audios_length': 183, 'speakers_length': 24, 'total_duration_seconds': 314, 'audios': [{'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_1@15-12-2020_14-57-52.wav', 'id': 13, 'text': 'Números', 'from_id': 5631317686, 'duration_seconds': 3, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'nilya musaeva*️⃣', 'file': 'db/audios/4472772915/audio_2@15-12-2020_14-58-37.wav', 'id': 15, 'text': 'еда', 'from_id': 4472772915, 'duration_seconds': 1, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'S. C.', 'file': 'db/audios/4408865338/audio_3@15-12-2020_16-21-06.wav', 'id': 22, 'text': '', 'from_id': 4408865338, 'duration_seconds': 3, 'lang': {'name': 'mandarin chinese', 'code': 'cmn', 'standard': 'ISO 639-3'}}, {'from': 'ruoxi', 'file': 'db/audios/5631317686/audio_4@15-12-2020_16-31-05.wav', 'id': 27, 'text': '怪迷日眼', 'from_id': 5136095171, 'duration_seconds': 1, 'lang': {'name': 'chongqing dialect', 'code': 'chen1267', 'standard': 'glottolog'}}, {'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_5@15-12-2020_17-10-04.wav', 'id': 30, 'text': 'Ensimesmado', 'from_id': 5631317686, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'ruoxi', 'file': 'db/audios/5136095171/audio_6@15-12-2020_17-11-15.wav', 'id': 32, 'text': '造孽巴撒', 'from_id': 5136095171, 'duration_seconds': 1, 'lang': {'name': 'chongqing dialect', 'code': 'chen1267', 'standard': 'glottolog'}}, {'from': 'ruoxi', 'file': 'db/audios/5136095171/audio_7@15-12-2020_17-20-54.wav', 'id': 34, 'text': '遇球得到', 'from_id': 5136095171, 'duration_seconds': 1, 'lang': {'name': 'chongqing dialect', 'code': 'chen1267', 'standard': 'glottolog'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_8@15-12-2020_17-36-43.wav', 'id': 36, 'text': 'ロックダウン', 'from_id': 5314577364, 'duration_seconds': 2, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_9@15-12-2020_17-37-06.wav', 'id': 39, 'text': '非常事態宣言', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_10@15-12-2020_17-37-48.wav', 'id': 41, 'text': '20秒間', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_11@15-12-2020_17-38-22.wav', 'id': 43, 'text': '三密', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_12@15-12-2020_17-41-09.wav', 'id': 45, 'text': 'Zoom会議', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_13@15-12-2020_17-41-53.wav', 'id': 47, 'text': 'コロナに効く！', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_14@15-12-2020_17-42-02.wav', 'id': 49, 'text': 'コロナに負けない', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_15@15-12-2020_17-42-35.wav', 'id': 51, 'text': 'コロナ下', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_16@15-12-2020_17-43-50.wav', 'id': 56, 'text': '閉店しました', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_17@15-12-2020_17-44-55.wav', 'id': 58, 'text': 'こんなご時世ですが', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_18@15-12-2020_17-45-04.wav', 'id': 60, 'text': 'また会う日まで', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Hem Poudyal', 'file': 'db/audios/5411097981/audio_19@15-12-2020_17-55-57.wav', 'id': 67, 'text': 'कोरोनाको समय, एक्लोपन अनि असहजता', 'from_id': 5411097981, 'duration_seconds': 6, 'lang': {'name': 'nepali', 'code': 'ne', 'standard': 'ISO 639-1'}}, {'from': 'Hem Poudyal', 'file': 'db/audios/5411097981/audio_23@15-12-2020_18-08-21.wav', 'id': 76, 'text': 'संवेदनशील मानव जीवन', 'from_id': 5411097981, 'duration_seconds': 4, 'lang': {'name': 'nepali', 'code': 'ne', 'standard': 'ISO 639-1'}}, {'from': 'Hem Poudyal', 'file': 'db/audios/5411097981/audio_24@15-12-2020_18-10-32.wav', 'id': 78, 'text': 'बाध्यता', 'from_id': 5411097981, 'duration_seconds': 2, 'lang': {'name': 'nepali', 'code': 'ne', 'standard': 'ISO 639-1'}}, {'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_25@15-12-2020_18-12-33.wav', 'id': 80, 'text': 'Sirenes', 'from_id': 5631317686, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_26@15-12-2020_18-13-47.wav', 'id': 82, 'text': 'Respiradores', 'from_id': 5631317686, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_27@15-12-2020_18-19-53.wav', 'id': 84, 'text': 'Esperança', 'from_id': 5631317686, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Antônio Hof', 'file': 'db/audios/5629926613/audio_28@15-12-2020_20-16-18.wav', 'id': 87, 'text': 'Alemão', 'from_id': 5629926613, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'nilya musaeva*️⃣', 'file': 'db/audios/4472772915/audio_29@15-12-2020_20-16-35.wav', 'id': 89, 'text': 'система цифровых пропусков', 'from_id': 4472772915, 'duration_seconds': 2, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'S. C.', 'file': 'db/audios/4408865338/audio_30@16-12-2020_13-17-48.wav', 'id': 91, 'text': '宅', 'from_id': 4408865338, 'duration_seconds': 1, 'lang': {'name': 'mandarin chinese', 'code': 'cmn', 'standard': 'ISO 639-3'}}, {'from': 'S. C.', 'file': 'db/audios/4408865338/audio_31@16-12-2020_13-20-38.wav', 'id': 93, 'text': '健康码', 'from_id': 4408865338, 'duration_seconds': 2, 'lang': {'name': 'mandarin chinese', 'code': 'cmn', 'standard': 'ISO 639-3'}}, {'from': 'Chi Him Chik', 'file': 'db/audios/5576183485/audio_32@16-12-2020_14-13-07.wav', 'id': 98, 'text': '第一波', 'from_id': 5576183485, 'duration_seconds': 1, 'lang': {'name': 'cantonese', 'code': 'yue', 'standard': 'ISO 639-3'}}, {'from': 'Chi Him Chik', 'file': 'db/audios/5576183485/audio_33@16-12-2020_14-13-19.wav', 'id': 100, 'text': '第二波', 'from_id': 5576183485, 'duration_seconds': 1, 'lang': {'name': 'cantonese', 'code': 'yue', 'standard': 'ISO 639-3'}}, {'from': 'Chi Him Chik', 'file': 'db/audios/5576183485/audio_34@16-12-2020_14-13-27.wav', 'id': 102, 'text': '第三波', 'from_id': 5576183485, 'duration_seconds': 1, 'lang': {'name': 'cantonese', 'code': 'yue', 'standard': 'ISO 639-3'}}, {'from': 'Chi Him Chik', 'file': 'db/audios/5576183485/audio_35@16-12-2020_14-13-36.wav', 'id': 104, 'text': '第四波', 'from_id': 5576183485, 'duration_seconds': 2, 'lang': {'name': 'cantonese', 'code': 'yue', 'standard': 'ISO 639-3'}}, {'from': 'Sangbong Lee', 'file': 'db/audios/5524258652/audio_36@16-12-2020_14-15-39.wav', 'id': 106, 'text': '코로나 감염병 확산', 'from_id': 5524258652, 'duration_seconds': 3, 'lang': {'name': 'korean', 'code': 'ko', 'standard': 'ISO 639-1'}}, {'from': 'Sangbong Lee', 'file': 'db/audios/5524258652/audio_37@16-12-2020_14-15-51.wav', 'id': 108, 'text': '확진자', 'from_id': 5524258652, 'duration_seconds': 2, 'lang': {'name': 'korean', 'code': 'ko', 'standard': 'ISO 639-1'}}, {'from': 'Sangbong Lee', 'file': 'db/audios/5524258652/audio_38@16-12-2020_14-16-06.wav', 'id': 110, 'text': '가짜뉴스와 음모론', 'from_id': 5524258652, 'duration_seconds': 2, 'lang': {'name': 'korean', 'code': 'ko', 'standard': 'ISO 639-1'}}, {'from': 'Sangbong Lee', 'file': 'db/audios/5524258652/audio_39@16-12-2020_14-16-16.wav', 'id': 112, 'text': '격리시설', 'from_id': 5524258652, 'duration_seconds': 2, 'lang': {'name': 'korean', 'code': 'ko', 'standard': 'ISO 639-1'}}, {'from': 'Sangbong Lee', 'file': 'db/audios/5524258652/audio_40@16-12-2020_14-49-03.wav', 'id': 114, 'text': '가짜뉴스와 음모론', 'from_id': 5524258652, 'duration_seconds': 3, 'lang': {'name': 'korean', 'code': 'ko', 'standard': 'ISO 639-1'}}, {'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_41@16-12-2020_15-16-56.wav', 'id': 116, 'text': 'Protocolos de distanciamento social', 'from_id': 5631317686, 'duration_seconds': 3, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_42@16-12-2020_15-19-02.wav', 'id': 118, 'text': 'Incertezas', 'from_id': 5631317686, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_43@16-12-2020_15-23-28.wav', 'id': 120, 'text': 'Minutos de silêncio', 'from_id': 5631317686, 'duration_seconds': 3, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Josh', 'file': 'db/audios/4953417715/audio_44@16-12-2020_18-02-27.wav', 'id': 124, 'text': "dog's dinner", 'from_id': 4953417715, 'duration_seconds': 2, 'lang': {'name': 'british english', 'code': 'en-GB', 'standard': 'IETF'}}, {'from': 'Josh', 'file': 'db/audios/4953417715/audio_45@16-12-2020_18-03-10.wav', 'id': 126, 'text': 'extended support bubble', 'from_id': 4953417715, 'duration_seconds': 2, 'lang': {'name': 'british english', 'code': 'en-GB', 'standard': 'IETF'}}, {'from': 'Antônio Hof', 'file': 'db/audios/5629926613/audio_46@16-12-2020_19-05-24.wav', 'id': 131, 'text': 'Máscara', 'from_id': 5629926613, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Antônio Hof', 'file': 'db/audios/5629926613/audio_47@16-12-2020_19-07-09.wav', 'id': 133, 'text': 'zigue-zague', 'from_id': 5629926613, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'nilya musaeva*️⃣', 'file': 'db/audios/4472772915/audio_48@16-12-2020_19-08-12.wav', 'id': 135, 'text': 'надоело', 'from_id': 4472772915, 'duration_seconds': 1, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'Bojana', 'file': 'db/audios/4612847105/audio_49@16-12-2020_19-10-14.wav', 'id': 137, 'text': 'nedostajanje', 'from_id': 4612847105, 'duration_seconds': 1, 'lang': {'name': 'serbian', 'code': 'srp', 'standard': 'ISO 639-3'}}, {'from': 'Bojana', 'file': 'db/audios/4612847105/audio_50@16-12-2020_19-10-23.wav', 'id': 139, 'text': 'vreme', 'from_id': 4612847105, 'duration_seconds': 1, 'lang': {'name': 'serbian', 'code': 'srp', 'standard': 'ISO 639-3'}}, {'from': 'Bojana', 'file': 'db/audios/4612847105/audio_51@16-12-2020_19-10-59.wav', 'id': 141, 'text': 'bliskost', 'from_id': 4612847105, 'duration_seconds': 1, 'lang': {'name': 'serbian', 'code': 'srp', 'standard': 'ISO 639-3'}}, {'from': 'Bojana', 'file': 'db/audios/4612847105/audio_52@16-12-2020_19-11-42.wav', 'id': 143, 'text': 'daljina', 'from_id': 4612847105, 'duration_seconds': 1, 'lang': {'name': 'serbian', 'code': 'srp', 'standard': 'ISO 639-3'}}, {'from': 'Bojana', 'file': 'db/audios/4612847105/audio_53@16-12-2020_19-22-23.wav', 'id': 145, 'text': 'ograničenost', 'from_id': 4612847105, 'duration_seconds': 1, 'lang': {'name': 'serbian', 'code': 'srp', 'standard': 'ISO 639-3'}}, {'from': 'Soumya Hfk', 'file': 'db/audios/5572716069/audio_54@16-12-2020_21-41-43.wav', 'id': 148, 'text': 'সবাই ভালো থেকো', 'from_id': 5572716069, 'duration_seconds': 2, 'lang': {'name': 'bengali', 'code': 'bn', 'standard': 'ISO 639-1'}}, {'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_55@17-12-2020_10-32-05.wav', 'id': 153, 'text': 'Luto', 'from_id': 5631317686, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Victor Artiga', 'file': 'db/audios/4963464597/audio_56@17-12-2020_11-50-21.wav', 'id': 156, 'text': 'Distancia', 'from_id': 4963464597, 'duration_seconds': 1, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Victor Artiga', 'file': 'db/audios/4963464597/audio_57@17-12-2020_11-50-29.wav', 'id': 158, 'text': 'Introspección', 'from_id': 4963464597, 'duration_seconds': 1, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Victor Artiga', 'file': 'db/audios/4963464597/audio_58@17-12-2020_11-50-39.wav', 'id': 160, 'text': 'Amistades', 'from_id': 4963464597, 'duration_seconds': 2, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Victor Artiga', 'file': 'db/audios/4963464597/audio_59@17-12-2020_11-50-48.wav', 'id': 162, 'text': 'Cercania', 'from_id': 4963464597, 'duration_seconds': 2, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Victor Artiga', 'file': 'db/audios/4963464597/audio_60@17-12-2020_11-50-57.wav', 'id': 164, 'text': 'Nostalgia', 'from_id': 4963464597, 'duration_seconds': 2, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Josh', 'file': 'db/audios/4953417715/audio_61@17-12-2020_12-06-09.wav', 'id': 166, 'text': 'church bells and sirens', 'from_id': 4953417715, 'duration_seconds': 3, 'lang': {'name': 'british english', 'code': 'en-GB', 'standard': 'IETF'}}, {'from': 'Josh', 'file': 'db/audios/4953417715/audio_62@17-12-2020_12-06-22.wav', 'id': 168, 'text': 'pandemonium', 'from_id': 4953417715, 'duration_seconds': 1, 'lang': {'name': 'british english', 'code': 'en-GB', 'standard': 'IETF'}}, {'from': 'nilya musaeva*️⃣', 'file': 'db/audios/4472772915/audio_63@17-12-2020_12-16-03.wav', 'id': 173, 'text': 'মন মরা ভাব', 'from_id': 4472772915, 'duration_seconds': 2, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'Debaditya Bhowmik', 'file': 'db/audios/5715773637/audio_64@17-12-2020_12-37-12.wav', 'id': 181, 'text': '', 'from_id': 5715773637, 'duration_seconds': 2, 'lang': {'name': 'bengali', 'code': 'bn', 'standard': 'ISO 639-1'}}, {'from': 'Julia', 'file': 'db/audios/5319950334/audio_65@17-12-2020_12-37-54.wav', 'id': 182, 'text': 'hamstern', 'from_id': 5319950334, 'duration_seconds': 1, 'lang': {'name': 'german', 'code': 'de', 'standard': 'ISO 639-1'}}, {'from': 'Debaditya Bhowmik', 'file': 'db/audios/5715773637/audio_66@17-12-2020_12-38-13.wav', 'id': 185, 'text': '', 'from_id': 5715773637, 'duration_seconds': 2, 'lang': {'name': 'bengali', 'code': 'bn', 'standard': 'ISO 639-1'}}, {'from': 'Julia', 'file': 'db/audios/5319950334/audio_67@17-12-2020_12-41-41.wav', 'id': 186, 'text': 'vereinsamen', 'from_id': 5319950334, 'duration_seconds': 1, 'lang': {'name': 'german', 'code': 'de', 'standard': 'ISO 639-1'}}, {'from': 'Ayse Seyhan', 'file': 'db/audios/5465850985/audio_68@17-12-2020_13-42-41.wav', 'id': 188, 'text': 'Kırlangıç', 'from_id': 5465850985, 'duration_seconds': 3, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Ayse Seyhan', 'file': 'db/audios/5465850985/audio_69@17-12-2020_13-43-02.wav', 'id': 190, 'text': 'Huzur', 'from_id': 5465850985, 'duration_seconds': 3, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Ayse Seyhan', 'file': 'db/audios/5465850985/audio_70@17-12-2020_13-43-14.wav', 'id': 192, 'text': 'Tesadüf', 'from_id': 5465850985, 'duration_seconds': 3, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Ayse Seyhan', 'file': 'db/audios/5465850985/audio_71@17-12-2020_13-43-29.wav', 'id': 194, 'text': 'Afilli', 'from_id': 5465850985, 'duration_seconds': 3, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Ayse Seyhan', 'file': 'db/audios/5465850985/audio_72@17-12-2020_13-43-48.wav', 'id': 196, 'text': 'Serzeniş', 'from_id': 5465850985, 'duration_seconds': 3, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Ayse Seyhan', 'file': 'db/audios/5465850985/audio_73@17-12-2020_13-46-23.wav', 'id': 198, 'text': 'Sadakat', 'from_id': 5465850985, 'duration_seconds': 2, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Ayse Seyhan', 'file': 'db/audios/5465850985/audio_74@17-12-2020_13-46-50.wav', 'id': 200, 'text': 'Masum', 'from_id': 5465850985, 'duration_seconds': 2, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Ayse Seyhan', 'file': 'db/audios/5465850985/audio_75@17-12-2020_13-46-59.wav', 'id': 202, 'text': 'Masumiyet', 'from_id': 5465850985, 'duration_seconds': 2, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Ayse Seyhan', 'file': 'db/audios/5465850985/audio_76@17-12-2020_13-47-15.wav', 'id': 204, 'text': 'Aşk', 'from_id': 5465850985, 'duration_seconds': 2, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Ayse Seyhan', 'file': 'db/audios/5465850985/audio_77@17-12-2020_13-47-33.wav', 'id': 206, 'text': 'Ansızın', 'from_id': 5465850985, 'duration_seconds': 2, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Chi Him Chik', 'file': 'db/audios/5576183485/audio_78@17-12-2020_13-57-42.wav', 'id': 208, 'text': '封關呀仆街', 'from_id': 5576183485, 'duration_seconds': 2, 'lang': {'name': 'cantonese', 'code': 'yue', 'standard': 'ISO 639-3'}}, {'from': 'Chi Him Chik', 'file': 'db/audios/5576183485/audio_79@17-12-2020_13-58-13.wav', 'id': 211, 'text': '帶口罩呀屌你老母', 'from_id': 5576183485, 'duration_seconds': 2, 'lang': {'name': 'cantonese', 'code': 'yue', 'standard': 'ISO 639-3'}}, {'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_80@17-12-2020_14-15-18.wav', 'id': 213, 'text': 'Falta de ar', 'from_id': 5631317686, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Antônio Hof', 'file': 'db/audios/5629926613/audio_81@17-12-2020_14-20-30.wav', 'id': 215, 'text': 'solidão', 'from_id': 5629926613, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Antônio Hof', 'file': 'db/audios/5629926613/audio_82@17-12-2020_14-20-58.wav', 'id': 217, 'text': 'ermo', 'from_id': 5629926613, 'duration_seconds': 1, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_83@17-12-2020_17-33-22.wav', 'id': 220, 'text': '', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_84@17-12-2020_17-33-30.wav', 'id': 221, 'text': '', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_85@17-12-2020_17-33-38.wav', 'id': 222, 'text': '', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_86@17-12-2020_17-33-56.wav', 'id': 223, 'text': '', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_87@18-12-2020_17-12-23.wav', 'id': 224, 'text': 'O Mundo', 'from_id': 5631317686, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Anna', 'file': 'db/audios/4570123136/audio_88@18-12-2020_18-05-21.wav', 'id': 226, 'text': 'Салідарнасць', 'from_id': 4570123136, 'duration_seconds': 2, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'Anna', 'file': 'db/audios/4570123136/audio_89@18-12-2020_18-06-14.wav', 'id': 228, 'text': 'Рэвалюцыя', 'from_id': 4570123136, 'duration_seconds': 1, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'Anna', 'file': 'db/audios/4570123136/audio_90@18-12-2020_18-06-45.wav', 'id': 230, 'text': 'Супольнасць', 'from_id': 4570123136, 'duration_seconds': 1, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'ruoxi', 'file': 'db/audios/5136095171/audio_91@19-12-2020_11-13-59.wav', 'id': 232, 'text': '恍儿胡兮', 'from_id': 5136095171, 'duration_seconds': 1, 'lang': {'name': 'chongqing dialect', 'code': 'chen1267', 'standard': 'glottolog'}}, {'from': 'ruoxi', 'file': 'db/audios/5136095171/audio_92@19-12-2020_11-14-59.wav', 'id': 234, 'text': '哭兮来呆', 'from_id': 5136095171, 'duration_seconds': 1, 'lang': {'name': 'chongqing dialect', 'code': 'chen1267', 'standard': 'glottolog'}}, {'from': 'Abdulghaffar', 'file': 'db/audios/4746759530/audio_93@19-12-2020_12-04-26.wav', 'id': 236, 'text': 'عزلة', 'from_id': 4746759530, 'duration_seconds': 2, 'lang': {'name': 'arabic', 'code': 'ar', 'standard': 'ISO 639-1'}}, {'from': 'Abdulghaffar', 'file': 'db/audios/4746759530/audio_94@19-12-2020_12-05-00.wav', 'id': 238, 'text': 'تضامن', 'from_id': 4746759530, 'duration_seconds': 2, 'lang': {'name': 'arabic', 'code': 'ar', 'standard': 'ISO 639-1'}}, {'from': 'Abdulghaffar', 'file': 'db/audios/4746759530/audio_95@19-12-2020_12-05-54.wav', 'id': 240, 'text': 'حنين', 'from_id': 4746759530, 'duration_seconds': 1, 'lang': {'name': 'arabic', 'code': 'ar', 'standard': 'ISO 639-1'}}, {'from': 'Abdulghaffar', 'file': 'db/audios/4746759530/audio_96@19-12-2020_12-06-21.wav', 'id': 242, 'text': 'واقع', 'from_id': 4746759530, 'duration_seconds': 1, 'lang': {'name': 'arabic', 'code': 'ar', 'standard': 'ISO 639-1'}}, {'from': 'Abdulghaffar', 'file': 'db/audios/4746759530/audio_97@19-12-2020_12-07-12.wav', 'id': 245, 'text': 'حياة', 'from_id': 4746759530, 'duration_seconds': 2, 'lang': {'name': 'arabic', 'code': 'ar', 'standard': 'ISO 639-1'}}, {'from': 'Abdulghaffar', 'file': 'db/audios/4746759530/audio_98@19-12-2020_12-07-32.wav', 'id': 247, 'text': 'خيال', 'from_id': 4746759530, 'duration_seconds': 2, 'lang': {'name': 'arabic', 'code': 'ar', 'standard': 'ISO 639-1'}}, {'from': 'Abdulghaffar', 'file': 'db/audios/4746759530/audio_99@19-12-2020_12-07-49.wav', 'id': 249, 'text': 'انتظار', 'from_id': 4746759530, 'duration_seconds': 2, 'lang': {'name': 'arabic', 'code': 'ar', 'standard': 'ISO 639-1'}}, {'from': 'Abdulghaffar', 'file': 'db/audios/4746759530/audio_100@19-12-2020_12-08-06.wav', 'id': 251, 'text': 'تغيير', 'from_id': 4746759530, 'duration_seconds': 2, 'lang': {'name': 'arabic', 'code': 'ar', 'standard': 'ISO 639-1'}}, {'from': 'Pelin', 'file': 'db/audios/5227186112/audio_101@19-12-2020_20-06-53.wav', 'id': 253, 'text': 'Bunaltı', 'from_id': 5227186112, 'duration_seconds': 2, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Pelin', 'file': 'db/audios/5227186112/audio_102@19-12-2020_20-08-49.wav', 'id': 255, 'text': 'Beynelmilel', 'from_id': 5227186112, 'duration_seconds': 2, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Pelin', 'file': 'db/audios/5227186112/audio_103@19-12-2020_20-10-33.wav', 'id': 257, 'text': 'Fütursuz', 'from_id': 5227186112, 'duration_seconds': 2, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Pelin', 'file': 'db/audios/5227186112/audio_104@19-12-2020_20-11-20.wav', 'id': 259, 'text': 'Belirsizlik', 'from_id': 5227186112, 'duration_seconds': 2, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Pelin', 'file': 'db/audios/5227186112/audio_105@19-12-2020_20-12-18.wav', 'id': 261, 'text': 'Muallak', 'from_id': 5227186112, 'duration_seconds': 2, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'Pelin', 'file': 'db/audios/5227186112/audio_106@19-12-2020_20-13-33.wav', 'id': 263, 'text': 'Yeni gerçeklik', 'from_id': 5227186112, 'duration_seconds': 2, 'lang': {'name': 'turkish', 'code': 'tr', 'standard': 'ISO 639-1'}}, {'from': 'ruoxi', 'file': 'db/audios/5136095171/audio_107@20-12-2020_13-48-13.wav', 'id': 265, 'text': '囊个嫩个列个安', 'from_id': 5136095171, 'duration_seconds': 2, 'lang': {'name': 'chongqing dialect', 'code': 'chen1267', 'standard': 'glottolog'}}, {'from': 'Bruno HfK', 'file': 'db/audios/5203538418/audio_108@21-12-2020_11-06-10.wav', 'id': 270, 'text': 'Provocações', 'from_id': 5203538418, 'duration_seconds': 3, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Ivett K.', 'file': 'db/audios/5170943596/audio_109@21-12-2020_18-13-43.wav', 'id': 272, 'text': 'SZFE-tüntetés', 'from_id': 5170943596, 'duration_seconds': 1, 'lang': {'name': 'hungarian', 'code': 'hu', 'standard': 'ISO 639-1'}}, {'from': 'Ivett K.', 'file': 'db/audios/5170943596/audio_110@21-12-2020_18-14-03.wav', 'id': 274, 'text': 'Operatív törzs', 'from_id': 5170943596, 'duration_seconds': 1, 'lang': {'name': 'hungarian', 'code': 'hu', 'standard': 'ISO 639-1'}}, {'from': 'Ivett K.', 'file': 'db/audios/5170943596/audio_111@21-12-2020_18-14-38.wav', 'id': 276, 'text': 'Bicikliút a körúton', 'from_id': 5170943596, 'duration_seconds': 2, 'lang': {'name': 'hungarian', 'code': 'hu', 'standard': 'ISO 639-1'}}, {'from': 'Ivett K.', 'file': 'db/audios/5170943596/audio_112@21-12-2020_18-15-09.wav', 'id': 278, 'text': 'Szeparáltság', 'from_id': 5170943596, 'duration_seconds': 1, 'lang': {'name': 'hungarian', 'code': 'hu', 'standard': 'ISO 639-1'}}, {'from': 'Ivett K.', 'file': 'db/audios/5170943596/audio_113@21-12-2020_18-15-28.wav', 'id': 280, 'text': 'A szituáció kihasználása', 'from_id': 5170943596, 'duration_seconds': 2, 'lang': {'name': 'hungarian', 'code': 'hu', 'standard': 'ISO 639-1'}}, {'from': 'Antônio Hof', 'file': 'db/audios/5629926613/audio_114@22-12-2020_20-15-42.wav', 'id': 282, 'text': 'estrangulado', 'from_id': 5629926613, 'duration_seconds': 3, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Antônio Hof', 'file': 'db/audios/5629926613/audio_115@22-12-2020_20-16-27.wav', 'id': 284, 'text': 'desbotado', 'from_id': 5629926613, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Antônio Hof', 'file': 'db/audios/5629926613/audio_116@22-12-2020_20-16-59.wav', 'id': 286, 'text': 'destituído', 'from_id': 5629926613, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Soumya Hfk', 'file': 'db/audios/5572716069/audio_117@24-12-2020_17-03-08.wav', 'id': 288, 'text': '', 'from_id': 5572716069, 'duration_seconds': 2, 'lang': {'name': 'bengali', 'code': 'bn', 'standard': 'ISO 639-1'}}, {'from': 'Soumya Hfk', 'file': 'db/audios/5572716069/audio_118@24-12-2020_17-04-00.wav', 'id': 289, 'text': 'দেখা যাক কি হয়', 'from_id': 5572716069, 'duration_seconds': 2, 'lang': {'name': 'bengali', 'code': 'bn', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_119@26-12-2020_03-26-48.wav', 'id': 293, 'text': '自粛警察', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_120@26-12-2020_03-27-47.wav', 'id': 297, 'text': '俺はまだいいけど', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_121@26-12-2020_03-29-13.wav', 'id': 300, 'text': '一億総引きこもり', 'from_id': 5314577364, 'duration_seconds': 2, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_122@26-12-2020_03-30-04.wav', 'id': 302, 'text': '俺もともと引きこもりだし', 'from_id': 5314577364, 'duration_seconds': 2, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_123@26-12-2020_03-33-15.wav', 'id': 304, 'text': '実はドッキリでした', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_124@26-12-2020_03-33-27.wav', 'id': 306, 'text': '茶番感', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_10@26-12-2020_13-44-04.wav', 'id': 308, 'text': 'クリスマスは今年もやって来る', 'from_id': 5314577364, 'duration_seconds': 5, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_126@26-12-2020_03-35-58.wav', 'id': 310, 'text': '県外ナンバーお断り', 'from_id': 5314577364, 'duration_seconds': 2, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_127@26-12-2020_03-36-31.wav', 'id': 312, 'text': 'ゼノフォビア', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_128@26-12-2020_03-36-46.wav', 'id': 314, 'text': 'ナショナリズム', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_129@26-12-2020_03-37-56.wav', 'id': 316, 'text': 'マスク買い占め', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_130@26-12-2020_03-38-12.wav', 'id': 318, 'text': 'トイレットペーパー品切れ', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_131@26-12-2020_03-38-25.wav', 'id': 320, 'text': '手作りマスク', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_132@26-12-2020_03-38-44.wav', 'id': 322, 'text': 'それでも桜は咲く', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_133@26-12-2020_03-39-46.wav', 'id': 324, 'text': '自殺者４割り増し', 'from_id': 5314577364, 'duration_seconds': 2, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_134@26-12-2020_03-40-14.wav', 'id': 326, 'text': 'テイクアウト始めました', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_135@26-12-2020_03-41-03.wav', 'id': 328, 'text': '介在', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_136@26-12-2020_03-41-15.wav', 'id': 330, 'text': '媒体', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'Kazuki', 'file': 'db/audios/5314577364/audio_137@26-12-2020_03-41-27.wav', 'id': 332, 'text': '介入', 'from_id': 5314577364, 'duration_seconds': 1, 'lang': {'name': 'japanese', 'code': 'ja', 'standard': 'ISO 639-1'}}, {'from': 'ruoxi', 'file': 'db/audios/5136095171/audio_138@26-12-2020_21-52-15.wav', 'id': 334, 'text': '小猫呼噜', 'from_id': 5136095171, 'duration_seconds': 3, 'lang': {'name': 'chongqing dialect', 'code': 'chen1267', 'standard': 'glottolog'}}, {'from': 'nilya musaeva*️⃣', 'file': 'db/audios/4472772915/audio_139@29-12-2020_14-08-11.wav', 'id': 336, 'text': 'пизда рулю ))))))', 'from_id': 4472772915, 'duration_seconds': 2, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'Slava Romanov', 'file': 'db/audios/4487042723/audio_140@29-12-2020_19-11-39.wav', 'id': 338, 'text': 'Холодильник', 'from_id': 4487042723, 'duration_seconds': 1, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'Slava Romanov', 'file': 'db/audios/4487042723/audio_141@29-12-2020_19-11-39.wav', 'id': 340, 'text': 'Домашняя дым-машина', 'from_id': 4487042723, 'duration_seconds': 2, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'Slava Romanov', 'file': 'db/audios/4487042723/audio_142@29-12-2020_19-11-39.wav', 'id': 342, 'text': 'Попытки убедить родных', 'from_id': 4487042723, 'duration_seconds': 3, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'Slava Romanov', 'file': 'db/audios/4487042723/audio_143@29-12-2020_19-11-39.wav', 'id': 344, 'text': 'Доставка суши', 'from_id': 4487042723, 'duration_seconds': 2, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'Slava Romanov', 'file': 'db/audios/4487042723/audio_144@29-12-2020_19-11-39.wav', 'id': 346, 'text': 'Изопропанол', 'from_id': 4487042723, 'duration_seconds': 1, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'Slava Romanov', 'file': 'db/audios/4487042723/audio_145@29-12-2020_19-11-39.wav', 'id': 348, 'text': 'Выпрыгнуть в окно возможностей', 'from_id': 4487042723, 'duration_seconds': 3, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'Marcela DM', 'file': 'db/audios/5172654043/audio_146@03-01-2021_20-19-30.wav', 'id': 352, 'text': 'Aislamiento', 'from_id': 5172654043, 'duration_seconds': 1, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Marcela DM', 'file': 'db/audios/5172654043/audio_147@03-01-2021_20-19-39.wav', 'id': 354, 'text': 'Extrañar', 'from_id': 5172654043, 'duration_seconds': 1, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Marcela DM', 'file': 'db/audios/5172654043/audio_148@03-01-2021_20-19-57.wav', 'id': 356, 'text': 'Normalidad', 'from_id': 5172654043, 'duration_seconds': 1, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Marcela DM', 'file': 'db/audios/5172654043/audio_149@03-01-2021_20-20-13.wav', 'id': 358, 'text': 'Compañía', 'from_id': 5172654043, 'duration_seconds': 1, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Marcela DM', 'file': 'db/audios/5172654043/audio_150@03-01-2021_20-20-23.wav', 'id': 360, 'text': 'Depresión', 'from_id': 5172654043, 'duration_seconds': 1, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Marcela DM', 'file': 'db/audios/5172654043/audio_151@03-01-2021_20-20-35.wav', 'id': 362, 'text': 'Incertidumbre', 'from_id': 5172654043, 'duration_seconds': 1, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Marcela DM', 'file': 'db/audios/5172654043/audio_152@03-01-2021_20-20-46.wav', 'id': 364, 'text': 'Dormitorio', 'from_id': 5172654043, 'duration_seconds': 1, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Marcela DM', 'file': 'db/audios/5172654043/audio_153@03-01-2021_20-20-57.wav', 'id': 366, 'text': 'Sobrevivir', 'from_id': 5172654043, 'duration_seconds': 1, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Marcela DM', 'file': 'db/audios/5172654043/audio_154@03-01-2021_20-21-09.wav', 'id': 368, 'text': 'Motivación', 'from_id': 5172654043, 'duration_seconds': 1, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Marcela DM', 'file': 'db/audios/5172654043/audio_155@03-01-2021_20-21-22.wav', 'id': 370, 'text': 'Miedo', 'from_id': 5172654043, 'duration_seconds': 1, 'lang': {'name': 'spanish', 'code': 'es', 'standard': 'ISO 639-1'}}, {'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_156@05-01-2021_13-55-12.wav', 'id': 373, 'text': 'Grupo de risco', 'from_id': 5631317686, 'duration_seconds': 3, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Anna', 'file': 'db/audios/4570123136/audio_157@05-01-2021_17-19-46.wav', 'id': 375, 'text': 'Адзінота', 'from_id': 4570123136, 'duration_seconds': 1, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'Anna', 'file': 'db/audios/4570123136/audio_158@05-01-2021_17-20-05.wav', 'id': 377, 'text': 'Хлеб', 'from_id': 4570123136, 'duration_seconds': 1, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'Anna', 'file': 'db/audios/4570123136/audio_159@05-01-2021_17-20-25.wav', 'id': 379, 'text': 'Сумаваць', 'from_id': 4570123136, 'duration_seconds': 1, 'lang': {'name': 'russian', 'code': 'ru', 'standard': 'ISO 639-1'}}, {'from': 'Hem Poudyal', 'file': 'db/audios/5411097981/audio_160@05-01-2021_17-33-47.wav', 'id': 381, 'text': 'माहामारी', 'from_id': 5411097981, 'duration_seconds': 1, 'lang': {'name': 'nepali', 'code': 'ne', 'standard': 'ISO 639-1'}}, {'from': 'Hem Poudyal', 'file': 'db/audios/5411097981/audio_161@05-01-2021_17-34-20.wav', 'id': 383, 'text': 'यथार्थ स्विकार्नु', 'from_id': 5411097981, 'duration_seconds': 3, 'lang': {'name': 'nepali', 'code': 'ne', 'standard': 'ISO 639-1'}}, {'from': 'Hem Poudyal', 'file': 'db/audios/5411097981/audio_162@05-01-2021_17-35-00.wav', 'id': 385, 'text': 'दुर शिक्षा', 'from_id': 5411097981, 'duration_seconds': 3, 'lang': {'name': 'nepali', 'code': 'ne', 'standard': 'ISO 639-1'}}, {'from': 'Hem Poudyal', 'file': 'db/audios/5411097981/audio_163@05-01-2021_17-36-03.wav', 'id': 387, 'text': 'सामाजिक दुरी', 'from_id': 5411097981, 'duration_seconds': 3, 'lang': {'name': 'nepali', 'code': 'ne', 'standard': 'ISO 639-1'}}, {'from': 'Lucca', 'file': 'db/audios/5155406234/audio_164@05-01-2021_17-37-09.wav', 'id': 389, 'text': 'Einsamkeit', 'from_id': 5155406234, 'duration_seconds': 1, 'lang': {'name': 'german', 'code': 'de', 'standard': 'ISO 639-1'}}, {'from': 'Lucca', 'file': 'db/audios/5155406234/audio_165@05-01-2021_17-37-25.wav', 'id': 391, 'text': 'Langeweile', 'from_id': 5155406234, 'duration_seconds': 1, 'lang': {'name': 'german', 'code': 'de', 'standard': 'ISO 639-1'}}, {'from': 'Lucca', 'file': 'db/audios/5155406234/audio_17@05-01-2021_17-44-03.wav', 'id': 393, 'text': 'Monotonie', 'from_id': 5155406234, 'duration_seconds': 1, 'lang': {'name': 'german', 'code': 'de', 'standard': 'ISO 639-1'}}, {'from': 'Lucca', 'file': 'db/audios/5155406234/audio_167@05-01-2021_17-38-00.wav', 'id': 395, 'text': 'Dunkelheit', 'from_id': 5155406234, 'duration_seconds': 1, 'lang': {'name': 'german', 'code': 'de', 'standard': 'ISO 639-1'}}, {'from': 'Lucca', 'file': 'db/audios/5155406234/audio_168@05-01-2021_17-38-28.wav', 'id': 397, 'text': 'Sehnsucht', 'from_id': 5155406234, 'duration_seconds': 2, 'lang': {'name': 'german', 'code': 'de', 'standard': 'ISO 639-1'}}, {'from': 'S. C.', 'file': 'db/audios/4408865338/audio_169@06-01-2021_15-35-42.wav', 'id': 399, 'text': '外卖', 'from_id': 4408865338, 'duration_seconds': 1, 'lang': {'name': 'mandarin chinese', 'code': 'cmn', 'standard': 'ISO 639-3'}}, {'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_170@06-01-2021_17-26-18.wav', 'id': 403, 'text': 'Carinho', 'from_id': 5631317686, 'duration_seconds': 2, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'ruoxi', 'file': 'db/audios/5136095171/audio_171@06-01-2021_21-01-02.wav', 'id': 405, 'text': '吃火锅', 'from_id': 5136095171, 'duration_seconds': 1, 'lang': {'name': 'chongqing dialect', 'code': 'chen1267', 'standard': 'glottolog'}}, {'from': 'Chi Him Chik', 'file': 'db/audios/5576183485/audio_172@06-01-2021_21-13-34.wav', 'id': 407, 'text': '乜都唔做', 'from_id': 5576183485, 'duration_seconds': 1, 'lang': {'name': 'cantonese', 'code': 'yue', 'standard': 'ISO 639-3'}}, {'from': 'Chi Him Chik', 'file': 'db/audios/5576183485/audio_173@06-01-2021_21-13-47.wav', 'id': 409, 'text': '乜都做唔到', 'from_id': 5576183485, 'duration_seconds': 2, 'lang': {'name': 'cantonese', 'code': 'yue', 'standard': 'ISO 639-3'}}, {'from': 'nilya musaeva*️⃣', 'file': 'db/audios/4472772915/audio_174@06-01-2021_21-17-40.wav', 'id': 411, 'text': 'tikişçilik', 'from_id': 4472772915, 'duration_seconds': 1, 'lang': {'name': 'azerbaijani', 'code': 'az', 'standard': 'ISO 639-1'}}, {'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_175@12-01-2021_18-29-14.wav', 'id': 415, 'text': 'Saudades', 'from_id': 5631317686, 'duration_seconds': 1, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'Bonasladybug', 'file': 'db/audios/4357336763/audio_176@14-01-2021_19-51-16.wav', 'id': 418, 'text': 'دلتنگی', 'from_id': 4357336763, 'duration_seconds': 2, 'lang': {'name': 'persian', 'code': 'pes', 'standard': 'ISO 639-3'}}, {'from': 'Bonasladybug', 'file': 'db/audios/4357336763/audio_177@14-01-2021_19-51-42.wav', 'id': 421, 'text': 'صبر', 'from_id': 4357336763, 'duration_seconds': 1, 'lang': {'name': 'persian', 'code': 'pes', 'standard': 'ISO 639-3'}}, {'from': 'Bonasladybug', 'file': 'db/audios/4357336763/audio_178@14-01-2021_19-52-05.wav', 'id': 423, 'text': 'رقصیدن', 'from_id': 4357336763, 'duration_seconds': 1, 'lang': {'name': 'persian', 'code': 'pes', 'standard': 'ISO 639-3'}}, {'from': 'Bonasladybug', 'file': 'db/audios/4357336763/audio_179@14-01-2021_19-52-25.wav', 'id': 425, 'text': 'موسیقی', 'from_id': 4357336763, 'duration_seconds': 2, 'lang': {'name': 'persian', 'code': 'pes', 'standard': 'ISO 639-3'}}, {'from': 'Bonasladybug', 'file': 'db/audios/4357336763/audio_180@14-01-2021_19-52-50.wav', 'id': 427, 'text': 'خانواده', 'from_id': 4357336763, 'duration_seconds': 1, 'lang': {'name': 'persian', 'code': 'pes', 'standard': 'ISO 639-3'}}, {'from': 'Bonasladybug', 'file': 'db/audios/4357336763/audio_181@14-01-2021_19-53-06.wav', 'id': 429, 'text': 'سلامتی', 'from_id': 4357336763, 'duration_seconds': 2, 'lang': {'name': 'persian', 'code': 'pes', 'standard': 'ISO 639-3'}}, {'from': 'Alberto Harres', 'file': 'db/audios/5631317686/audio_182@21-01-2021_01-26-41.wav', 'id': 431, 'text': 'Afetos criptografados', 'from_id': 5631317686, 'duration_seconds': 4, 'lang': {'name': 'brazilian portuguese', 'code': 'pt-br', 'standard': 'ISO 639-1'}}, {'from': 'S. C.', 'file': 'db/audios/4408865338/audio_183@21-01-2021_19-37-15.wav', 'id': 433, 'text': '剪头发', 'from_id': 4408865338, 'duration_seconds': 2, 'lang': {'name': 'mandarin chinese', 'code': 'cmn', 'standard': 'ISO 639-3'}}], 'speakers': [{'speaker': 'Alberto Harres', 'id': 5631317686}, {'speaker': 'nilya musaeva', 'id': 4472772915}, {'speaker': 'S. C.', 'id': 4408865338}, {'speaker': 'ruoxi', 'id': 5136095171}, {'speaker': 'Kazuki', 'id': 5314577364}, {'speaker': 'Hem Poudyal', 'id': 5411097981}, {'speaker': 'Antônio Hof', 'id': 5629926613}, {'speaker': 'Chi Him Chik', 'id': 5576183485}, {'speaker': 'Sangbong Lee', 'id': 5524258652}, {'speaker': 'Josh', 'id': 4953417715}, {'speaker': 'Bojana', 'id': 4612847105}, {'speaker': 'Victor Artiga', 'id': 4963464597}, {'speaker': 'Debaditya Bhowmik', 'id': 5715773637}, {'speaker': 'Julia', 'id': 5319950334}, {'speaker': 'Ayse Seyhan', 'id': 5465850985}, {'speaker': 'Anna', 'id': 4570123136}, {'speaker': 'Abdulghaffar', 'id': 4746759530}, {'speaker': 'Pelin', 'id': 5227186112}, {'speaker': 'Bruno HfK', 'id': 5203538418}, {'speaker': 'Ivett K.', 'id': 5170943596}, {'speaker': 'Slava Romanov', 'id': 4487042723}, {'speaker': 'Marcela DM', 'id': 5172654043}, {'speaker': 'Lucca', 'id': 5155406234}, {'speaker': 'Bonasladybug', 'id': 4357336763}, {'speaker': 'Soumya HfK', 'id': 5572716069}]}
Reading audio data¶
- Get random audio from the archive.
- Convert it to 8bit audio with 8000hz Sample Rate
- Save the data and plot it
In [49]:
from scipy.io import wavfile
import scipy.io
import matplotlib.pyplot as plt
import numpy as np
import os
db_url = 'https://pandemic-archive-of-voices.herokuapp.com/'
# pick random auido fomr database
audio_data = np.random.choice(audios, size=1)[0]
# download file from database and save it temporarily
r = requests.get(db_url + audio_data['file'], allow_redirects=True)
filename = audio_data['file'].split('/')[3]
open(filename, 'wb').write(r.content)
# Run ffmpeg to convert audio to 8bit 8000hz sample rate
os.system('ffmpeg -i ' + filename + ' -ar 8000 -ac 1 -acodec pcm_u8 output.wav')
## load converted file data
samplerate, data = wavfile.read('output.wav')
# plot audio data
length = data.shape[0] / samplerate
time = np.linspace(0., length, data.shape[0])
plt.plot(time, data)
plt.xlabel("Time [s]")
plt.ylabel("Amplitude")
plt.show()
# delete downloaded file
os.remove(filename)
# print(samplerate, data)
#file_path = db_url + audio_data['file']
8000 [125 124 125 ... 128 128 128]
Visualize audio data as image data¶
In [50]:
from matplotlib import colors
from matplotlib import figure
import math
# set size of plot
fig = plt.figure(figsize = (12,12))
# find middle divisor of the array data
numbers = []
for i in range(1, len(data) + 1):
if len(data) % i == 0:
numbers.append(i)
divisor = numbers[math.ceil(len(numbers) / 2)]
# transform array data into a "rectangle"
grid_values = np.reshape(data, (-1, divisor))
plt.axis('off')
img = plt.imshow(grid_values, interpolation='bicubic', cmap = 'magma')
Create Alphabet¶
Creating array of characters to be used when transforming the 8bit data into a Unicode character.
In [2]:
texts = ""
for i in audios:
texts = texts + i['text']
print(texts)
Númerosеда怪迷日眼Ensimesmado造孽巴撒遇球得到ロックダウン非常事態宣言20秒間三密Zoom会議コロナに効く！コロナに負けないコロナ下閉店しましたこんなご時世ですがまた会う日までकोरोनाको समय, एक्लोपन अनि असहजतासंवेदनशील मानव जीवनबाध्यताSirenesRespiradoresEsperançaAlemãoсистема цифровых пропусков宅健康码第一波第二波第三波第四波코로나 감염병 확산확진자가짜뉴스와 음모론격리시설가짜뉴스와 음모론Protocolos de distanciamento socialIncertezasMinutos de silênciodog's dinnerextended support bubbleMáscarazigue-zagueнадоелоnedostajanjevremebliskostdaljinaograničenostসবাই ভালো থেকোLutoDistanciaIntrospecciónAmistadesCercaniaNostalgiachurch bells and sirenspandemoniumমন মরা ভাবhamsternvereinsamenKırlangıçHuzurTesadüfAfilliSerzenişSadakatMasumMasumiyetAşkAnsızın封關呀仆街帶口罩呀屌你老母Falta de arsolidãoermoO MundoСалідарнасцьРэвалюцыяСупольнасць恍儿胡兮哭兮来呆عزلةتضامنحنينواقعحياةخيالانتظارتغييرBunaltıBeynelmilelFütursuzBelirsizlikMuallakYeni gerçeklik囊个嫩个列个安ProvocaçõesSZFE-tüntetésOperatív törzsBicikliút a körútonSzeparáltságA szituáció kihasználásaestranguladodesbotadodestituídoদেখা যাক কি হয়自粛警察俺はまだいいけど一億総引きこもり俺もともと引きこもりだし実はドッキリでした茶番感クリスマスは今年もやって来る県外ナンバーお断りゼノフォビアナショナリズムマスク買い占めトイレットペーパー品切れ手作りマスクそれでも桜は咲く自殺者４割り増しテイクアウト始めました介在媒体介入小猫呼噜пизда рулю ))))))ХолодильникДомашняя дым-машинаПопытки убедить родныхДоставка сушиИзопропанолВыпрыгнуть в окно возможностейAislamientoExtrañarNormalidadCompañíaDepresiónIncertidumbreDormitorioSobrevivirMotivaciónMiedoGrupo de riscoАдзінотаХлебСумавацьमाहामारीयथार्थ स्विकार्नुदुर शिक्षासामाजिक दुरीEinsamkeitLangeweileMonotonieDunkelheitSehnsucht外卖Carinho吃火锅乜都唔做乜都做唔到tikişçilikSaudadesدلتنگیصبررقصیدنموسیقیخانوادهسلامتیAfetos criptografados剪头发
In [54]:
import random
def split(word):
return [char for char in word]
characters = split(texts)
unique_characters = [i for j, i in enumerate(characters) if i not in characters[:j]]
random.shuffle(unique_characters)
random.shuffle(characters)
with open('unique-characters.json', 'w') as f:
json.dump(unique_characters, f)
print(unique_characters)
['п', '在', "'", 'ध', 'ペ', '作', 'अ', 'v', 'н', 'n', '介', '코', 'ü', 'ض', 'া', 'ド', '第', 'о', 'ь', 'د', '秒', '়', 'ं', 'দ', 'z', 'হ', 'в', '兮', 'い', 'd', '店', '仆', 'に', 'め', 'č', '口', 'ン', '孽', 'で', '球', '码', '짜', '切', '康', '健', 'す', 'j', '老', 'S', '2', '品', '呼', '做', '迷', '0', 'х', '宅', 'A', 'ই', 'ह', 'س', '察', 'な', '乜', 'ص', 'テ', '粛', '安', 'F', '怪', '封', '警', '巴', 'b', '्', 'C', '４', '得', 'á', '時', 'k', 'け', 'ビ', '！', 'と', 'ご', 'ظ', 'ا', '론', '密', 'Y', '-', '시', '呆', 'त', '리', 'П', ',', 'L', 'ク', '嫩', 'ォ', '확', 'u', 'れ', '桜', 'б', 'て', '胡', 'f', 'Х', 'я', '뉴', 'خ', 'ゼ', 'م', 'й', 'は', '帶', '媒', 'ل', '負', '剪', 'í', '진', 'А', 'ö', 'ん', 'ョ', 'õ', 'フ', '閉', 'ノ', 'ó', 'র', 'ы', 'گ', 'O', 'ि', 'ع', '事', 'w', 'ন', '占', 'N', 'ã', '个', 'ष', 'व', '卖', 'a', '屌', '入', '体', 'غ', '始', 'p', ' ', 'ब', 'ズ', 'i', '關', 'う', 'x', 'у', 'く', 'P', '会', 'े', 'খ', 'य', '撒', 'э', 'こ', 'イ', 'ー', 'ো', 'ر', 'ة', '罩', '头', '산', 'り', 'ю', '呀', 'e', 'و', '年', 'е', 'ب', '감', 'ज', 'ı', 'ه', 'レ', 'а', '遇', 'バ', 'た', 'I', 'р', '効', 't', 'ভ', 'ス', 'м', '火', 'ş', '番', 'Р', '今', '恍', '모', '県', '者', 'म', '割', '锅', 'ア', 'リ', '母', '음', 's', 'ح', 'G', 'থ', '造', 'る', '염', 'や', '小', 'そ', '哭', '眼', 'з', '儿', 'ダ', ')', 'E', '列', '総', 'K', 'к', '吃', 'ी', 'ن', 'ु', 'し', 'ж', '自', '非', 'र', 'क', 'が', 'ی', 'ど', 'श', 'ロ', 'M', 'Z', 'r', 'ト', 'ウ', '言', '로', 'h', '断', 'D', 'T', 'ت', '外', '感', '唔', 'л', 'っ', 'ま', '가', 'प', '買', 'ক', 'ি', '二', '噜', 'ê', 'ф', 'コ', 'ッ', '都', 'ム', '実', '手', 'ল', 'ي', 'ल', 'ú', 'H', 'न', '설', '世', '병', 'ो', '一', 'l', 'é', 'थ', 'だ', 'm', 'स', '咲', 'ए', '到', '격', 'И', 'ে', '日', 'R', 'c', 'も', '間', 'y', 'с', 'С', '殺', 'ナ', 'g', '宣', '議', '増', 'き', 'т', '茶', '스', 'Д', 'য', 'パ', 'ц', 'シ', 'ш', 'ñ', '猫', 'o', '来', '와', '四', 'ব', '億', '街', '자', 'द', '发', 'ম', 'マ', 'ç', '常', '囊', '態', '俺', '引', 'キ', '波', 'і', 'и', 'ز', 'г', 'ق', 'ा', '你', 'B', 'お', 'д', 'স', '三', 'В', '下', '나']
Create SVG text grid with audio data¶
In [58]:
import drawSvg as draw
width=450
height=600
d = draw.Drawing(width, height)
# Draw text
fontSize = 4
fontWidth = fontSize - 1
x=0
y=height-fontSize
i=0
for i in data:
character = unique_characters[i]
d.append(draw.Text(character, fontSize, x, y)) # Text with font size 8
x = x + fontSize
if x > width-fontSize:
i = 0
x = 0
y = y - (fontSize + 2)
d.setPixelScale(2) # Set number of pixels per geometry unit
# Display in Jupyter notebook
d.rasterize() # Display as PNG
d # Display as SVG
# d.saveSvg('ArcheWriting.svg')
Out[58]: