wikitongues-db 0.2.6 → 0.2.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +6 -2
- package/data/processed/wikitongues_normalized.json +141 -0
- package/data/processed/wikitongues_normalized.jsonl +3 -0
- package/dist/dataset.js +141 -0
- package/dist/dataset.js.map +1 -1
- package/dist/dataset.mjs +141 -0
- package/dist/dataset.mjs.map +1 -1
- package/dist/index.js +141 -0
- package/dist/index.js.map +1 -1
- package/dist/index.mjs +141 -0
- package/dist/index.mjs.map +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -3,10 +3,14 @@
|
|
|
3
3
|
> A zero-dependency, in-memory database and search engine mapping three independent language classifications — **ISO 639-3**, **Glottolog** and **BCP 47** —
|
|
4
4
|
plus autonyms and Wikitongues' own labels to curated Wikitongues video recordings. Published for **TypeScript / JavaScript (npm)**.
|
|
5
5
|
|
|
6
|
-
*Built by the [Panglotive](https://www.panglotive.com) Team. Check out our work!*
|
|
7
|
-
|
|
8
6
|
---
|
|
9
7
|
|
|
8
|
+
## Explore the database
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
Explore the DB in [Panglotive](https://panglotive.com/en/blog/wikitongues/)'s blog :
|
|
12
|
+

|
|
13
|
+
|
|
10
14
|
## Motivation & Context
|
|
11
15
|
|
|
12
16
|
[Wikitongues](https://wikitongues.org/) is a non-profit organization dedicated to language documentation, revitalization, and diversity. Over the past decade, they have built an archive of video recordings representing hundreds of languages and dialects across YouTube and Wikimedia Commons.
|
|
@@ -55124,5 +55124,146 @@
|
|
|
55124
55124
|
"Chinese"
|
|
55125
55125
|
]
|
|
55126
55126
|
}
|
|
55127
|
+
},
|
|
55128
|
+
{
|
|
55129
|
+
"id": "yoEbTFxNrhE",
|
|
55130
|
+
"url": "https://www.youtube.com/watch?v=yoEbTFxNrhE",
|
|
55131
|
+
"duration_seconds": 22,
|
|
55132
|
+
"upload_date": "2026-09-25",
|
|
55133
|
+
"license": "ALL_RIGHTS_RESERVED",
|
|
55134
|
+
"content_type": "oral_history",
|
|
55135
|
+
"primary_language": {
|
|
55136
|
+
"standards": {
|
|
55137
|
+
"iso639_3": "cor",
|
|
55138
|
+
"glottocode": "corn1251",
|
|
55139
|
+
"bcp47": "kw"
|
|
55140
|
+
},
|
|
55141
|
+
"speaker_claim": null,
|
|
55142
|
+
"wikitongues_classification": "Cornish",
|
|
55143
|
+
"wikitongues_lineage": null,
|
|
55144
|
+
"autonym": "Kernewek"
|
|
55145
|
+
},
|
|
55146
|
+
"additional_languages": [],
|
|
55147
|
+
"speakers": [
|
|
55148
|
+
{
|
|
55149
|
+
"name": "Elizabeth",
|
|
55150
|
+
"role": "native",
|
|
55151
|
+
"origin": "United Kingdom"
|
|
55152
|
+
}
|
|
55153
|
+
],
|
|
55154
|
+
"provenance": {
|
|
55155
|
+
"country_code": "GB",
|
|
55156
|
+
"country_name": "United Kingdom",
|
|
55157
|
+
"region": "Cornwall",
|
|
55158
|
+
"city": null,
|
|
55159
|
+
"recorded_by": null,
|
|
55160
|
+
"recording_date": null
|
|
55161
|
+
},
|
|
55162
|
+
"transcription": {
|
|
55163
|
+
"has_subtitles": false,
|
|
55164
|
+
"available_subtitles": [],
|
|
55165
|
+
"native_text": null,
|
|
55166
|
+
"english_translation": null
|
|
55167
|
+
},
|
|
55168
|
+
"raw_metadata": {
|
|
55169
|
+
"title": "Elizabeth speaking Cornish",
|
|
55170
|
+
"tags": [
|
|
55171
|
+
"Wikitongues"
|
|
55172
|
+
]
|
|
55173
|
+
}
|
|
55174
|
+
},
|
|
55175
|
+
{
|
|
55176
|
+
"id": "bEVt0Tp6ZEA",
|
|
55177
|
+
"url": "https://www.youtube.com/watch?v=bEVt0Tp6ZEA",
|
|
55178
|
+
"duration_seconds": 31,
|
|
55179
|
+
"upload_date": "2026-09-23",
|
|
55180
|
+
"license": "ALL_RIGHTS_RESERVED",
|
|
55181
|
+
"content_type": "oral_history",
|
|
55182
|
+
"primary_language": {
|
|
55183
|
+
"standards": {
|
|
55184
|
+
"iso639_3": "cor",
|
|
55185
|
+
"glottocode": "corn1251",
|
|
55186
|
+
"bcp47": "kw"
|
|
55187
|
+
},
|
|
55188
|
+
"speaker_claim": null,
|
|
55189
|
+
"wikitongues_classification": "Cornish",
|
|
55190
|
+
"wikitongues_lineage": null,
|
|
55191
|
+
"autonym": "Kernewek"
|
|
55192
|
+
},
|
|
55193
|
+
"additional_languages": [],
|
|
55194
|
+
"speakers": [
|
|
55195
|
+
{
|
|
55196
|
+
"name": "Elizabeth",
|
|
55197
|
+
"role": "native",
|
|
55198
|
+
"origin": "United Kingdom"
|
|
55199
|
+
}
|
|
55200
|
+
],
|
|
55201
|
+
"provenance": {
|
|
55202
|
+
"country_code": "GB",
|
|
55203
|
+
"country_name": "United Kingdom",
|
|
55204
|
+
"region": "Cornwall",
|
|
55205
|
+
"city": null,
|
|
55206
|
+
"recorded_by": null,
|
|
55207
|
+
"recording_date": null
|
|
55208
|
+
},
|
|
55209
|
+
"transcription": {
|
|
55210
|
+
"has_subtitles": false,
|
|
55211
|
+
"available_subtitles": [],
|
|
55212
|
+
"native_text": null,
|
|
55213
|
+
"english_translation": null
|
|
55214
|
+
},
|
|
55215
|
+
"raw_metadata": {
|
|
55216
|
+
"title": "Elizabeth speaking Cornish",
|
|
55217
|
+
"tags": [
|
|
55218
|
+
"Wikitongues"
|
|
55219
|
+
]
|
|
55220
|
+
}
|
|
55221
|
+
},
|
|
55222
|
+
{
|
|
55223
|
+
"id": "TO0jkeuirFA",
|
|
55224
|
+
"url": "https://www.youtube.com/watch?v=TO0jkeuirFA",
|
|
55225
|
+
"duration_seconds": 26,
|
|
55226
|
+
"upload_date": "2026-09-21",
|
|
55227
|
+
"license": "ALL_RIGHTS_RESERVED",
|
|
55228
|
+
"content_type": "oral_history",
|
|
55229
|
+
"primary_language": {
|
|
55230
|
+
"standards": {
|
|
55231
|
+
"iso639_3": "zul",
|
|
55232
|
+
"glottocode": "zulu1248",
|
|
55233
|
+
"bcp47": "zu"
|
|
55234
|
+
},
|
|
55235
|
+
"speaker_claim": null,
|
|
55236
|
+
"wikitongues_classification": "Zulu",
|
|
55237
|
+
"wikitongues_lineage": null,
|
|
55238
|
+
"autonym": "isiZulu"
|
|
55239
|
+
},
|
|
55240
|
+
"additional_languages": [],
|
|
55241
|
+
"speakers": [
|
|
55242
|
+
{
|
|
55243
|
+
"name": "Lolly",
|
|
55244
|
+
"role": "native",
|
|
55245
|
+
"origin": "South Africa"
|
|
55246
|
+
}
|
|
55247
|
+
],
|
|
55248
|
+
"provenance": {
|
|
55249
|
+
"country_code": "ZA",
|
|
55250
|
+
"country_name": "South Africa",
|
|
55251
|
+
"region": null,
|
|
55252
|
+
"city": null,
|
|
55253
|
+
"recorded_by": null,
|
|
55254
|
+
"recording_date": null
|
|
55255
|
+
},
|
|
55256
|
+
"transcription": {
|
|
55257
|
+
"has_subtitles": false,
|
|
55258
|
+
"available_subtitles": [],
|
|
55259
|
+
"native_text": null,
|
|
55260
|
+
"english_translation": null
|
|
55261
|
+
},
|
|
55262
|
+
"raw_metadata": {
|
|
55263
|
+
"title": "Lolly speaking Zulu",
|
|
55264
|
+
"tags": [
|
|
55265
|
+
"Wikitongues"
|
|
55266
|
+
]
|
|
55267
|
+
}
|
|
55127
55268
|
}
|
|
55128
55269
|
]
|
|
@@ -907,3 +907,6 @@
|
|
|
907
907
|
{"id":"gE11A0fmkR0","url":"https://www.youtube.com/watch?v=gE11A0fmkR0","duration_seconds":21,"upload_date":"2019-08-30","license":"CC-BY-SA-4.0","content_type":"oral_history","primary_language":{"standards":{"iso639_3":"alt","glottocode":"sout2694","bcp47":"alt"},"speaker_claim":null,"wikitongues_classification":"Altai","wikitongues_lineage":null,"autonym":"Алтай тил"},"additional_languages":[],"speakers":[{"name":"Dmitry","role":"native","origin":"Russia"}],"provenance":{"country_code":"RU","country_name":"Russia","region":"Altai Republic","city":null,"recorded_by":"Archyn Termishev","recording_date":null},"transcription":{"has_subtitles":false,"available_subtitles":[],"native_text":null,"english_translation":null},"raw_metadata":{"title":"WIKITONGUES: Dmitry speaking Altai","tags":["Wikitongues","IYIL2019","2019 International Year of Indigenous Languages"]}}
|
|
908
908
|
{"id":"TotFWZLrQAY","url":"https://www.youtube.com/watch?v=TotFWZLrQAY","duration_seconds":55,"upload_date":"2014-08-07","license":"ALL_RIGHTS_RESERVED","content_type":"oral_history","primary_language":{"standards":{"iso639_3":"epo","glottocode":"espe1235","bcp47":"eo"},"speaker_claim":null,"wikitongues_classification":"Esperanto","wikitongues_lineage":null,"autonym":"Esperanto"},"additional_languages":[],"speakers":[{"name":"Hilliard (Hiljardo)","role":"second_language","origin":"United States"}],"provenance":{"country_code":"US","country_name":"United States","region":"Connecticut","city":null,"recorded_by":null,"recording_date":null},"transcription":{"has_subtitles":false,"available_subtitles":[],"native_text":"Saluton. Mia nomo estas Hiljardo, en Esperanto, kaj mi parolis Esperanton dum du monatoj. Mi havas dek kvar de jaroj. Mi lernis Esperanton por lerni pri aliaj kulturoj kaj aliaj popoloj. Esperanto helpas min multe. Mi ofte konversacias kun homoj de la mondo. Mi loĝas en Konektikuto en Usono. Mi amas lerni pri lingvoj kaj historio. Mi ankaŭ parolas anglan lingvon, francan lingvon, rusan lingvon, nederlandan lingvon, kaj afrikanson. Mi amas lerni novajn lingvojn , ĉar ĝi estas sana, kaj ĝi estas bona ekzerco por la cerbo. Dankon por rigardi.","english_translation":"Hi. Mi name is \"Hiljardo\" [Hilliard], in Esperanto, and I have spoken Esperanto for two months. I am fourteen years old. I learned Esperanto to learn about foreign cultures and foreign peoples. Esperanto helps me a lot. I often converse with people from the world. I live in Connecticut in the United States of America. I like to learn about languages and history. I also speak English, French, Russian, Dutch, and Afrikaans. I like to learn new languages, because it is healthy, and it is a good exercise for the brain. Thanks for watching."},"raw_metadata":{"title":"WIKITONGUES: Hiljiardo speaking Esperanto","tags":["Wikitongues","Esperanto Language (Human Language)"]}}
|
|
909
909
|
{"id":"--DnU743JLU","url":"https://www.youtube.com/watch?v=--DnU743JLU","duration_seconds":40,"upload_date":"2013-02-18","license":"ALL_RIGHTS_RESERVED","content_type":"oral_history","primary_language":{"standards":{"iso639_3":"nan","glottocode":"minn1241","bcp47":"nan-TW"},"speaker_claim":null,"wikitongues_classification":"Taiwanese Min Nan","wikitongues_lineage":null,"autonym":"臺灣話"},"additional_languages":[],"speakers":[{"name":"Liang Cheng Chia (Sunny)","role":"native","origin":"Taiwan"}],"provenance":{"country_code":"TW","country_name":"Taiwan","region":null,"city":"Kaohsiung","recorded_by":null,"recording_date":null},"transcription":{"has_subtitles":false,"available_subtitles":[],"native_text":null,"english_translation":null},"raw_metadata":{"title":"WIKITONGUES: Sunny speaking Taiwanese Min Nan","tags":["Taiwanese","Hokkien","Taiwan","nation","country","Vietnam","USA","languages of Taiwan","Min Nan","Chinese"]}}
|
|
910
|
+
{"id":"yoEbTFxNrhE","url":"https://www.youtube.com/watch?v=yoEbTFxNrhE","duration_seconds":22,"upload_date":"2026-09-25","license":"ALL_RIGHTS_RESERVED","content_type":"oral_history","primary_language":{"standards":{"iso639_3":"cor","glottocode":"corn1251","bcp47":"kw"},"speaker_claim":null,"wikitongues_classification":"Cornish","wikitongues_lineage":null,"autonym":"Kernewek"},"additional_languages":[],"speakers":[{"name":"Elizabeth","role":"native","origin":"United Kingdom"}],"provenance":{"country_code":"GB","country_name":"United Kingdom","region":"Cornwall","city":null,"recorded_by":null,"recording_date":null},"transcription":{"has_subtitles":false,"available_subtitles":[],"native_text":null,"english_translation":null},"raw_metadata":{"title":"Elizabeth speaking Cornish","tags":["Wikitongues"]}}
|
|
911
|
+
{"id":"bEVt0Tp6ZEA","url":"https://www.youtube.com/watch?v=bEVt0Tp6ZEA","duration_seconds":31,"upload_date":"2026-09-23","license":"ALL_RIGHTS_RESERVED","content_type":"oral_history","primary_language":{"standards":{"iso639_3":"cor","glottocode":"corn1251","bcp47":"kw"},"speaker_claim":null,"wikitongues_classification":"Cornish","wikitongues_lineage":null,"autonym":"Kernewek"},"additional_languages":[],"speakers":[{"name":"Elizabeth","role":"native","origin":"United Kingdom"}],"provenance":{"country_code":"GB","country_name":"United Kingdom","region":"Cornwall","city":null,"recorded_by":null,"recording_date":null},"transcription":{"has_subtitles":false,"available_subtitles":[],"native_text":null,"english_translation":null},"raw_metadata":{"title":"Elizabeth speaking Cornish","tags":["Wikitongues"]}}
|
|
912
|
+
{"id":"TO0jkeuirFA","url":"https://www.youtube.com/watch?v=TO0jkeuirFA","duration_seconds":26,"upload_date":"2026-09-21","license":"ALL_RIGHTS_RESERVED","content_type":"oral_history","primary_language":{"standards":{"iso639_3":"zul","glottocode":"zulu1248","bcp47":"zu"},"speaker_claim":null,"wikitongues_classification":"Zulu","wikitongues_lineage":null,"autonym":"isiZulu"},"additional_languages":[],"speakers":[{"name":"Lolly","role":"native","origin":"South Africa"}],"provenance":{"country_code":"ZA","country_name":"South Africa","region":null,"city":null,"recorded_by":null,"recording_date":null},"transcription":{"has_subtitles":false,"available_subtitles":[],"native_text":null,"english_translation":null},"raw_metadata":{"title":"Lolly speaking Zulu","tags":["Wikitongues"]}}
|
package/dist/dataset.js
CHANGED
|
@@ -55202,6 +55202,147 @@ Best wishes to everybody at home, and I'm looking forward to be surrounded by re
|
|
|
55202
55202
|
"Chinese"
|
|
55203
55203
|
]
|
|
55204
55204
|
}
|
|
55205
|
+
},
|
|
55206
|
+
{
|
|
55207
|
+
id: "yoEbTFxNrhE",
|
|
55208
|
+
url: "https://www.youtube.com/watch?v=yoEbTFxNrhE",
|
|
55209
|
+
duration_seconds: 22,
|
|
55210
|
+
upload_date: "2026-09-25",
|
|
55211
|
+
license: "ALL_RIGHTS_RESERVED",
|
|
55212
|
+
content_type: "oral_history",
|
|
55213
|
+
primary_language: {
|
|
55214
|
+
standards: {
|
|
55215
|
+
iso639_3: "cor",
|
|
55216
|
+
glottocode: "corn1251",
|
|
55217
|
+
bcp47: "kw"
|
|
55218
|
+
},
|
|
55219
|
+
speaker_claim: null,
|
|
55220
|
+
wikitongues_classification: "Cornish",
|
|
55221
|
+
wikitongues_lineage: null,
|
|
55222
|
+
autonym: "Kernewek"
|
|
55223
|
+
},
|
|
55224
|
+
additional_languages: [],
|
|
55225
|
+
speakers: [
|
|
55226
|
+
{
|
|
55227
|
+
name: "Elizabeth",
|
|
55228
|
+
role: "native",
|
|
55229
|
+
origin: "United Kingdom"
|
|
55230
|
+
}
|
|
55231
|
+
],
|
|
55232
|
+
provenance: {
|
|
55233
|
+
country_code: "GB",
|
|
55234
|
+
country_name: "United Kingdom",
|
|
55235
|
+
region: "Cornwall",
|
|
55236
|
+
city: null,
|
|
55237
|
+
recorded_by: null,
|
|
55238
|
+
recording_date: null
|
|
55239
|
+
},
|
|
55240
|
+
transcription: {
|
|
55241
|
+
has_subtitles: false,
|
|
55242
|
+
available_subtitles: [],
|
|
55243
|
+
native_text: null,
|
|
55244
|
+
english_translation: null
|
|
55245
|
+
},
|
|
55246
|
+
raw_metadata: {
|
|
55247
|
+
title: "Elizabeth speaking Cornish",
|
|
55248
|
+
tags: [
|
|
55249
|
+
"Wikitongues"
|
|
55250
|
+
]
|
|
55251
|
+
}
|
|
55252
|
+
},
|
|
55253
|
+
{
|
|
55254
|
+
id: "bEVt0Tp6ZEA",
|
|
55255
|
+
url: "https://www.youtube.com/watch?v=bEVt0Tp6ZEA",
|
|
55256
|
+
duration_seconds: 31,
|
|
55257
|
+
upload_date: "2026-09-23",
|
|
55258
|
+
license: "ALL_RIGHTS_RESERVED",
|
|
55259
|
+
content_type: "oral_history",
|
|
55260
|
+
primary_language: {
|
|
55261
|
+
standards: {
|
|
55262
|
+
iso639_3: "cor",
|
|
55263
|
+
glottocode: "corn1251",
|
|
55264
|
+
bcp47: "kw"
|
|
55265
|
+
},
|
|
55266
|
+
speaker_claim: null,
|
|
55267
|
+
wikitongues_classification: "Cornish",
|
|
55268
|
+
wikitongues_lineage: null,
|
|
55269
|
+
autonym: "Kernewek"
|
|
55270
|
+
},
|
|
55271
|
+
additional_languages: [],
|
|
55272
|
+
speakers: [
|
|
55273
|
+
{
|
|
55274
|
+
name: "Elizabeth",
|
|
55275
|
+
role: "native",
|
|
55276
|
+
origin: "United Kingdom"
|
|
55277
|
+
}
|
|
55278
|
+
],
|
|
55279
|
+
provenance: {
|
|
55280
|
+
country_code: "GB",
|
|
55281
|
+
country_name: "United Kingdom",
|
|
55282
|
+
region: "Cornwall",
|
|
55283
|
+
city: null,
|
|
55284
|
+
recorded_by: null,
|
|
55285
|
+
recording_date: null
|
|
55286
|
+
},
|
|
55287
|
+
transcription: {
|
|
55288
|
+
has_subtitles: false,
|
|
55289
|
+
available_subtitles: [],
|
|
55290
|
+
native_text: null,
|
|
55291
|
+
english_translation: null
|
|
55292
|
+
},
|
|
55293
|
+
raw_metadata: {
|
|
55294
|
+
title: "Elizabeth speaking Cornish",
|
|
55295
|
+
tags: [
|
|
55296
|
+
"Wikitongues"
|
|
55297
|
+
]
|
|
55298
|
+
}
|
|
55299
|
+
},
|
|
55300
|
+
{
|
|
55301
|
+
id: "TO0jkeuirFA",
|
|
55302
|
+
url: "https://www.youtube.com/watch?v=TO0jkeuirFA",
|
|
55303
|
+
duration_seconds: 26,
|
|
55304
|
+
upload_date: "2026-09-21",
|
|
55305
|
+
license: "ALL_RIGHTS_RESERVED",
|
|
55306
|
+
content_type: "oral_history",
|
|
55307
|
+
primary_language: {
|
|
55308
|
+
standards: {
|
|
55309
|
+
iso639_3: "zul",
|
|
55310
|
+
glottocode: "zulu1248",
|
|
55311
|
+
bcp47: "zu"
|
|
55312
|
+
},
|
|
55313
|
+
speaker_claim: null,
|
|
55314
|
+
wikitongues_classification: "Zulu",
|
|
55315
|
+
wikitongues_lineage: null,
|
|
55316
|
+
autonym: "isiZulu"
|
|
55317
|
+
},
|
|
55318
|
+
additional_languages: [],
|
|
55319
|
+
speakers: [
|
|
55320
|
+
{
|
|
55321
|
+
name: "Lolly",
|
|
55322
|
+
role: "native",
|
|
55323
|
+
origin: "South Africa"
|
|
55324
|
+
}
|
|
55325
|
+
],
|
|
55326
|
+
provenance: {
|
|
55327
|
+
country_code: "ZA",
|
|
55328
|
+
country_name: "South Africa",
|
|
55329
|
+
region: null,
|
|
55330
|
+
city: null,
|
|
55331
|
+
recorded_by: null,
|
|
55332
|
+
recording_date: null
|
|
55333
|
+
},
|
|
55334
|
+
transcription: {
|
|
55335
|
+
has_subtitles: false,
|
|
55336
|
+
available_subtitles: [],
|
|
55337
|
+
native_text: null,
|
|
55338
|
+
english_translation: null
|
|
55339
|
+
},
|
|
55340
|
+
raw_metadata: {
|
|
55341
|
+
title: "Lolly speaking Zulu",
|
|
55342
|
+
tags: [
|
|
55343
|
+
"Wikitongues"
|
|
55344
|
+
]
|
|
55345
|
+
}
|
|
55205
55346
|
}
|
|
55206
55347
|
];
|
|
55207
55348
|
|