Files
docling/tests/data/groundtruth/docling_v2/webvtt_example_03.vtt.json
Cesar Berrospi Ramis 46efaaefee feat: add a backend parser for WebVTT files (#2288)
* feat: add a backend parser for WebVTT files

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* docs: update README with VTT support

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* docs: add description to supported formats

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* chore: upgrade docling-core to unescape WebVTT in markdown

Pin the new release of docling-core 2.48.2.
Do not escape HTML reserved characters when exporting WebVTT documents to markdown.

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* test: add missing copyright notice

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

---------

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
2025-09-22 15:24:34 +02:00

1240 lines
26 KiB
JSON
Vendored

{
"schema_name": "DoclingDocument",
"version": "1.6.0",
"name": "webvtt_example_03",
"origin": {
"mimetype": "text/vtt",
"binary_hash": 11620880316586573676,
"filename": "webvtt_example_03.vtt"
},
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
"body": {
"self_ref": "#/body",
"children": [
{
"$ref": "#/groups/0"
},
{
"$ref": "#/groups/2"
},
{
"$ref": "#/groups/4"
},
{
"$ref": "#/groups/5"
},
{
"$ref": "#/groups/7"
},
{
"$ref": "#/groups/9"
},
{
"$ref": "#/groups/11"
},
{
"$ref": "#/groups/13"
},
{
"$ref": "#/groups/15"
},
{
"$ref": "#/groups/17"
},
{
"$ref": "#/groups/19"
},
{
"$ref": "#/groups/21"
},
{
"$ref": "#/groups/23"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
"groups": [
{
"self_ref": "#/groups/0",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/0"
},
{
"$ref": "#/texts/1"
},
{
"$ref": "#/groups/1"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/1",
"parent": {
"$ref": "#/groups/0"
},
"children": [
{
"$ref": "#/texts/2"
},
{
"$ref": "#/texts/3"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
},
{
"self_ref": "#/groups/2",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/4"
},
{
"$ref": "#/texts/5"
},
{
"$ref": "#/groups/3"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/3",
"parent": {
"$ref": "#/groups/2"
},
"children": [
{
"$ref": "#/texts/6"
},
{
"$ref": "#/texts/7"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
},
{
"self_ref": "#/groups/4",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/8"
},
{
"$ref": "#/texts/9"
},
{
"$ref": "#/texts/10"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/5",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/11"
},
{
"$ref": "#/texts/12"
},
{
"$ref": "#/groups/6"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/6",
"parent": {
"$ref": "#/groups/5"
},
"children": [
{
"$ref": "#/texts/13"
},
{
"$ref": "#/texts/14"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
},
{
"self_ref": "#/groups/7",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/15"
},
{
"$ref": "#/texts/16"
},
{
"$ref": "#/groups/8"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/8",
"parent": {
"$ref": "#/groups/7"
},
"children": [
{
"$ref": "#/texts/17"
},
{
"$ref": "#/texts/18"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
},
{
"self_ref": "#/groups/9",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/19"
},
{
"$ref": "#/texts/20"
},
{
"$ref": "#/groups/10"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/10",
"parent": {
"$ref": "#/groups/9"
},
"children": [
{
"$ref": "#/texts/21"
},
{
"$ref": "#/texts/22"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
},
{
"self_ref": "#/groups/11",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/23"
},
{
"$ref": "#/texts/24"
},
{
"$ref": "#/groups/12"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/12",
"parent": {
"$ref": "#/groups/11"
},
"children": [
{
"$ref": "#/texts/25"
},
{
"$ref": "#/texts/26"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
},
{
"self_ref": "#/groups/13",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/27"
},
{
"$ref": "#/texts/28"
},
{
"$ref": "#/groups/14"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/14",
"parent": {
"$ref": "#/groups/13"
},
"children": [
{
"$ref": "#/texts/29"
},
{
"$ref": "#/texts/30"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
},
{
"self_ref": "#/groups/15",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/31"
},
{
"$ref": "#/texts/32"
},
{
"$ref": "#/groups/16"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/16",
"parent": {
"$ref": "#/groups/15"
},
"children": [
{
"$ref": "#/texts/33"
},
{
"$ref": "#/texts/34"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
},
{
"self_ref": "#/groups/17",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/35"
},
{
"$ref": "#/texts/36"
},
{
"$ref": "#/groups/18"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/18",
"parent": {
"$ref": "#/groups/17"
},
"children": [
{
"$ref": "#/texts/37"
},
{
"$ref": "#/texts/38"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
},
{
"self_ref": "#/groups/19",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/39"
},
{
"$ref": "#/texts/40"
},
{
"$ref": "#/groups/20"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/20",
"parent": {
"$ref": "#/groups/19"
},
"children": [
{
"$ref": "#/texts/41"
},
{
"$ref": "#/texts/42"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
},
{
"self_ref": "#/groups/21",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/43"
},
{
"$ref": "#/texts/44"
},
{
"$ref": "#/groups/22"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/22",
"parent": {
"$ref": "#/groups/21"
},
"children": [
{
"$ref": "#/texts/45"
},
{
"$ref": "#/texts/46"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
},
{
"self_ref": "#/groups/23",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/47"
},
{
"$ref": "#/texts/48"
},
{
"$ref": "#/groups/24"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/24",
"parent": {
"$ref": "#/groups/23"
},
"children": [
{
"$ref": "#/texts/49"
},
{
"$ref": "#/texts/50"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
}
],
"texts": [
{
"self_ref": "#/texts/0",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/15-0",
"text": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/15-0"
},
{
"self_ref": "#/texts/1",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:00:04.963 --> 00:00:08.571",
"text": "00:00:04.963 --> 00:00:08.571"
},
{
"self_ref": "#/texts/2",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Speaker A: ",
"text": "Speaker A: "
},
{
"self_ref": "#/texts/3",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "OK, I think now we should be recording",
"text": "OK, I think now we should be recording",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/4",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/15-1",
"text": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/15-1"
},
{
"self_ref": "#/texts/5",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:00:08.571 --> 00:00:09.403",
"text": "00:00:08.571 --> 00:00:09.403"
},
{
"self_ref": "#/texts/6",
"parent": {
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Speaker A: ",
"text": "Speaker A: "
},
{
"self_ref": "#/texts/7",
"parent": {
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "properly.",
"text": "properly.",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/8",
"parent": {
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/16-0",
"text": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/16-0"
},
{
"self_ref": "#/texts/9",
"parent": {
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:00:10.683 --> 00:00:11.563",
"text": "00:00:10.683 --> 00:00:11.563"
},
{
"self_ref": "#/texts/10",
"parent": {
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Good.",
"text": "Good.",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/11",
"parent": {
"$ref": "#/groups/5"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/17-0",
"text": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/17-0"
},
{
"self_ref": "#/texts/12",
"parent": {
"$ref": "#/groups/5"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:00:13.363 --> 00:00:13.803",
"text": "00:00:13.363 --> 00:00:13.803"
},
{
"self_ref": "#/texts/13",
"parent": {
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Speaker A: ",
"text": "Speaker A: "
},
{
"self_ref": "#/texts/14",
"parent": {
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Yeah.",
"text": "Yeah.",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/15",
"parent": {
"$ref": "#/groups/7"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/78-0",
"text": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/78-0"
},
{
"self_ref": "#/texts/16",
"parent": {
"$ref": "#/groups/7"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:00:49.603 --> 00:00:53.363",
"text": "00:00:49.603 --> 00:00:53.363"
},
{
"self_ref": "#/texts/17",
"parent": {
"$ref": "#/groups/8"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Speaker B: ",
"text": "Speaker B: "
},
{
"self_ref": "#/texts/18",
"parent": {
"$ref": "#/groups/8"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "I was also thinking.",
"text": "I was also thinking.",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/19",
"parent": {
"$ref": "#/groups/9"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/113-0",
"text": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/113-0"
},
{
"self_ref": "#/texts/20",
"parent": {
"$ref": "#/groups/9"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:00:54.963 --> 00:01:02.072",
"text": "00:00:54.963 --> 00:01:02.072"
},
{
"self_ref": "#/texts/21",
"parent": {
"$ref": "#/groups/10"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Speaker B: ",
"text": "Speaker B: "
},
{
"self_ref": "#/texts/22",
"parent": {
"$ref": "#/groups/10"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Would be maybe good to create items,",
"text": "Would be maybe good to create items,",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/23",
"parent": {
"$ref": "#/groups/11"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/113-1",
"text": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/113-1"
},
{
"self_ref": "#/texts/24",
"parent": {
"$ref": "#/groups/11"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:01:02.072 --> 00:01:06.811",
"text": "00:01:02.072 --> 00:01:06.811"
},
{
"self_ref": "#/texts/25",
"parent": {
"$ref": "#/groups/12"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Speaker B: ",
"text": "Speaker B: "
},
{
"self_ref": "#/texts/26",
"parent": {
"$ref": "#/groups/12"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "some metadata, some options that can be specific.",
"text": "some metadata, some options that can be specific.",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/27",
"parent": {
"$ref": "#/groups/13"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/150-0",
"text": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/150-0"
},
{
"self_ref": "#/texts/28",
"parent": {
"$ref": "#/groups/13"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:01:10.243 --> 00:01:13.014",
"text": "00:01:10.243 --> 00:01:13.014"
},
{
"self_ref": "#/texts/29",
"parent": {
"$ref": "#/groups/14"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Speaker A: ",
"text": "Speaker A: "
},
{
"self_ref": "#/texts/30",
"parent": {
"$ref": "#/groups/14"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Yeah, I mean I think you went even more than",
"text": "Yeah, I mean I think you went even more than",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/31",
"parent": {
"$ref": "#/groups/15"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/119-0",
"text": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/119-0"
},
{
"self_ref": "#/texts/32",
"parent": {
"$ref": "#/groups/15"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:01:10.563 --> 00:01:12.643",
"text": "00:01:10.563 --> 00:01:12.643"
},
{
"self_ref": "#/texts/33",
"parent": {
"$ref": "#/groups/16"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Speaker B: ",
"text": "Speaker B: "
},
{
"self_ref": "#/texts/34",
"parent": {
"$ref": "#/groups/16"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "But we preserved the atoms.",
"text": "But we preserved the atoms.",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/35",
"parent": {
"$ref": "#/groups/17"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/150-1",
"text": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/150-1"
},
{
"self_ref": "#/texts/36",
"parent": {
"$ref": "#/groups/17"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:01:13.014 --> 00:01:15.907",
"text": "00:01:13.014 --> 00:01:15.907"
},
{
"self_ref": "#/texts/37",
"parent": {
"$ref": "#/groups/18"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Speaker A: ",
"text": "Speaker A: "
},
{
"self_ref": "#/texts/38",
"parent": {
"$ref": "#/groups/18"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "than me. I just opened the format.",
"text": "than me. I just opened the format.",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/39",
"parent": {
"$ref": "#/groups/19"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/197-1",
"text": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/197-1"
},
{
"self_ref": "#/texts/40",
"parent": {
"$ref": "#/groups/19"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:01:50.222 --> 00:01:51.643",
"text": "00:01:50.222 --> 00:01:51.643"
},
{
"self_ref": "#/texts/41",
"parent": {
"$ref": "#/groups/20"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Speaker A: ",
"text": "Speaker A: "
},
{
"self_ref": "#/texts/42",
"parent": {
"$ref": "#/groups/20"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "give it a try, yeah.",
"text": "give it a try, yeah.",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/43",
"parent": {
"$ref": "#/groups/21"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/200-0",
"text": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/200-0"
},
{
"self_ref": "#/texts/44",
"parent": {
"$ref": "#/groups/21"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:01:52.043 --> 00:01:55.043",
"text": "00:01:52.043 --> 00:01:55.043"
},
{
"self_ref": "#/texts/45",
"parent": {
"$ref": "#/groups/22"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Speaker B: ",
"text": "Speaker B: "
},
{
"self_ref": "#/texts/46",
"parent": {
"$ref": "#/groups/22"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Okay, talk to you later.",
"text": "Okay, talk to you later.",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/47",
"parent": {
"$ref": "#/groups/23"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/202-0",
"text": "62357a1d-d250-41d5-a1cf-6cc0eeceffcc/202-0"
},
{
"self_ref": "#/texts/48",
"parent": {
"$ref": "#/groups/23"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:01:54.603 --> 00:01:55.283",
"text": "00:01:54.603 --> 00:01:55.283"
},
{
"self_ref": "#/texts/49",
"parent": {
"$ref": "#/groups/24"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Speaker A: ",
"text": "Speaker A: "
},
{
"self_ref": "#/texts/50",
"parent": {
"$ref": "#/groups/24"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "See you.",
"text": "See you.",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
}
],
"pictures": [],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}