Speech with word timestamps, 5 minutes

Input

The input this example runs Audio & Video Transcriber with. “Try this input” opens it in the console, where you can run it as-is or change any field first.

Media files, podcast feeds or pagesurls

https://upload.wikimedia.org/wikipedia/commons/7/7c/Marcus_Garvey%2C_speech%2C_1921.ogg

Episodes per podcast feedmaxEpisodesPerFeed

1

Speech modelmodel

Small (most accurate)

Spoken languagelanguage

English

Translate to EnglishtranslateToEnglish

No

Word timestampswordTimestamps

Yes

Skip silence and musicskipSilence

Yes

Beam sizebeamSize

1

Max minutes per filemaxMinutesPerFile

5

Timestamped segmentsincludeSegments

Yes

Save SRT, VTT and TXT filessaveSubtitleFiles

Yes

SRT and VTT text in the rowsubtitlesInDataset

Yes

Max file size (MB)maxFileSizeMb

1024

{
  "urls": [
    "https://upload.wikimedia.org/wikipedia/commons/7/7c/Marcus_Garvey%2C_speech%2C_1921.ogg"
  ],
  "model": "small",
  "language": "English",
  "wordTimestamps": true,
  "subtitlesInDataset": true,
  "maxEpisodesPerFeed": 1,
  "translateToEnglish": false,
  "skipSilence": true,
  "beamSize": 1,
  "maxMinutesPerFile": 5,
  "includeSegments": true,
  "saveSubtitleFiles": true,
  "maxFileSizeMb": 1024
}