jd7h / edit-video-by-editing-text

A pipeline for superfast video editing! Make cuts to a video by editing its transcript.

  • Public
  • 711 runs
  • L40S
  • GitHub
  • License

Input

*file

Video file to transcribe or edit

string

Mode: either transcribe or edit

Default: "transcribe"

string
Shift + Return to add a new line

When using mode 'edit', this should be the transcription of the desired output video. Use mode 'transcribe' to create a starting point.

string

When using mode 'edit', split transcription at the word level or character level. Default: word level. Character level is more precise but can lead to matching errors.

Default: "word"

Output

Generated in

This example was created by a different version, jd7h/edit-video-by-editing-text:5bb1266a.

Run time and cost

This model costs approximately $0.063 to run on Replicate, or 15 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 65 seconds. The predict time for this model varies significantly based on the inputs.

Readme

A pipeline for fast video editing. The pipeline can be used in two modes: transcribe and edit.

  • transcribe: make a transcription of the video. Use this to create the input for ‘edit’ mode.
  • edit: provide the desired transcription of the video as input. The pipeline will cut out the parts of the video that are missing in the transcription.