https://github.com/anouarg88/capsgat
Tool for interviewers to convert common subtitle files to interview transcripts by assigning speakers to segments. Supported import file formats are SRT, TXT, JSON and TSV. Exported interview transcripts based on GAT2 convention.
https://github.com/anouarg88/capsgat
assign captions cleanup gat2 interview qual qualitative research subs subtitles transcribing transcription whisper
Last synced: 3 days ago
JSON representation
Tool for interviewers to convert common subtitle files to interview transcripts by assigning speakers to segments. Supported import file formats are SRT, TXT, JSON and TSV. Exported interview transcripts based on GAT2 convention.
- Host: GitHub
- URL: https://github.com/anouarg88/capsgat
- Owner: anouarg88
- License: gpl-3.0
- Created: 2025-09-29T12:51:28.000Z (6 days ago)
- Default Branch: main
- Last Pushed: 2025-09-29T16:13:24.000Z (5 days ago)
- Last Synced: 2025-09-29T18:25:24.424Z (5 days ago)
- Topics: assign, captions, cleanup, gat2, interview, qual, qualitative, research, subs, subtitles, transcribing, transcription, whisper
- Language: Python
- Homepage:
- Size: 38.1 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# CapsGAT
CapsGAT is a simple tool for interviewers to convert subtitle files (.SRT, .JSON, .TSV, .TXT) to interview transcripts by assigning speakers to segments quickly using keyboard shortcuts.
CapsGAT features basic GAT2-editing functionality such as segment splitting and merging, overlapping speech, pauses and comments.
However, it is not meant as a replacement for professional transcription software (for full-fledged, professional transcription software, check out EXMARaLDA: www.exmaralda.org; importing subtitle files seems to be implemented in newer versions as well), but more as a complementary lightweight tool to be used with transcription AI models such as Whisper AI or CapsWriter.
CapsGAT projects can be loaded or saved. Transcripts can be exported as .HTML or .TXT files, with or without time stamps. With the exception of segments containing unassigned pauses, only segments that have been assigned are included in the transcripts that are exported. The format for interview transcripts is based on the minimal GAT2 transcription convention, though many aspects (such as multiple tiers) are not implemented.
CapsGAT was developed using AI.