Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
dcc:itsol:whisper:datamanage [2026/09/24 12:26] – New Whisper Guide camarocicodcc:itsol:whisper:datamanage [2026/09/25 10:26] (current) – alba
Line 16: Line 16:
 Once all three are downloaded and cleared, you are ready for a new round of transcriptions. Once all three are downloaded and cleared, you are ready for a new round of transcriptions.
  
-===== The Recordings =====+===== The recordings =====
  
-Check the transcripts before you delete the audio. If a job has to be run again — because the wrong language was detected, for example — having the recordings still on Hábrók saves you uploading them a second time. A quick check that the transcription succeeded is enough; the detailed reading can happen in your own work environment.+Check the transcripts before you delete the audio. If a job has to be run again — because the wrong language was detected, for example — having the recordings still on Hábrók saves you from uploading them a second time. A quick check that the transcription succeeded is enough; the detailed reading can happen in your own work environment.
  
 Once the transcripts are what you expect, remove the recordings promptly. Leaving transcribed audio on the cluster serves no purpose and increases the risk of a data leak. Once the transcripts are what you expect, remove the recordings promptly. Leaving transcribed audio on the cluster serves no purpose and increases the risk of a data leak.
  
-===== The Transcripts =====+===== The transcripts =====
  
 Download everything you need from ''%%whisper/output/%%'' and then empty it. The output files can be removed at any time, but clear them before starting a new job so that one run's results are never mistaken for another's. Download everything you need from ''%%whisper/output/%%'' and then empty it. The output files can be removed at any time, but clear them before starting a new job so that one run's results are never mistaken for another's.
  
-===== The Job Log =====+===== The job log =====
  
 The job log sits next to the job script, in the ''%%whisper/%%'' directory rather than in the output directory, and is named after the job: ''%%slurm-<JobID>.out%%''. The job log sits next to the job script, in the ''%%whisper/%%'' directory rather than in the output directory, and is named after the job: ''%%slurm-<JobID>.out%%''.