Differences

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

--- dcc:itsol:whisper [2025/02/21 09:39] – fixed order after introducing remote access page giulio
+++ dcc:itsol:whisper [2026/09/25 10:27] (current) – alba
@@ Line 1: / Line 1: @@
 {{indexmenu_n>5}}
 ====== Whisper Guide ======
 ===== Attention! =====
-**The use of Whisper is currently being piloted by the DCC. We are trying to build a highly secure environment for you to safely use this A.I. based tool. We kindly ask for your patience while we set this up for you.**
+<WRAP round important>
-**If you are interested in using this tool and you are not already in contact with the DCC, please feel free to send us a message at [[dcc@rug.nl|dcc@rug.nl]]. We will put you on our waiting list and will contact you as soon as the pilot is over. Once the pilot is complete, we will make the tool available on demand.**
+The use of Whisper is at the user's own responsibility. The setup illustrated in this guide uses a locally run instance of Whisper that does not send data outside the local environment. **Please make sure to handle your data correctly.** If you have any doubts about how to do so, start by following the steps in [[dcc:itsol:whisper:datamanage|Data management safety measures]].
+If you have any questions on Whisper that this guide does not answer, send us a message at <dcc@rug.nl>.
+</WRAP>
 ===== Introduction =====
-This guide takes you through the steps to set up a personal system of speech-to-text transcription on University of Groningen infrastructure (for UG staff and students) on the basis of the [[https://openai.com/research/whisper|OpenAI Whisper automatic speech recognition (ASR) model]] running on the [[https://iris.service.rug.nl/tas/public/ssp/content/detail/service?unid=0d51dd1aa44f4cdcb4949f1702d1829f|Hábrók High Performance Computing]] (HPC) cluster.
+This guide takes you through the steps to set up a series of folders and a script to run speech-to-text transcription on the University of Groningen infrastructure (for UG staff and students) based on the [[https://openai.com/research/whisper|OpenAI Whisper automatic speech recognition (ASR) model]] running on the [[https://iris.service.rug.nl/tas/public/ssp/content/detail/service?unid=0d51dd1aa44f4cdcb4949f1702d1829f|Hábrók High Performance Computing]] (HPC) cluster.
+The process of transcribing spoken audio to text is usually a very time-consuming manual process. The UG offers a licensed version of [[https://www.audiotranskription.de/en/f4transkript/|F4 Transkript]] on the University Workplace as an aid for manual transcription, but doesn't offer automatic speech recognition software.
+This guide is offered by the DCC to help researchers process their research data as efficiently as possible, while optimizing data protection (keeping their audio files on UG storage instead of sending them to cloud services). The app is the work of three CIT teams: the DCC came up with the concept, the Data Science team developed an early command-line version, and the HPC team builds and maintains the app you run from the portal. If you wish to read more on the detailed functionalities of Whisper, refer to the [[https://github.com/openai/whisper|manual in their Git repository]].
+Should you have any further questions on the use or initial setup of Whisper on Hábrók HPC, contact the DCC at <dcc@rug.nl>.
+===== What Whisper can do =====
+Whisper turns speech in audio and video recordings into text. On Hábrók, it runs as a batch job that you start from the web portal, so you do not need to install anything or use the command line.
+The app can:
+  * transcribe speech in its original language;
+  * translate speech into English;
+  * align the transcript to the audio for more precise timestamps; and
+  * label who is speaking, through optional speaker diarization.
+The output is produced automatically and can contain errors. Check names, numbers, specialist terms, and quotations against the recording before you rely on the result.
+===== How it works =====
+The guide follows four steps, one page each. Each page links on to the next.
+  - [[dcc:itsol:whisper:setup|Before you start]] — request an account, create the input and output directories, and upload your recordings.
+  - [[dcc:itsol:whisper:running|Run a Whisper job]] — open the app, fill in the form, and submit and monitor the job.
+  - [[dcc:itsol:whisper:results|Find and review the results]] — the output files, the job log, and what to check before you rely on a transcript.
+  - [[dcc:itsol:whisper:datamanage|Data management safety measures]] — what to remove from Hábrók once you have your transcripts.
-The process of transcribing spoken audio to text is usually a very time consuming manual process. The UG offers a licensed version of [[https://www.audiotranskription.de/en/f4transkript/|F4 Transkript]] on the University Workplace as an aid for manual transcription, but doesn't offer automatic speech recognition software.
+[[dcc:itsol:whisper:troubleshooting|Troubleshooting]] is there for when a job fails or the output is wrong; it also says where to get help and answers common questions.
-This guide is offered by the DCC to help researchers process their research data as efficiently as possible, while optimizing data protection (keeping their audio files on UG storage instead of sending it to cloud services). For technical aspects, the service is supported by the Data Science and HPC team of the CIT. If you wish to read more on the detailed functionalities of Whisper, please refer to the [[https://github.com/openai/whisper|manual in their Git repository]].
+The clip below shows the whole process, from upload to finished transcript.
-Because audio is highly sensitive data, our advice is to access this tool by requesting a [[https://www.rug.nl/society-business/centre-for-information-technology/research/services/virtual-research-workspace?lang=en|Virtual Research Workspace]] (VRW). To request a VRW capable to access Whisper, please use the form found in the linked webpage and specify that you need transcription capabilities.
+{{ :dcc:itsol:whisper:end_to_end.webm?800x450 |}}
-**N.B.**: As stated above, we are as of now not able to give you access to the tool due to an ongoing pilot. You can still contact us at [[dcc@rug.nl|dcc@rug.nl]] and we will put you on our waiting list. When the pilot is over, we will contact you again to onboard you.
+For your first job, use one short recording. It finishes quickly and lets you check the settings and the output before you commit a whole collection to a run.
-Should you have any further questions on the use or initial set up of Whisper on Hábrók HPC, please contact the DCC at [[dcc@rug.nl|dcc@rug.nl]].
+<WRAP rightalign>[[dcc:itsol:whisper:setup|Next: Before You Start →]]</WRAP>
-[[dcc:itsol:whisper:setup| → Move to the next step]]