Differences

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

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
vrw:installedfunctionality:whisper [2026/04/09 10:11] margueritevrw:installedfunctionality:whisper [2026/04/16 13:44] (current) marguerite
Line 13: Line 13:
 ==== Prepare the environment ==== ==== Prepare the environment ====
  
-  * Make sure that de source file that you want to transcribe is in your home drive H: and not in a sub folder. This is because spaces are not allowed in the command line.+  * Make sure that the source file that you want to transcribe is in your home drive H: and not in a sub folder. This is because spaces are not allowed in the command line.
   * Create a folder for the output in your home folder H:\, for instance H:\output_Whisper   * Create a folder for the output in your home folder H:\, for instance H:\output_Whisper
   * Open Notepad or a text editor and create the command line so you can easily paste the whole command with all the components (source file, model and output folder) in the command line of Whisper.   * Open Notepad or a text editor and create the command line so you can easily paste the whole command with all the components (source file, model and output folder) in the command line of Whisper.
  
 The general structure of the command is: The general structure of the command is:
-''whisper [source file] --[model to be used]--output_dir [directory for the output]''+<code> 
 +whisper [source file] --[model to be used]--output_dir [directory for the output]
 The used model is always the language model at \\hsr\aps\ServerBased\Whisper\LanguageModelfiles.  The used model is always the language model at \\hsr\aps\ServerBased\Whisper\LanguageModelfiles. 
 +</code>
  
-An example or the command: +An example of the command: 
- +<code> 
-whisper H:\opnameAIworkshop.mp3 --model_dir \\hsr\aps\ServerBased\Whisper\LanguageModelfiles --output_dir H:\Whisper_output\+whisper H:\opnameAIworkshop.mp3 --model_dir \\hsr\aps\ServerBased\Whisper\LanguageModelfiles --output_dir H:\output_Whisper\ 
 +</code>
  
 ==== Make the transcription ==== ==== Make the transcription ====
Line 29: Line 32:
 Start Whisper Start Whisper
 Open the Windows menu and type Whisper cmd. you will find Whisper - CMD Open the Windows menu and type Whisper cmd. you will find Whisper - CMD
 +
 +
 {{ :vrw:installedfunctionality:whisper1.png?nolink&400 |}} {{ :vrw:installedfunctionality:whisper1.png?nolink&400 |}}
  
Line 34: Line 39:
 Paste the command you created in the text editor after the prompt and press ENTER.It will take a while for Whisper to start but after that and some output on a module the transcription will be shown on the screen.  Paste the command you created in the text editor after the prompt and press ENTER.It will take a while for Whisper to start but after that and some output on a module the transcription will be shown on the screen. 
 That output will also be written to the output folder you defined. That output will also be written to the output folder you defined.
-{{ :vrw:installedfunctionality:whisper2.png?direct&600 |}} 
  
  
-Please refer to the manual of our DCC colleagues on [[https://wiki.hpc.rug.nl/dcc/itsol/whisper|running Whisper on HPC]].+{{ :vrw:installedfunctionality:whisper2.png?direct&600 |}}