You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: content/learning-paths/servers-and-cloud-computing/whisper/_demo.md
+11-5Lines changed: 11 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,14 +1,19 @@
1
1
---
2
2
title: Demo - Audio transcription on Arm
3
3
overview: |
4
-
Insert helpful overview here.
4
+
This Learning Path shows you how to use a c8g.8xlarge AWS Graviton4 instance powered by an Arm Neoverse CPU to build a simple Transcription-as-a-Service server.
5
5
6
+
This architecture is suitable for businesses looking to deploy the latest Generative AI technologies with audio transcription capabilities using their existing CPU compute capacity and deployment pipelines. This demo provides speech recognition using the `whisper-large-v3-turbo model`, deployed using the Hugging Face Transformers framework.
7
+
8
+
Record audio from your browser to interact with the Whisper model and send it to be transcribed to see the performance for yourself. Note that no recorded audio is saved on our servers at any point.
9
+
10
+
After running the demo you can follow the Learning Path to build your own Generative AI service on Arm Neoverse.
6
11
7
12
8
13
demo_steps:
9
-
- Record your voice (giving mic permissions to your browser).
10
-
- Review and send to _________________insert technical thing here_____________.
11
-
- Get transcription and view stats.
14
+
- Record your voice (give microphone permissions to your browser).
15
+
- Review and send the audio file to the sever for transcription.
stats_description: The 'total time' for a whisper voice-to-text process refers to the complete duration taken from the moment the audio input is received until the final text output is generated. This includes several related times such as the 'pre-processing time', which is the time taken to prepare the audio data for transcription, the 'transcription time', which is the actual time spent converting the audio to text, and the 'post-processing time', which involves refining and formatting the transcribed text. Each of these stages contributes to the overall 'total time' and can vary depending on factors such as audio quality, length of the audio, and the efficiency of the transcription algorithm.
29
+
stats_description: |
30
+
The 'total time' for a whisper voice-to-text process refers to the complete duration taken from the moment the audio input is received until the final text output is generated. This includes several related times such as the 'pre-processing time', which is the time taken to prepare the audio data for transcription, the 'transcription time', which is the actual time spent converting the audio to text, and the 'post-processing time', which involves refining and formatting the transcribed text. Each of these stages contributes to the overall 'total time' and can vary depending on factors such as audio quality, length of the audio, and the efficiency of the transcription algorithm.
Copy file name to clipboardExpand all lines: content/learning-paths/servers-and-cloud-computing/whisper/demo-terms-and-conditions.txt
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
TERMS OF SERVICE FOR USE OF CHATBOT DEMO
1
+
TERMS OF SERVICE FOR USE OF WHISPER DEMO
2
2
3
3
PLEASE READ THESE TERMS OF SERVICE CAREFULLY.
4
4
BY USING THE SERVICE, YOU HEREBY ACKNOWLEDGE AND AGREE THAT YOU HAVE READ, FULLY UNDERSTAND, AND AGREE TO BE BOUND BY THESE TERMS OF SERVICE. IF YOU ARE ENTERING INTO THESE TERMS OF SERVICE ON BEHALF OF A COMPANY OR OTHER ENTITY, YOU REPRESENT THAT YOU HAVE THE AUTHORITY TO BIND SUCH COMPANY OR OTHER ENTITY TO THESE TERMS OF SERVICE.
Copy file name to clipboardExpand all lines: themes/arm-design-system-hugo-theme/layouts/partials/demo-components/llm-voice-transcriber/demo-stats--llm-voice-transcriber.html
Copy file name to clipboardExpand all lines: themes/arm-design-system-hugo-theme/layouts/partials/demo-components/llm-voice-transcriber/javascript--llm-voice-transcriber.html
<p>Join the Arm Developer Program to share ideas, ask questions, and explore solutions with the support of the developer community.</p>
259
+
260
+
<ads-modalid="modal-custom-trigger">
261
+
<divslot="body">
262
+
<divid="form-display">
263
+
<h2class="modal-title u-margin-right-1/2" style="margin-top: 0px; margin-bottom: 16px;">Join Arm Developer Program</h2>
264
+
<divclass="c-row" style="max-width: 650px;">
265
+
<p>By signing up, you will receive member news and email updates on topics that interest you. You can manage your subscription preferences anytime.</p>
<pclass="success-message">You're almost there! To complete your membership registration, please click 'confirm membership' in the email we have just sent you.</p>
276
+
<pclass="success-message">Please check your spam folder if you do not see any email in your inbox within 10 minutes.</p>
0 commit comments