diff options
| author | Pinapelz <yukais@pinapelz.com> | 2026-04-27 00:53:21 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2026-04-27 00:53:21 -0700 |
| commit | af8dea1a569f4bccc2d86b2a7d7c636c777692ec (patch) | |
| tree | 7aea49e3b32de5bb6ca7215fdc7633e514698629 | |
| parent | f1c5df1541823c4177b9c2efd8de56eb3e309dd3 (diff) | |
Add demo section with usage examples to README
Added a demo section with examples of usage.
| -rw-r--r-- | README.md | 18 |
1 files changed, 17 insertions, 1 deletions
@@ -3,7 +3,6 @@ A basic LOCAL translation backend that listens to an audio sink via PCM and runs Translations and trascriptions are transformers based, inaccuracies and hallucinations will occur. - # Setup > It's highly recommended that you run this with a GPU, running with CPU is possible but inference will be very slow outside of using tiny models (which compromise accuracy) > @@ -91,3 +90,20 @@ for event in client.events(): import json print(json.loads(event.data)["text"]) ``` + + +## Demo +Ran using faster-whisper medium and qwen2.5-7B-instruct on RTX 3060 Mobile (CUDA) + +Example 1: + +https://github.com/user-attachments/assets/db602a11-2d13-4e58-a5e8-1d4a71c1be0e + + +Example 2: + +https://github.com/user-attachments/assets/a480809e-77f7-4b66-9686-aa2ffea8333d + + + + |
