-
-
Notifications
You must be signed in to change notification settings - Fork 80
Whisper
VRCWizard edited this page Aug 18, 2024
·
18 revisions
Implementation using WhisperNet a C# wrapper for whisper.cpp
Setup instructions no longer required, Whisper models can be downloaded directly in app.
- To get started using Whisper Download one of the models below or from the official whisper.cpp model list
- Keep in mind that this implementation of Whisper uses your GPU.
- The medium model may cause stuttering in a GPU intensive game like VRChat while in VR.
| Recommended Model Download | Size | Memory |
|---|---|---|
| ggml-medium.bin | 1.5 GB | ~2.6 GB |
| ggml-small.bin | 466 MB | ~1.0 GB |
| ggml-base.bin | 142 MB | ~500 MB |
| ggml-tiny.bin | 75 MB | ~390 MB |
- Add the model to Speech Provider > Local > Whisper.cpp Model (BIN file)

- Noises that the Whisper AI recognizes are filtered out by default. It can recognize music, keyboard and mouse clicks etc.
- If you notice that after talking for too long that you end up outputting 2 TTS messages at the same time increase the Max Duration Setting under where you select your model. The default for TTS Voice Wizard is 8.0 or 8 seconds (the message is cut off after 8 seconds). (This issue has been solved with the TTS Message Queue System)
