Skip to content

armgit / Handy

Public Imported from GitHub
0

A free, open source, and extensible speech-to-text application that works completely offline.

update instructions to include downloading the models to run when building locally

CJ Pais447f2385dcfb
diff --git a/README.md b/README.md
index a097330b..60baf628 100644
--- a/README.md
+++ b/README.md
@@ -64,6 +64,30 @@ bun run tauri dev
bun run tauri build
```
+**Model Files Setup:**
+
+For development, you need to download the required model files:
+
+1. Create the models directory inside the resources folder:
+ ```bash
+ mkdir -p src-tauri/resources/models
+ ```
+
+2. Download the required model files:
+ ```bash
+ # Download Whisper model (Small model)
+ curl -o src-tauri/resources/models/ggml-small.bin https://blob.handy.computer/ggml-small.bin
+
+ # Download Silero VAD model
+ curl -o src-tauri/resources/models/silero_vad_v4.onnx https://blob.handy.computer/silero_vad_v4.onnx
+ ```
+
+**Alternative Whisper Models:**
+
+The `ggml-small.bin` file can be replaced with any GGML model for whisper.cpp. Available models can be found at [huggingface.co/ggerganov/whisper.cpp](https://huggingface.co/ggerganov/whisper.cpp/tree/main).
+
+**Important:** If you use a different Whisper model, you'll need to update the filename reference in the manager's transcription code to match your chosen model file.
+
## Architecture
Handy is built as a Tauri application combining: