From b495b7d177957480a7cf42ca6bf464e3d651a9fa Mon Sep 17 00:00:00 2001 From: Shiven Mian Date: Sat, 10 Feb 2024 20:09:16 -0800 Subject: [PATCH] fix: updated README --- README.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/README.md b/README.md index 5350605..f092ce9 100644 --- a/README.md +++ b/README.md @@ -23,8 +23,6 @@ python -m pip install -r requirements.txt ``` NB: Depending on your local Python version, you may run into [this issue↗](https://github.com/TaylorSMarks/playsound/issues/150) installing playsound. Workarounds are provided in the issue. -If you want to run local speech-to-text from whisper, download the GGML Whisper model from [Huggingface](https://huggingface.co/ggerganov/whisper.cpp). Then in `OS/01/start.sh`, set `ALL_LOCAL=TRUE` and set `WHISPER_MODEL_PATH` to the path of the model. - ## Usage ```bash @@ -32,6 +30,7 @@ cd OS/01 bash start.sh ``` +If you want to run local text-to-speech and speech-to-text, set `ALL_LOCAL` in the `start.sh` script to True. This will use the [whisper.cpp](https://github.com/ggerganov/whisper.cpp) and [Piper](https://github.com/rhasspy/piper) models.
## Background