From 89532d624c6a2f40c4357db6c3052cea5a3725dc Mon Sep 17 00:00:00 2001 From: Ayo Date: Thu, 25 Jun 2026 17:11:25 +0200 Subject: [PATCH] chore: add instruction on using HuggingFace access token --- README.md | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/README.md b/README.md index 7270766..003e202 100644 --- a/README.md +++ b/README.md @@ -180,6 +180,16 @@ ls ./outputs/simple-greetings Each of the [voices below](#voices) need to be downloaded once the first time they are used, and this needs an online connection. Subsequent runs can be done offline. +### HuggingFace Access Token (Optional) + +The download of the model can be faster if you sent the `HF_TOKEN` environment variable. Create a [user access token](https://huggingface.co/docs/hub/security-tokens) and set the environment variable if you want to unlock this, but it is totally optional. + +Once you have a HuggingFace access token, you can add it on your `.bashrc` file (or similar) + +```bash +export HF_TOKEN= +``` + ### Voices You can choose a voice to use with the `--voice` flag. For this, we use [kokoro](https://huggingface.co/hexgrad/Kokoro-82M), which is an Apache-licensed model. See [all available voices](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md).