From a89daa1af05e2816f970d6a7b28a07df4f102f7d Mon Sep 17 00:00:00 2001 From: historia Date: Tue, 18 Aug 2026 23:29:16 -0400 Subject: readme --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 433370f..fd24a8d 100644 --- a/README.md +++ b/README.md @@ -85,7 +85,7 @@ python audiobook.py Change the voice settings in `converter/config.py`. -## Using the `--faster` backend +## Optional: Using the `--faster` backend Instead of the Qwen Gradio demos, `--faster` talks to the OpenAI-compatible server from [faster-qwen3-tts](https://github.com/andimarafioti/faster-qwen3-tts), which uses CUDA graph capture for roughly 5-10x faster inference with the same models. **It requires an NVIDIA GPU**. @@ -162,7 +162,7 @@ python audiobook.py --faster [--faster-voice NAME] Other options and defaults are configured in `converter/config.py` -## FlashAttention for qwen-tts-demo server (optional) +## Optional: FlashAttention for qwen-tts-demo server This is **not** used with the `--faster` backend. The Gradio server tries to use FlashAttention 2 by default, but requires `--no-flash-attn` without it. On supported GPUs FlashAttention can give a modest speedup. -- cgit v1.2.3