From a97c0506f8b20cdc5ed8a11892ef10a9fc1938ef Mon Sep 17 00:00:00 2001 From: historia Date: Tue, 18 Aug 2026 20:16:22 -0400 Subject: readme --- README.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 63e78db..705a770 100644 --- a/README.md +++ b/README.md @@ -47,9 +47,9 @@ cd qwen3-audiobook-converter pip install -r requirements.txt ``` -## Running the Qwen-TTS server +## Running the Qwen server and audiobook script -The converter script talks to a Qwen3-TTS Gradio server that is run using `qwen-tts-demo`. Add `--no-flash-attn` if FlashAttention isn't installed (see below). The script expects the custom voice model and base model to be on different ports depending on which you're using. The Qwen model(s) will automatically download. +The audiobook script talks to a Qwen3-TTS Gradio server that is run using `qwen-tts-demo`. Add `--no-flash-attn` if FlashAttention isn't installed (see below). The script expects the custom voice model and base model to be on different ports depending on which you're using. The Qwen model(s) will automatically download. Put your book files (epub, etc.) in the `input/` folder. Then run the script. The output goes to `output/`. @@ -120,10 +120,12 @@ Third-party wheels: https://mjunya.com/flash-attention-prebuild-wheels/ (hosted ## Tips -Transcription affects the output a lot. Whisper is okay, but does not give perfect transcription. A manual transcription passed via `--transcription` is usually better. +Transcription affects the output a lot. Whisper is okay, but does not give perfect transcription. A manual transcription passed via `--transcription` is better. Manual transcription, imperfect whisper transcription, and `--no-transcription` each provide different results. Usually the most accurate transcription is the best, but sometimes `--no-transcription` can produce a flat tone that might be preferable for certain voices. +Even tiny amounts of pause between phrases in the sample audio can have a big impact. Try increasing or decreasing them. + Setting `--language` to the "wrong" language for English text can produce an accent. It is not as strong as cloning a voice with the desired accent. The built-in "custom" voices are mediocre. I get *much* better results cloning anything. -- cgit v1.2.3