From 8f427735644e45a87a98331a2a9ec026f0690afd Mon Sep 17 00:00:00 2001 From: Eustache Le Bihan <eustachelebihan@Eustaches-MacBook-Pro.local> Date: Wed, 14 Aug 2024 22:07:12 +0200 Subject: [PATCH] update readme --- README.md | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/README.md b/README.md index 466c57b..06df542 100644 --- a/README.md +++ b/README.md @@ -70,6 +70,24 @@ python s2s_pipeline.py --recv_host localhost --send_host localhost python listen_and_play.py --host localhost ``` +### Recommended usage + +Leverage Torch Compile for Whisper and Parler-TTS: + +```bash +python s2s_pipeline.py \ + --recv_host 0.0.0.0 \ + --send_host 0.0.0.0 \ + --lm_model_name microsoft/Phi-3-mini-4k-instruct \ + --init_chat_role system \ + --stt_compile_mode reduce-overhead \ + --tts_compile_mode default +``` + +For the moment, modes capturing CUDA Graphs are not compatible with streaming Parler-TTS (`reduce-overhead`, `max-autotune`). + + + ## Command-line Usage ### Model Parameters -- GitLab