From b3a8f8e0e9e6062831c3b7af781384fa8688d8b1 Mon Sep 17 00:00:00 2001 From: TKS <32640296+bigsk1@users.noreply.github.com> Date: Sat, 22 Jun 2024 07:58:19 -0700 Subject: [PATCH] update readme and requirements --- README.md | 5 ++++- requirements.txt | 8 +++++--- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 0e97d1f..d0818e1 100644 --- a/README.md +++ b/README.md @@ -276,7 +276,7 @@ You are a wise and ancient wizard who speaks with a mystical and enchanting tone } ``` -For XTTS find a .wav voice and add it to the wizard folder and name it as wizard.wav , the voice only needs to be 6 seconds long. Running the app will automatically find the .wav when it has the characters name and use it. If only using Openai Speech a .wav isn't needed +For XTTS find a .wav voice and add it to the wizard folder and name it as wizard.wav , the voice only needs to be 6 seconds long. Running the app will automatically find the .wav when it has the characters name and use it. If only using Openai Speech or ElevenLabs a .wav isn't needed ## Watch the Demos @@ -286,6 +286,7 @@ Webui - OpenAI and Ollama [![Watch the video](https://img.youtube.com/vi/bgdQkzGltdk/maxresdefault.jpg)](https://youtu.be/bgdQkzGltdk) +--- CLI @@ -294,6 +295,7 @@ GPU - 100% local - ollama llama3, xtts-v2 [![Watch the video](https://img.youtube.com/vi/WsWbYnITdCo/maxresdefault.jpg)](https://youtu.be/WsWbYnITdCo) +--- CPU Only mode CLI @@ -301,6 +303,7 @@ Alien conversation using openai gpt4o and openai speech for tts. [![Watch the video](https://img.youtube.com/vi/d5LbRLhWa5c/maxresdefault.jpg)](https://youtu.be/d5LbRLhWa5c) +--- Docker - ollama - xtts-v2 diff --git a/requirements.txt b/requirements.txt index 23cbe8e..4585bed 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,8 +1,10 @@ # pip install -r requirements.txt -torch==2.3.1 -torchaudio==2.3.1 -torchvision==0.18.1 +# CUDA-enabled PyTorch and related libraries +torch==2.3.1+cu121 +torchaudio==2.3.1+cu121 +torchvision==0.18.1+cu121 +-f https://download.pytorch.org/whl/torch_stable.html pyaudio numpy faster-whisper==1.0.2