Skip to content

README_2.md

Latest commit

 

History

History
66 lines (57 loc) · 1.57 KB

README_2.md

File metadata and controls

66 lines (57 loc) · 1.57 KB

ubuntu

sudo apt-get update && sudo apt-get upgrade

wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh

chmod +x Miniconda3-latest-Linux-x86_64.sh

./Miniconda3-latest-Linux-x86_64.sh

conda create -n openvoice python=3.9

conda activate openvoice

conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.7 -c pytorch -c nvidia

cd Downloads

sudo apt install git -y

git clone https://github.com/Zbrooklyn/Local-Low-Latency-Speech-to-Speech.git

cd Local-Low-Latency-Speech-to-Speech

pip install -r requirements.txt

part 2

LOCAL LOW LATENCY SPEECH TO SPEECH

  1. git clone https://github.com/All-About-AI-YouTube/low-latency-sts.git
  2. cd low-latency-sts
  3. run:
  • conda create -n openvoice python=3.9
  • conda activate openvoice
  • conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.7 -c pytorch -c nvidia
  • pip install -r requirements.txt
  1. create a folder "checkpoints"
  2. Download checkpoints from HERE: https://myshell-public-repo-hosting.s3.amazonaws.com/checkpoints_1226.zip
  3. Unzip to Checkpoints (basespeakers + converter)
  4. Install LM Studio (https://lmstudio.ai/)
  5. Download Bloke Dolphin Mistral 7B V2 (https://huggingface.co/TheBloke/dolphin-2.2.1-mistral-7B-AWQ) in LM Studio
  6. Setup Local Server in LM Studio (https://youtu.be/IgcBuXFE6QE)
  7. Start Server
  8. Get a reference voice in PATH / PATHS (mp3)
  9. RUN talk.py or voice69.py