Skip to content

Instantly share code, notes, and snippets.

@ottter

ottter/environment.yml

Created July 19, 2023 18:48
Show Gist options
  • Save ottter/bcd79fdf902c1348c2075acb4b66084a to your computer and use it in GitHub Desktop.
Save ottter/bcd79fdf902c1348c2075acb4b66084a to your computer and use it in GitHub Desktop.
Download ZIP
Tortoise TTS w/ CUDA on Windows
Raw
environment.yml
name: tortoise
channels:
- conda-forge
dependencies:
- python=3.8
- charset-normalizer
- pip
- pillow
Raw
requirements.new.txt
tqdm
rotary_embedding_torch
transformers==4.19
tokenizers
inflect
progressbar
einops==0.4.1
unidecode
scipy==1.10.1
librosa==0.9.1
numba
ffmpeg
numpy
threadpoolctl
llvmlite
appdirs
soundfile
Raw
tortoise.sh
# SOURCES
# https://github.com/neonbjb/tortoise-tts
# https://github.com/neonbjb/tortoise-tts/issues/441
conda env create -f environment.yml -p ./env
conda activate ./env
conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia
conda install transformers=4.29.2
git clone https://github.com/neonbjb/tortoise-tts.git
cd tortoise-tts
python -m pip install -r requirements.new.txt
python setup.py install
# If getting errors, try this:
pip install torch==2.0.0+cu118 torchvision==0.15.1+cu118 torchaudio==2.0.1 --index-url https://download.pytorch.org/whl/cu118
# test cuda is working. should print true that gpu is available.
python -c "import torch; print(torch.cuda.is_available());torch.zeros(1).cuda()"
# test tortoise:
python tortoise/do_tts.py --text "I'm going to speak this" --voice random --preset fast
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment