# 1. clone the repo on in a directory on a drive with plenty of free space
git clone git@github.com:jasonppy/VoiceCraft.git
cd VoiceCraft

# 2. assumes you have docker installed with nvidia container container-toolkit (windows has this built into the driver)
# https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/1.13.5/install-guide.html
# sudo apt-get install -y nvidia-container-toolkit-base || yay -Syu nvidia-container-toolkit || echo etc...

# 3. First build the docker image
docker build --tag "voicecraft" .

# 4. Try to start an existing container otherwise create a new one passing in all GPUs
./start-jupyter.sh  # linux
start-jupyter.bat   # windows

# 5. now open a webpage on the host box to the URL shown at the bottom of:
docker logs jupyter

# 6. optionally look inside from another terminal
docker exec -it jupyter /bin/bash
export USER=(your_linux_username_used_above)
export HOME=/home/$USER
sudo apt-get update

# 7. confirm video card(s) are visible inside container
nvidia-smi

# 8. Now in browser, open inference_tts.ipynb and work through one cell at a time
echo GOOD LUCK

conda create -n voicecraft python=3.9.16
conda activate voicecraft

pip install -e git+https://github.com/facebookresearch/audiocraft.git@c5157b5bf14bf83449c17ea1eeb66c19fb4bc7f0#egg=audiocraft
pip install xformers==0.0.22
pip install torchaudio==2.0.2 torch==2.0.1 # this assumes your system is compatible with CUDA 11.7, otherwise checkout https://pytorch.org/get-started/previous-versions/#v201
apt-get install ffmpeg # if you don't already have ffmpeg installed
apt-get install espeak-ng # backend for the phonemizer installed below
pip install tensorboard==2.16.2
pip install phonemizer==3.2.1
pip install datasets==2.16.0
pip install torchmetrics==0.11.1
pip install huggingface_hub==0.22.2
# install MFA for getting forced-alignment, this could take a few minutes
conda install -c conda-forge montreal-forced-aligner=2.2.17 openfst=1.8.2 kaldi=5.5.1068
# install MFA english dictionary and model
mfa model download dictionary english_us_arpa
mfa model download acoustic english_us_arpa
# pip install huggingface_hub
# conda install pocl # above gives an warning for installing pocl, not sure if really need this

# to run ipynb
conda install -n voicecraft ipykernel --no-deps --force-reinstall

apt-get install -y espeak espeak-data libespeak1 libespeak-dev
apt-get install -y festival*
apt-get install -y build-essential
apt-get install -y flac libasound2-dev libsndfile1-dev vorbis-tools
apt-get install -y libxml2-dev libxslt-dev zlib1g-dev
pip install -r gradio_requirements.txt

python gradio_app.py

conda activate voicecraft
export CUDA_VISIBLE_DEVICES=0
cd ./data
python phonemize_encodec_encode_hf.py \
--dataset_size xs \
--download_to path/to/store_huggingface_downloads \
--save_dir path/to/store_extracted_codes_and_phonemes \
--encodec_model_path path/to/encodec_model \
--mega_batch_size 120 \
--batch_size 32 \
--max_len 30000

conda activate voicecraft
cd ./z_scripts
bash e830M.sh