pip install pyloudnorm
mkdir repos
git clone https://github.com/xiph/rnnoise.git repos/rnnoise
sudo apt-get install curl autoconf automake libtool python-dev pkg-config sox ffmpeg

sh autogen.sh
sh configure
make clean
make

cd ~/repos
git clone https://github.com/openai/whisper.git
pip install git+https://github.com/openai/whisper.git
sudo apt-get install espeak-ng
git clone https://github.com/coqui-ai/TTS.git
pip install TTS
tts --list_models

mkdir audioclips
cd audioclips
explorer.exe .
mkdir out
find . -name '*.mp3' -exec bash -c 'for f; do ffmpeg -i "$f" -acodec pcm_s16le -ar 22050 -ac 1 out/"${f%.mp3}".wav ; done' _ {} +


for f in *.wav; do ffmpeg -y -i "$f" -acodec pcm_s16le -ar 22050 -ac 1 out/"$f.wav"; done

cd out
mkdir splits

for FILE in *.wav; do sox "$FILE" splits/"$FILE" --show-progress silence 1 0.5 0.1% 1 0.5 0.1% : newfile : restart ; done
cd splits
find . -name "*.wav" -type f -size -15k -delete




tts --text "I am the very model of a modern Major General" --model_name "tts_models/en/ljspeech/vits" --out_path ljspeech-vits.wav



!CUDA_VISIBLE_DEVICES="0" python train_vits.py --restore_path ~/.local/share/tts/tts_models--en--ljspeech--vits/model_file.pth --config_file ~/.local/share/tts/tts_models--en--ljspeech--vits/config.json