Hugging Face's logo

Spaces:
robinhad
/
ukrainian-tts
Running

App Files Community
1
ukrainian-tts / training /STEPS.md
Yurii Paniv
Improve training steps
eb57397
preview code
|
raw
history blame
914 Bytes

Setup env Link: https://espnet.github.io/espnet/installation.html

  1. sudo apt-get install cmake sox libsndfile1-dev ffmpeg
  2. git clone --branch v.202209 https://github.com/espnet/espnet
  3. cd ./espnet/tools ./setup_anaconda.sh anaconda espnet 3.8
  4. CONDA_TOOLS_DIR=$(dirname ${CONDA_EXE})/.. ./setup_anaconda.sh ${CONDA_TOOLS_DIR} espnet 3.8
  5. make pip install --upgrade torch torchaudio # or setup same versions make
  6. . ./activate_python.sh; python3 check_install.py

run training

cd ../egs2/ljspeech/tts1 ./run.sh

./run.sh
--stage 2
--use_sid true
--fs 22050
--n_fft 1024
--n_shift 256
--win_length null
--dumpdir dump/22k
--expdir exp/22k
--tts_task gan_tts
--feats_extract linear_spectrogram
--feats_normalize none
--train_config ./conf/tuning/train_vits.yaml
--inference_config ./conf/tuning/decode_vits.yaml