Code for vector quantizing speech dataset, including melspectrograms, phonetic-posteriorgrams/bottleneck features(BNFs). This repo trains an independent module to vector quantize BNFs.

For usage in voice conversion, see here

• Install ffmpeg.
• Install Kaldi
• Install PyKaldi
• Install packages using environment.yml file.
• Download pretrained TDNN-F model, extract it, and set PRETRAIN_ROOT in kaldi_scripts/extract_features_kaldi.sh to the pretrained model directory.

• Acoustic Model: LibriSpeech. Download pretrained TDNN-F acoustic model here.
  • You also need to set KALDI_ROOT and PRETRAIN_ROOT in kaldi_scripts/extract_features_kaldi.sh accordingly.
• Vector Quantization: [ARCTIC and L2-ARCTIC, see here for detailed training process.

All the pretrained the models are available (To be updated) here

datatset_root
├── speaker 1
├── speaker 2 
│   ├── wav          # contains all the wav files from speaker 2
│   └── kaldi        # Kaldi files (auto-generated after running kaldi-scripts
.
.
└── speaker N

See the inference script

• Use Kaldi to extract BNF for individual speakers (Do it for all speakers)

./kaldi_scripts/extract_features_kaldi.sh /path/to/speaker

• Preprocessing

python preprocess_bnfs.py path/to/dataset
python python make_data_all.py  #Edit the file to specify dataset path

• Setting Training params. See conf/

• Training VQ Model

./train.sh