# Set path to CUDA, NCCL
CUDAROOT=/usr/local/cuda
NCCL_ROOT=/usr/local/nccl

export CPATH=$NCCL_ROOT/include:$CPATH
export LD_LIBRARY_PATH=$NCCL_ROOT/lib/:$CUDAROOT/lib64:$LD_LIBRARY_PATH
export LIBRARY_PATH=$NCCL_ROOT/lib/:$LIBRARY_PATH
export CUDA_HOME=$CUDAROOT
export CUDA_PATH=$CUDAROOT
export CPATH=$CUDA_PATH/include:$CPATH  # for warp-rnnt

# Install miniconda, python libraries, and other tools
cd tools
make KALDI=/path/to/kaldi

• ASR

  • AISHELL-1
  • CSJ
  • Librispeech
  • Switchboard (+ Fisher)
  • TEDLIUM2/TEDLIUM3
  • TIMIT
  • WSJ

• LM

  • Penn Tree Bank
  • WikiText2

• Frame stacking
• Sequence summary network [link]
• SpecAugment [link]
• Adaptive SpecAugment [link]

• RNN encoder
  • (CNN-)BLSTM, (CNN-)LSTM, (CNN-)BLGRU, (CNN-)LGRU
  • Latency-controlled BLSTM [link]
• Transformer encoder [link]
  • (CNN-)Transformer
  • Chunk hopping mechanism [link]
  • Relative positional encoding [link]
• Time-depth separable (TDS) convolution encoder [link] [line]
• Gated CNN encoder (GLU) [link]
• Conformer encoder [link]

• Forced alignment
• Beam search
• Shallow fusion

• RNN decoder
  • Shallow fusion
  • Cold fusion [link]
  • Deep fusion [link]
  • Forward-backward attention decoding [link]
  • Ensemble decoding
• Streaming RNN decoder
  • Hard monotonic attention [link]
  • Monotonic chunkwise attention (MoChA) [link]
  • CTC-synchronous training (CTC-ST) [link]
• RNN transducer [link]
• Transformer decoder [link]
• Streaming Transformer decoder
  • Monotonic Multihead Attention [link] [link]

• RNNLM (recurrent neural network language model)
• Gated convolutional LM [link]
• Transformer LM
• Transformer-XL LM [link]
• Adaptive softmax [link]

• Phoneme
• Grapheme
• Wordpiece (BPE, sentencepiece)
• Word
• Word-char mix

Multi-task learning (MTL) with different units are supported to alleviate data sparseness.

• Hybrid CTC/attention [link]
• Hierarchical Attention (e.g., word attention + character attention) [link]
• Hierarchical CTC (e.g., word CTC + character CTC) [link]
• Hierarchical CTC+Attention (e.g., word attention + character CTC) [link]
• Forward-backward attention [link]
• LM objective

• https://github.com/kaldi-asr/kaldi
• https://github.com/espnet/espnet
• https://github.com/awni/speech
• https://github.com/HawkAaron/E2E-ASR

• https://github.com/SeanNaren/warp-ctc
• https://github.com/HawkAaron/warp-transducer
• https://github.com/1ytic/warp-rnnt