ESPnet: end-to-end speech processing toolkit

system/pytorch ver.	1.10.2	1.11.0	1.12.1	1.13.1
ubuntu/python3.10/pip
ubuntu/python3.9/pip
ubuntu/python3.8/pip
ubuntu/python3.7/pip
debian11/python3.7/conda
centos7/python3.7/conda
ubuntu/doc/python3.8

Docs | Example | Example (ESPnet2) | Docker | Notebook

ESPnet is an end-to-end speech processing toolkit covering end-to-end speech recognition, text-to-speech, speech translation, speech enhancement, speaker diarization, spoken language understanding, and so on. ESPnet uses pytorch as a deep learning engine and also follows Kaldi style data processing, feature extraction/format, and recipes to provide a complete setup for various speech processing experiments.

Tutorial Series

• 2019 Tutorial at Interspeech
  • Material
• 2021 Tutorial at CMU
  • Online video
  • Material
• 2022 Tutorial at CMU
  • Usage of ESPnet (ASR as an example)
    • Online video
    • Material
  • Add new models/tasks to ESPnet
    • Online video
    • Material

Key Features

Kaldi style complete recipe

• Support numbers of ASR recipes (WSJ, Switchboard, CHiME-4/5, Librispeech, TED, CSJ, AMI, HKUST, Voxforge, REVERB, etc.)
• Support numbers of TTS recipes with a similar manner to the ASR recipe (LJSpeech, LibriTTS, M-AILABS, etc.)
• Support numbers of ST recipes (Fisher-CallHome Spanish, Libri-trans, IWSLT'18, How2, Must-C, Mboshi-French, etc.)
• Support numbers of MT recipes (IWSLT'14, IWSLT'16, the above ST recipes etc.)
• Support numbers of SLU recipes (CATSLU-MAPS, FSC, Grabo, IEMOCAP, JDCINAL, SNIPS, SLURP, SWBD-DA, etc.)
• Support numbers of SE/SS recipes (DNS-IS2020, LibriMix, SMS-WSJ, VCTK-noisyreverb, WHAM!, WHAMR!, WSJ-2mix, etc.)
• Support voice conversion recipe (VCC2020 baseline)
• Support speaker diarization recipe (mini_librispeech, librimix)
• Support singing voice synthesis recipe (ofuton_p_utagoe_db)

ASR: Automatic Speech Recognition

• State-of-the-art performance in several ASR benchmarks (comparable/superior to hybrid DNN/HMM and CTC)
• Hybrid CTC/attention based end-to-end ASR
  • Fast/accurate training with CTC/attention multitask training
  • CTC/attention joint decoding to boost monotonic alignment decoding
  • Encoder: VGG-like CNN + BiRNN (LSTM/GRU), sub-sampling BiRNN (LSTM/GRU), Transformer, Conformer, Branchformer, or E-Branchformer
  • Decoder: RNN (LSTM/GRU), Transformer, or S4
• Attention: Dot product, location-aware attention, variants of multi-head
• Incorporate RNNLM/LSTMLM/TransformerLM/N-gram trained only with text data
• Batch GPU decoding
• Data augmentation
• Transducer based end-to-end ASR
  • Architecture:
    • RNN-based encoder and decoder.
    • Custom encoder and decoder supporting Transformer, Conformer (encoder), 1D Conv / TDNN (encoder) and causal 1D Conv (decoder) blocks.
    • VGG2L (RNN/custom encoder) and Conv2D (custom encoder) bottlenecks.
  • Search algorithms:
    • Greedy search constrained to one emission by timestep.
    • Default beam search algorithm [Graves, 2012] without prefix search.
    • Alignment-Length Synchronous decoding [Saon et al., 2020].
    • Time Synchronous Decoding [Saon et al., 2020].
    • N-step Constrained beam search modified from [Kim et al., 2020].
    • modified Adaptive Expansion Search based on [Kim et al., 2021] and NSC.
  • Features:
    • Multi-task learning with various auxiliary losses:
      • Encoder: CTC, auxiliary Transducer and symmetric KL divergence.
      • Decoder: cross-entropy w/ label smoothing.
    • Transfer learning with acoustic model and/or language model.
    • Training with FastEmit regularization method [Yu et al., 2021].

  Please refer to the tutorial page for complete documentation.

• CTC segmentation
• Non-autoregressive model based on Mask-CTC
• ASR examples for supporting endangered language documentation (Please refer to egs/puebla_nahuatl and egs/yoloxochitl_mixtec for details)
• Wav2Vec2.0 pretrained model as Encoder, imported from FairSeq.
• Self-supervised learning representations as features, using upstream models in S3PRL in frontend.
  • Set frontend to be s3prl
  • Select any upstream model by setting the frontend_conf to the corresponding name.
• Transfer Learning :
  • easy usage and transfers from models previously trained by your group, or models from ESPnet Hugging Face repository.
  • Documentation and toy example runnable on colab.
• Streaming Transformer/Conformer ASR with blockwise synchronous beam search.
• Restricted Self-Attention based on Longformer as an encoder for long sequences
• OpenAI Whisper model, robust ASR based on large-scale, weakly-supervised multitask learning

Demonstration

• Real-time ASR demo with ESPnet2
• Gradio Web Demo on Hugging Face Spaces. Check out the Web Demo
• Streaming Transformer ASR Local Demo with ESPnet2.

TTS: Text-to-speech

• Architecture
  • Tacotron2
  • Transformer-TTS
  • FastSpeech
  • FastSpeech2
  • Conformer FastSpeech & FastSpeech2
  • VITS
  • JETS
• Multi-speaker & multi-language extention
  • Pretrained speaker embedding (e.g., X-vector)
  • Speaker ID embedding
  • Language ID embedding
  • Global style token (GST) embedding
  • Mix of the above embeddings
• End-to-end training
  • End-to-end text-to-wav model (e.g., VITS, JETS, etc.)
  • Joint training of text2mel and vocoder
• Various language support
  • En / Jp / Zn / De / Ru / And more...
• Integration with neural vocoders
  • Parallel WaveGAN
  • MelGAN
  • Multi-band MelGAN
  • HiFiGAN
  • StyleMelGAN
  • Mix of the above models

Demonstration

• Real-time TTS demo with ESPnet2
• Integrated to Hugging Face Spaces with Gradio. See demo:

To train the neural vocoder, please check the following repositories:

• kan-bayashi/ParallelWaveGAN
• r9y9/wavenet_vocoder

NOTE:

• We are moving on ESPnet2-based development for TTS.
• The use of ESPnet1-TTS is deprecated, please use ESPnet2-TTS.

SE: Speech enhancement (and separation)

• Single-speaker speech enhancement
• Multi-speaker speech separation
• Unified encoder-separator-decoder structure for time-domain and frequency-domain models
  • Encoder/Decoder: STFT/iSTFT, Convolution/Transposed-Convolution
  • Separators: BLSTM, Transformer, Conformer, TasNet, DPRNN, SkiM, SVoice, DC-CRN, DCCRN, Deep Clustering, Deep Attractor Network, FaSNet, iFaSNet, Neural Beamformers, etc.
• Flexible ASR integration: working as an individual task or as the ASR frontend
• Easy to import pretrained models from Asteroid
  • Both the pre-trained models from Asteroid and the specific configuration are supported.

Demonstration

• Interactive SE demo with ESPnet2
• Streaming SE demo with ESPnet2

ST: Speech Translation & MT: Machine Translation

• State-of-the-art performance in several ST benchmarks (comparable/superior to cascaded ASR and MT)
• Transformer based end-to-end ST (new!)
• Transformer based end-to-end MT (new!)

VC: Voice conversion

• Transformer and Tacotron2 based parallel VC using melspectrogram (new!)
• End-to-end VC based on cascaded ASR+TTS (Baseline system for Voice Conversion Challenge 2020!)

SLU: Spoken Language Understanding

• Architecture
  • Transformer based Encoder
  • Conformer based Encoder
  • Branchformer based Encoder
  • E-Branchformer based Encoder
  • RNN based Decoder
  • Transformer based Decoder
• Support Multitasking with ASR
  • Predict both intent and ASR transcript
• Support Multitasking with NLU
  • Deliberation encoder based 2 pass model
• Support using pretrained ASR models
  • Hubert
  • Wav2vec2
  • VQ-APC
  • TERA and more ...
• Support using pretrained NLP models
  • BERT
  • MPNet And more...
• Various language support
  • En / Jp / Zn / Nl / And more...
• Supports using context from previous utterances
• Supports using other tasks like SE in pipeline manner
• Supports Two Pass SLU that combines audio and ASR transcript Demonstration
• Performing noisy spoken language understanding using speech enhancement model followed by spoken language understanding model.
• Performing two pass spoken language understanding where the second pass model attends on both acoustic and semantic information.
• Integrated to Hugging Face Spaces with Gradio. See SLU demo on multiple languages:

SUM: Speech Summarization

• End to End Speech Summarization Recipe for Instructional Videos using Restricted Self-Attention [Sharma et al., 2022]

SVS: Singing Voice Synthesis

• Framework merge from Muskits
• Architecture
  • RNN-based non-autoregressive model
  • Xiaoice
  • Sequence-to-sequence Transformer (with GLU-based encoder)
  • MLP singer (in progress)
  • Tacotron-singing (in progress)
  • DiffSinger (in progress)
  • VISinger
  • VISinger 2
• Support multi-speaker & multilingual singing synthesis
  • Speaker ID embedding
  • Language ID embedding
• Various language support
  • Jp / En / Kr / Zh
• Tight integration with neural vocoders (the same as TTS)

SSL: Self-supervised Learning

• Support HuBERT Pretraining:
  • Example recipe: egs2/LibriSpeech/ssl1

UASR: Unsupervised ASR (EURO: ESPnet Unsupervised Recognition - Open-source)

• Architecture
  • wav2vec-U (with different self-supervised models)
  • wav2vec-U 2.0 (in progress)
• Support PrefixBeamSearch and K2-based WFST decoding

DNN Framework

• Flexible network architecture thanks to chainer and pytorch
• Flexible front-end processing thanks to kaldiio and HDF5 support
• Tensorboard based monitoring

ESPnet2

See ESPnet2.

• Independent from Kaldi/Chainer, unlike ESPnet1
• On the fly feature extraction and text processing when training
• Supporting DistributedDataParallel and DaraParallel both
• Supporting multiple nodes training and integrated with Slurm or MPI
• Supporting Sharded Training provided by fairscale
• A template recipe which can be applied for all corpora
• Possible to train any size of corpus without CPU memory error
• ESPnet Model Zoo
• Integrated with wandb

Installation

• If you intend to do full experiments including DNN training, then see Installation.

• If you just need the Python module only:

  # We recommend you installing pytorch before installing espnet following https://pytorch.org/get-started/locally/
  pip install espnet
  # To install latest
  # pip install git+https://github.com/espnet/espnet
  # To install additional packages
  # pip install "espnet[all]"
  

  If you'll use ESPnet1, please install chainer and cupy.

  pip install chainer==6.0.0 cupy==6.0.0    # [Option]
  

  You might need to install some packages depending on each task. We prepared various installation scripts at tools/installers.

• (ESPnet2) Once installed, run wandb login and set --use_wandb true to enable tracking runs using W&B.

Usage

See Usage.

Docker Container

go to docker/ and follow instructions.

Contribution

Thank you for taking times for ESPnet! Any contributions to ESPnet are welcome and feel free to ask any questions or requests to issues. If it's the first contribution to ESPnet for you, please follow the contribution guide.

Results and demo

You can find useful tutorials and demos in Interspeech 2019 Tutorial

ASR results

ASR demo

# go to recipe directory and source path of espnet tools
cd egs/tedlium2/asr1 && . ./path.sh
# let's recognize speech!
recog_wav.sh --models tedlium2.transformer.v1 example.wav

SE results

SE demos

ST results

ST demo

# go to recipe directory and source path of espnet tools
cd egs/fisher_callhome_spanish/st1 && . ./path.sh
# download example wav file
wget -O - https://github.com/espnet/espnet/files/4100928/test.wav.tar.gz | tar zxvf -
# let's translate speech!
translate_wav.sh --models fisher_callhome_spanish.transformer.v1.es-en test.wav

MT results

TTS results

TTS demo

# go to recipe directory and source path of espnet tools
cd egs/ljspeech/tts1 && . ./path.sh
# we use upper-case char sequence for the default model.
echo "THIS IS A DEMONSTRATION OF TEXT TO SPEECH." > example.txt
# let's synthesize speech!
synth_wav.sh example.txt

# also you can use multiple sentences
echo "THIS IS A DEMONSTRATION OF TEXT TO SPEECH." > example_multi.txt
echo "TEXT TO SPEECH IS A TECHNIQUE TO CONVERT TEXT INTO SPEECH." >> example_multi.txt
synth_wav.sh example_multi.txt

synth_wav.sh --models ljspeech.fastspeech.v1 example.txt

synth_wav.sh --vocoder_models ljspeech.wavenet.mol.v1 example.txt

synth_wav.sh --help

VC results

SLU results

CTC Segmentation demo

cd egs/tedlium2/align1/
# data directory
align_dir=data/demo
mkdir -p ${align_dir}
# wav file
base=ctc_align_test
wav=../../../test_utils/${base}.wav
# recipe files
echo "batchsize: 0" > ${align_dir}/align.yaml

cat << EOF > ${align_dir}/utt_text
${base} THE SALE OF THE HOTELS
${base} IS PART OF HOLIDAY'S STRATEGY
${base} TO SELL OFF ASSETS
${base} AND CONCENTRATE
${base} ON PROPERTY MANAGEMENT
EOF

# pre-trained ASR model
model=wsj.transformer_small.v1
mkdir ./conf && cp ../../wsj/asr1/conf/no_preprocess.yaml ./conf

../../../utils/asr_align_wav.sh \
    --models ${model} \
    --align_dir ${align_dir} \
    --align_config ${align_dir}/align.yaml \
    ${wav} ${align_dir}/utt_text

min_confidence_score=-5
awk -v ms=${min_confidence_score} '{ if ($5 > ms) {print} }' ${align_dir}/aligned_segments

# load a model with character tokens
from espnet_model_zoo.downloader import ModelDownloader
d = ModelDownloader(cachedir="./modelcache")
wsjmodel = d.download_and_unpack("kamo-naoyuki/wsj")
# load the example file included in the ESPnet repository
import soundfile
speech, rate = soundfile.read("./test_utils/ctc_align_test.wav")
# CTC segmentation
from espnet2.bin.asr_align import CTCSegmentation
aligner = CTCSegmentation( **wsjmodel , fs=rate )
text = """
utt1 THE SALE OF THE HOTELS
utt2 IS PART OF HOLIDAY'S STRATEGY
utt3 TO SELL OFF ASSETS
utt4 AND CONCENTRATE ON PROPERTY MANAGEMENT
"""
segments = aligner(speech, text)
print(segments)
# utt1 utt 0.26 1.73 -0.0154 THE SALE OF THE HOTELS
# utt2 utt 1.73 3.19 -0.7674 IS PART OF HOLIDAY'S STRATEGY
# utt3 utt 3.19 4.20 -0.7433 TO SELL OFF ASSETS
# utt4 utt 4.20 6.10 -0.4899 AND CONCENTRATE ON PROPERTY MANAGEMENT

aligner.set_config( gratis_blank=True, kaldi_style_text=False )
text = ["SALE OF THE HOTELS", "PROPERTY MANAGEMENT"]
segments = aligner(speech, text)
print(segments)
# utt_0000 utt 0.37 1.72 -2.0651 SALE OF THE HOTELS
# utt_0001 utt 4.70 6.10 -5.0566 PROPERTY MANAGEMENT

# ASR model and config files from pretrained model (e.g. from cachedir):
asr_config=<path-to-model>/config.yaml
asr_model=<path-to-model>/valid.*best.pth
# prepare the text file
wav="test_utils/ctc_align_test.wav"
text="test_utils/ctc_align_text.txt"
cat << EOF > ${text}
utt1 THE SALE OF THE HOTELS
utt2 IS PART OF HOLIDAY'S STRATEGY
utt3 TO SELL OFF ASSETS
utt4 AND CONCENTRATE
utt5 ON PROPERTY MANAGEMENT
EOF
# obtain alignments:
python espnet2/bin/asr_align.py --asr_train_config ${asr_config} --asr_model_file ${asr_model} --audio ${wav} --text ${text}
# utt1 ctc_align_test 0.26 1.73 -0.0154 THE SALE OF THE HOTELS
# utt2 ctc_align_test 1.73 3.19 -0.7674 IS PART OF HOLIDAY'S STRATEGY
# utt3 ctc_align_test 3.19 4.20 -0.7433 TO SELL OFF ASSETS
# utt4 ctc_align_test 4.20 4.97 -0.6017 AND CONCENTRATE
# utt5 ctc_align_test 4.97 6.10 -0.3477 ON PROPERTY MANAGEMENT

min_confidence_score=-7
# here, we assume that the output was written to the file `segments`
awk -v ms=${min_confidence_score} '{ if ($5 > ms) {print} }' segments

Citations

@inproceedings{watanabe2018espnet,
  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson {Enrique Yalta Soplin} and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
  title={{ESPnet}: End-to-End Speech Processing Toolkit},
  year={2018},
  booktitle={Proceedings of Interspeech},
  pages={2207--2211},
  doi={10.21437/Interspeech.2018-1456},
  url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
}
@inproceedings{hayashi2020espnet,
  title={{Espnet-TTS}: Unified, reproducible, and integratable open source end-to-end text-to-speech toolkit},
  author={Hayashi, Tomoki and Yamamoto, Ryuichi and Inoue, Katsuki and Yoshimura, Takenori and Watanabe, Shinji and Toda, Tomoki and Takeda, Kazuya and Zhang, Yu and Tan, Xu},
  booktitle={Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={7654--7658},
  year={2020},
  organization={IEEE}
}
@inproceedings{inaguma-etal-2020-espnet,
    title = "{ESP}net-{ST}: All-in-One Speech Translation Toolkit",
    author = "Inaguma, Hirofumi  and
      Kiyono, Shun  and
      Duh, Kevin  and
      Karita, Shigeki  and
      Yalta, Nelson  and
      Hayashi, Tomoki  and
      Watanabe, Shinji",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.acl-demos.34",
    pages = "302--311",
}
@inproceedings{li2020espnet,
  title={{ESPnet-SE}: End-to-End Speech Enhancement and Separation Toolkit Designed for {ASR} Integration},
  author={Chenda Li and Jing Shi and Wangyou Zhang and Aswin Shanmugam Subramanian and Xuankai Chang and Naoyuki Kamo and Moto Hira and Tomoki Hayashi and Christoph Boeddeker and Zhuo Chen and Shinji Watanabe},
  booktitle={Proceedings of IEEE Spoken Language Technology Workshop (SLT)},
  pages={785--792},
  year={2021},
  organization={IEEE},
}
@inproceedings{arora2021espnet,
  title={{ESPnet-SLU}: Advancing Spoken Language Understanding through ESPnet},
  author={Arora, Siddhant and Dalmia, Siddharth and Denisov, Pavel and Chang, Xuankai and Ueda, Yushi and Peng, Yifan and Zhang, Yuekai and Kumar, Sujay and Ganesan, Karthik and Yan, Brian and others},
  booktitle={ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={7167--7171},
  year={2022},
  organization={IEEE}
}
@inproceedings{shi2022muskits,
  author={Shi, Jiatong and Guo, Shuai and Qian, Tao and Huo, Nan and Hayashi, Tomoki and Wu, Yuning and Xu, Frank and Chang, Xuankai and Li, Huazhe and Wu, Peter and Watanabe, Shinji and Jin, Qin},
  title={{Muskits}: an End-to-End Music Processing Toolkit for Singing Voice Synthesis},
  year={2022},
  booktitle={Proceedings of Interspeech},
  pages={4277-4281},
  url={https://www.isca-speech.org/archive/pdfs/interspeech_2022/shi22d_interspeech.pdf}
}
@article{gao2022euro,
  title={{EURO}: {ESPnet} Unsupervised ASR Open-source Toolkit},
  author={Gao, Dongji and Shi, Jiatong and Chuang, Shun-Po and Garcia, Leibny Paola and Lee, Hung-yi and Watanabe, Shinji and Khudanpur, Sanjeev},
  journal={arXiv preprint arXiv:2211.17196},
  year={2022}
}