%global _empty_manifest_terminate_build 0 Name: python-espnet Version: 202304 Release: 1 Summary: ESPnet: end-to-end speech processing toolkit License: Apache Software License URL: http://github.com/espnet/espnet Source0: https://mirrors.nju.edu.cn/pypi/web/packages/1f/ce/e078613e73ec5f9c01b6a3b075af7e570e80ec2f777f471562df3a2067bc/espnet-202304.tar.gz BuildArch: noarch Requires: python3-setuptools Requires: python3-packaging Requires: python3-configargparse Requires: python3-typeguard Requires: python3-humanfriendly Requires: python3-scipy Requires: python3-filelock Requires: python3-librosa Requires: python3-jamo Requires: python3-PyYAML Requires: python3-soundfile Requires: python3-h5py Requires: python3-kaldiio Requires: python3-torch Requires: python3-torch-complex Requires: python3-nltk Requires: python3-numpy Requires: python3-protobuf Requires: python3-hydra-core Requires: python3-opt-einsum Requires: python3-sentencepiece Requires: python3-ctc-segmentation Requires: python3-pyworld Requires: python3-pypinyin Requires: python3-espnet-tts-frontend Requires: python3-ci-sdr Requires: python3-pytorch-wpe Requires: python3-fast-bss-eval Requires: python3-editdistance Requires: python3-importlib-metadata Requires: python3-torchaudio Requires: python3-torch-optimizer Requires: python3-fairscale Requires: python3-transformers Requires: python3-gtn Requires: python3-matplotlib Requires: python3-pillow Requires: python3-editdistance Requires: python3-wandb Requires: python3-tensorboard Requires: python3-espnet-model-zoo Requires: python3-gdown Requires: python3-resampy Requires: python3-pysptk Requires: python3-morfessor Requires: python3-youtube-dl Requires: python3-nnmnkwii Requires: python3-museval Requires: python3-pystoi Requires: python3-mir-eval Requires: python3-fastdtw Requires: python3-nara-wpe Requires: python3-sacrebleu Requires: python3-praatio Requires: python3-scikit-learn Requires: python3-Jinja2 Requires: python3-Sphinx Requires: python3-sphinx-rtd-theme Requires: python3-sphinx-argparse Requires: python3-commonmark Requires: python3-recommonmark Requires: python3-nbsphinx Requires: python3-sphinx-markdown-tables Requires: python3-espnet-model-zoo Requires: python3-gdown Requires: python3-resampy Requires: python3-pysptk Requires: python3-morfessor Requires: python3-youtube-dl Requires: python3-nnmnkwii Requires: python3-museval Requires: python3-pystoi Requires: python3-mir-eval Requires: python3-fastdtw Requires: python3-nara-wpe Requires: python3-sacrebleu Requires: python3-praatio Requires: python3-scikit-learn Requires: python3-pytest Requires: python3-pytest-timeouts Requires: python3-pytest-pythonpath Requires: python3-pytest-cov Requires: python3-hacking Requires: python3-mock Requires: python3-pycodestyle Requires: python3-jsondiff Requires: python3-flake8 Requires: python3-flake8-docstrings Requires: python3-black Requires: python3-isort Requires: python3-music21 Requires: python3-matplotlib Requires: python3-pillow Requires: python3-editdistance Requires: python3-wandb Requires: python3-tensorboard Requires: python3-matplotlib Requires: python3-pillow Requires: python3-editdistance Requires: python3-wandb Requires: python3-tensorboard %description You can translate speech in a WAV file using pretrained models. Go to a recipe directory and run `utils/translate_wav.sh` as follows: ```sh # 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 ``` where `test.wav` is a WAV file to be translated. The sampling rate must be consistent with that of data used in training. Available pretrained models in the demo script are listed as below. | Model | Notes | | :----------------------------------------------------------------------------------------------------------- | :------------------------------------------------------- | | [fisher_callhome_spanish.transformer.v1](https://drive.google.com/open?id=1hawp5ZLw4_SIHIT3edglxbKIIkPVe8n3) | Transformer-ST trained on Fisher-CallHome Spanish Es->En | ### MT results
expand
| Task | BLEU | Pretrained model | | ------------------------------------------------- | :---: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------: | | Fisher-CallHome Spanish fisher_test (Es->En) | 61.45 | [link](https://github.com/espnet/espnet/blob/master/egs/fisher_callhome_spanish/mt1/RESULTS.md#trainen_lcrm_lcrm_pytorch_train_pytorch_transformer_bpe_bpe1000) | | Fisher-CallHome Spanish callhome_evltest (Es->En) | 29.86 | [link](https://github.com/espnet/espnet/blob/master/egs/fisher_callhome_spanish/mt1/RESULTS.md#trainen_lcrm_lcrm_pytorch_train_pytorch_transformer_bpe_bpe1000) | | Libri-trans test (En->Fr) | 18.09 | [link](https://github.com/espnet/espnet/blob/master/egs/libri_trans/mt1/RESULTS.md#trainfr_lcrm_tc_pytorch_train_pytorch_transformer_bpe1000) | | How2 dev5 (En->Pt) | 58.61 | [link](https://github.com/espnet/espnet/blob/master/egs/how2/mt1/RESULTS.md#trainpt_tc_tc_pytorch_train_pytorch_transformer_bpe8000) | | Must-C tst-COMMON (En->De) | 27.63 | [link](https://github.com/espnet/espnet/blob/master/egs/must_c/mt1/RESULTS.md#summary-4-gram-bleu) | | IWSLT'14 test2014 (En->De) | 24.70 | [link](https://github.com/espnet/espnet/blob/master/egs/iwslt16/mt1/RESULTS.md#result) | | IWSLT'14 test2014 (De->En) | 29.22 | [link](https://github.com/espnet/espnet/blob/master/egs/iwslt16/mt1/RESULTS.md#result) | | IWSLT'14 test2014 (De->En) | 32.2 | [link](https://github.com/espnet/espnet/blob/master/egs2/iwslt14/mt1/README.md) | | IWSLT'16 test2014 (En->De) | 24.05 | [link](https://github.com/espnet/espnet/blob/master/egs/iwslt16/mt1/RESULTS.md#result) | | IWSLT'16 test2014 (De->En) | 29.13 | [link](https://github.com/espnet/espnet/blob/master/egs/iwslt16/mt1/RESULTS.md#result) |
### TTS results
ESPnet2
You can listen to the generated samples in the following URL. - [ESPnet2 TTS generated samples](https://drive.google.com/drive/folders/1H3fnlBbWMEkQUfrHqosKN_ZX_WjO29ma?usp=sharing) > Note that in the generation we use Griffin-Lim (`wav/`) and [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) (`wav_pwg/`). You can download pretrained models via `espnet_model_zoo`. - [ESPnet model zoo](https://github.com/espnet/espnet_model_zoo) - [Pretrained model list](https://github.com/espnet/espnet_model_zoo/blob/master/espnet_model_zoo/table.csv) You can download pretrained vocoders via `kan-bayashi/ParallelWaveGAN`. - [kan-bayashi/ParallelWaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) - [Pretrained vocoder list](https://github.com/kan-bayashi/ParallelWaveGAN#results)
ESPnet1
> NOTE: We are moving on ESPnet2-based development for TTS. Please check the latest results in the above ESPnet2 results. You can listen to our samples in demo HP [espnet-tts-sample](https://espnet.github.io/espnet-tts-sample/). Here we list some notable ones: - [Single English speaker Tacotron2](https://drive.google.com/open?id=18JgsOCWiP_JkhONasTplnHS7yaF_konr) - [Single Japanese speaker Tacotron2](https://drive.google.com/open?id=1fEgS4-K4dtgVxwI4Pr7uOA1h4PE-zN7f) - [Single other language speaker Tacotron2](https://drive.google.com/open?id=1q_66kyxVZGU99g8Xb5a0Q8yZ1YVm2tN0) - [Multi English speaker Tacotron2](https://drive.google.com/open?id=18S_B8Ogogij34rIfJOeNF8D--uG7amz2) - [Single English speaker Transformer](https://drive.google.com/open?id=14EboYVsMVcAq__dFP1p6lyoZtdobIL1X) - [Single English speaker FastSpeech](https://drive.google.com/open?id=1PSxs1VauIndwi8d5hJmZlppGRVu2zuy5) - [Multi English speaker Transformer](https://drive.google.com/open?id=1_vrdqjM43DdN1Qz7HJkvMQ6lCMmWLeGp) - [Single Italian speaker FastSpeech](https://drive.google.com/open?id=13I5V2w7deYFX4DlVk1-0JfaXmUR2rNOv) - [Single Mandarin speaker Transformer](https://drive.google.com/open?id=1mEnZfBKqA4eT6Bn0eRZuP6lNzL-IL3VD) - [Single Mandarin speaker FastSpeech](https://drive.google.com/open?id=1Ol_048Tuy6BgvYm1RpjhOX4HfhUeBqdK) - [Multi Japanese speaker Transformer](https://drive.google.com/open?id=1fFMQDF6NV5Ysz48QLFYE8fEvbAxCsMBw) - [Single English speaker models with Parallel WaveGAN](https://drive.google.com/open?id=1HvB0_LDf1PVinJdehiuCt5gWmXGguqtx) - [Single English speaker knowledge distillation-based FastSpeech](https://drive.google.com/open?id=1wG-Y0itVYalxuLAHdkAHO7w1CWFfRPF4) You can download all of the pretrained models and generated samples: - [All of the pretrained E2E-TTS models](https://drive.google.com/open?id=1k9RRyc06Zl0mM2A7mi-hxNiNMFb_YzTF) - [All of the generated samples](https://drive.google.com/open?id=1bQGuqH92xuxOX__reWLP4-cif0cbpMLX) Note that in the generated samples we use the following vocoders: Griffin-Lim (**GL**), WaveNet vocoder (**WaveNet**), Parallel WaveGAN (**ParallelWaveGAN**), and MelGAN (**MelGAN**). The neural vocoders are based on following repositories. - [kan-bayashi/ParallelWaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN): Parallel WaveGAN / MelGAN / Multi-band MelGAN - [r9y9/wavenet_vocoder](https://github.com/r9y9/wavenet_vocoder): 16 bit mixture of Logistics WaveNet vocoder - [kan-bayashi/PytorchWaveNetVocoder](https://github.com/kan-bayashi/PytorchWaveNetVocoder): 8 bit Softmax WaveNet Vocoder with the noise shaping If you want to build your own neural vocoder, please check the above repositories. [kan-bayashi/ParallelWaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) provides [the manual](https://github.com/kan-bayashi/ParallelWaveGAN#decoding-with-espnet-tts-models-features) about how to decode ESPnet-TTS model's features with neural vocoders. Please check it. Here we list all of the pretrained neural vocoders. Please download and enjoy the generation of high quality speech! | Model link | Lang | Fs [Hz] | Mel range [Hz] | FFT / Shift / Win [pt] | Model type | | :--------------------------------------------------------------------------------------------------- | :---: | :-----: | :------------: | :--------------------: | :---------------------------------------------------------------------- | | [ljspeech.wavenet.softmax.ns.v1](https://drive.google.com/open?id=1eA1VcRS9jzFa-DovyTgJLQ_jmwOLIi8L) | EN | 22.05k | None | 1024 / 256 / None | [Softmax WaveNet](https://github.com/kan-bayashi/PytorchWaveNetVocoder) | | [ljspeech.wavenet.mol.v1](https://drive.google.com/open?id=1sY7gEUg39QaO1szuN62-Llst9TrFno2t) | EN | 22.05k | None | 1024 / 256 / None | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [ljspeech.parallel_wavegan.v1](https://drive.google.com/open?id=1tv9GKyRT4CDsvUWKwH3s_OfXkiTi0gw7) | EN | 22.05k | None | 1024 / 256 / None | [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [ljspeech.wavenet.mol.v2](https://drive.google.com/open?id=1es2HuKUeKVtEdq6YDtAsLNpqCy4fhIXr) | EN | 22.05k | 80-7600 | 1024 / 256 / None | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [ljspeech.parallel_wavegan.v2](https://drive.google.com/open?id=1Grn7X9wD35UcDJ5F7chwdTqTa4U7DeVB) | EN | 22.05k | 80-7600 | 1024 / 256 / None | [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [ljspeech.melgan.v1](https://drive.google.com/open?id=1ipPWYl8FBNRlBFaKj1-i23eQpW_W_YcR) | EN | 22.05k | 80-7600 | 1024 / 256 / None | [MelGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [ljspeech.melgan.v3](https://drive.google.com/open?id=1_a8faVA5OGCzIcJNw4blQYjfG4oA9VEt) | EN | 22.05k | 80-7600 | 1024 / 256 / None | [MelGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [libritts.wavenet.mol.v1](https://drive.google.com/open?id=1jHUUmQFjWiQGyDd7ZeiCThSjjpbF_B4h) | EN | 24k | None | 1024 / 256 / None | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [jsut.wavenet.mol.v1](https://drive.google.com/open?id=187xvyNbmJVZ0EZ1XHCdyjZHTXK9EcfkK) | JP | 24k | 80-7600 | 2048 / 300 / 1200 | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [jsut.parallel_wavegan.v1](https://drive.google.com/open?id=1OwrUQzAmvjj1x9cDhnZPp6dqtsEqGEJM) | JP | 24k | 80-7600 | 2048 / 300 / 1200 | [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [csmsc.wavenet.mol.v1](https://drive.google.com/open?id=1PsjFRV5eUP0HHwBaRYya9smKy5ghXKzj) | ZH | 24k | 80-7600 | 2048 / 300 / 1200 | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [csmsc.parallel_wavegan.v1](https://drive.google.com/open?id=10M6H88jEUGbRWBmU1Ff2VaTmOAeL8CEy) | ZH | 24k | 80-7600 | 2048 / 300 / 1200 | [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | If you want to use the above pretrained vocoders, please exactly match the feature setting with them.
### TTS demo
ESPnet2
You can try the real-time demo in Google Colab. Please access the notebook from the following button and enjoy the real-time synthesis! - Real-time TTS demo with ESPnet2 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/espnet/notebook/blob/master/espnet2_tts_realtime_demo.ipynb) English, Japanese, and Mandarin models are available in the demo.
ESPnet1
> NOTE: We are moving on ESPnet2-based development for TTS. Please check the latest demo in the above ESPnet2 demo. You can try the real-time demo in Google Colab. Please access the notebook from the following button and enjoy the real-time synthesis. - Real-time TTS demo with ESPnet1 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/espnet/notebook/blob/master/tts_realtime_demo.ipynb) We also provide shell script to perform synthesize. Go to a recipe directory and run `utils/synth_wav.sh` as follows: ```sh # 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 ``` You can change the pretrained model as follows: ```sh synth_wav.sh --models ljspeech.fastspeech.v1 example.txt ``` Waveform synthesis is performed with Griffin-Lim algorithm and neural vocoders (WaveNet and ParallelWaveGAN). You can change the pretrained vocoder model as follows: ```sh synth_wav.sh --vocoder_models ljspeech.wavenet.mol.v1 example.txt ``` WaveNet vocoder provides very high quality speech but it takes time to generate. See more details or available models via `--help`. ```sh synth_wav.sh --help ```
### VC results
expand
- Transformer and Tacotron2 based VC You can listen to some samples on the [demo webpage](https://unilight.github.io/Publication-Demos/publications/transformer-vc/). - Cascade ASR+TTS as one of the baseline systems of VCC2020 The [Voice Conversion Challenge 2020](http://www.vc-challenge.org/) (VCC2020) adopts ESPnet to build an end-to-end based baseline system. In VCC2020, the objective is intra/cross lingual nonparallel VC. You can download converted samples of the cascade ASR+TTS baseline system [here](https://drive.google.com/drive/folders/1oeZo83GrOgtqxGwF7KagzIrfjr8X59Ue?usp=sharing).
### SLU results
expand
We list the performance on various SLU tasks and dataset using the metric reported in the original dataset paper | Task | Dataset | Metric | Result | Pretrained Model | | ----------------------------------------------------------------- | :-------------: | :-------------: | :-------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | | Intent Classification | SLURP | Acc | 86.3 | [link](https://github.com/espnet/espnet/tree/master/egs2/slurp/asr1/README.md) | | Intent Classification | FSC | Acc | 99.6 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc/asr1/README.md) | | Intent Classification | FSC Unseen Speaker Set | Acc | 98.6 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc_unseen/asr1/README.md) | | Intent Classification | FSC Unseen Utterance Set | Acc | 86.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc_unseen/asr1/README.md) | | Intent Classification | FSC Challenge Speaker Set | Acc | 97.5 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc_challenge/asr1/README.md) | | Intent Classification | FSC Challenge Utterance Set | Acc | 78.5 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc_challenge/asr1/README.md) | | Intent Classification | SNIPS | F1 | 91.7 | [link](https://github.com/espnet/espnet/tree/master/egs2/snips/asr1/README.md) | | Intent Classification | Grabo (Nl) | Acc | 97.2 | [link](https://github.com/espnet/espnet/tree/master/egs2/grabo/asr1/README.md) | | Intent Classification | CAT SLU MAP (Zn) | Acc | 78.9 | [link](https://github.com/espnet/espnet/tree/master/egs2/catslu/asr1/README.md) | | Intent Classification | Google Speech Commands | Acc | 98.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/speechcommands/asr1/README.md) | | Slot Filling | SLURP | SLU-F1 | 71.9 | [link](https://github.com/espnet/espnet/tree/master/egs2/slurp_entity/asr1/README.md) | | Dialogue Act Classification | Switchboard | Acc | 67.5 | [link](https://github.com/espnet/espnet/tree/master/egs2/swbd_da/asr1/README.md) | | Dialogue Act Classification | Jdcinal (Jp) | Acc | 67.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/jdcinal/asr1/README.md) | | Emotion Recognition | IEMOCAP | Acc | 69.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/iemocap/asr1/README.md) | | Emotion Recognition | swbd_sentiment | Macro F1 | 61.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/swbd_sentiment/asr1/README.md) | | Emotion Recognition | slue_voxceleb | Macro F1 | 44.0 | [link](https://github.com/espnet/espnet/tree/master/egs2/slue-voxceleb/asr1/README.md) | If you want to check the results of the other recipes, please check `egs2//asr1/RESULTS.md`.
### CTC Segmentation demo
ESPnet1
[CTC segmentation](https://arxiv.org/abs/2007.09127) determines utterance segments within audio files. Aligned utterance segments constitute the labels of speech datasets. As demo, we align start and end of utterances within the audio file `ctc_align_test.wav`, using the example script `utils/asr_align_wav.sh`. For preparation, set up a data directory: ```sh 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 ``` Here, `utt_text` is the file containing the list of utterances. Choose a pre-trained ASR model that includes a CTC layer to find utterance segments: ```sh # pre-trained ASR model model=wsj.transformer_small.v1 mkdir ./conf && cp ../../wsj/asr1/conf/no_preprocess.yaml ./conf --models ${model} \ --align_dir ${align_dir} \ --align_config ${align_dir}/align.yaml \ ${wav} ${align_dir}/utt_text ``` Segments are written to `aligned_segments` as a list of file/utterance name, utterance start and end times in seconds and a confidence score. The confidence score is a probability in log space that indicates how good the utterance was aligned. If needed, remove bad utterances: ```sh min_confidence_score=-5 awk -v ms=${min_confidence_score} '{ if ($5 > ms) {print} }' ${align_dir}/aligned_segments ``` The demo script `utils/ctc_align_wav.sh` uses an already pretrained ASR model (see list above for more models). It is recommended to use models with RNN-based encoders (such as BLSTMP) for aligning large audio files; rather than using Transformer models that have a high memory consumption on longer audio data. The sample rate of the audio must be consistent with that of the data used in training; adjust with `sox` if needed. A full example recipe is in `egs/tedlium2/align1/`.
ESPnet2
[CTC segmentation](https://arxiv.org/abs/2007.09127) determines utterance segments within audio files. Aligned utterance segments constitute the labels of speech datasets. As demo, we align start and end of utterances within the audio file `ctc_align_test.wav`. This can be done either directly from the Python command line or using the script `espnet2/bin/asr_align.py`. From the Python command line interface: ```python # 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 ``` Aligning also works with fragments of the text. For this, set the `gratis_blank` option that allows skipping unrelated audio sections without penalty. It's also possible to omit the utterance names at the beginning of each line, by setting `kaldi_style_text` to False. ```python 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 ``` The script `espnet2/bin/asr_align.py` uses a similar interface. To align utterances: ```sh # ASR model and config files from pretrained model (e.g. from cachedir): asr_config=/config.yaml asr_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 ${text} # utt1 ctc_align_test 0.26 1.73 -0.0154 THE SALE OF THE HOTELS # utt2 ctc_align_test 1.73 3.19 -0.7674 IS PART OF HOLIDAY'S STRATEGY # utt3 ctc_align_test 3.19 4.20 -0.7433 TO SELL OFF ASSETS # utt4 ctc_align_test 4.20 4.97 -0.6017 AND CONCENTRATE # utt5 ctc_align_test 4.97 6.10 -0.3477 ON PROPERTY MANAGEMENT ``` The output of the script can be redirected to a `segments` file by adding the argument `--output segments`. Each line contains file/utterance name, utterance start and end times in seconds and a confidence score; optionally also the utterance text. The confidence score is a probability in log space that indicates how good the utterance was aligned. If needed, remove bad utterances: ```sh min_confidence_score=-7 # here, we assume that the output was written to the file `segments` awk -v ms=${min_confidence_score} '{ if ($5 > ms) {print} }' segments ``` See the module documentation for more information. It is recommended to use models with RNN-based encoders (such as BLSTMP) for aligning large audio files; rather than using Transformer models that have a high memory consumption on longer audio data. The sample rate of the audio must be consistent with that of the data used in training; adjust with `sox` if needed. Also, we can use this tool to provide token-level segmentation information if we prepare a list of tokens instead of that of utterances in the `text` file. See the discussion in https://github.com/espnet/espnet/issues/4278#issuecomment-1100756463.
## 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} } ``` %package -n python3-espnet Summary: ESPnet: end-to-end speech processing toolkit Provides: python-espnet BuildRequires: python3-devel BuildRequires: python3-setuptools BuildRequires: python3-pip %description -n python3-espnet You can translate speech in a WAV file using pretrained models. Go to a recipe directory and run `utils/translate_wav.sh` as follows: ```sh # 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 ``` where `test.wav` is a WAV file to be translated. The sampling rate must be consistent with that of data used in training. Available pretrained models in the demo script are listed as below. | Model | Notes | | :----------------------------------------------------------------------------------------------------------- | :------------------------------------------------------- | | [fisher_callhome_spanish.transformer.v1](https://drive.google.com/open?id=1hawp5ZLw4_SIHIT3edglxbKIIkPVe8n3) | Transformer-ST trained on Fisher-CallHome Spanish Es->En | ### MT results
expand
| Task | BLEU | Pretrained model | | ------------------------------------------------- | :---: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------: | | Fisher-CallHome Spanish fisher_test (Es->En) | 61.45 | [link](https://github.com/espnet/espnet/blob/master/egs/fisher_callhome_spanish/mt1/RESULTS.md#trainen_lcrm_lcrm_pytorch_train_pytorch_transformer_bpe_bpe1000) | | Fisher-CallHome Spanish callhome_evltest (Es->En) | 29.86 | [link](https://github.com/espnet/espnet/blob/master/egs/fisher_callhome_spanish/mt1/RESULTS.md#trainen_lcrm_lcrm_pytorch_train_pytorch_transformer_bpe_bpe1000) | | Libri-trans test (En->Fr) | 18.09 | [link](https://github.com/espnet/espnet/blob/master/egs/libri_trans/mt1/RESULTS.md#trainfr_lcrm_tc_pytorch_train_pytorch_transformer_bpe1000) | | How2 dev5 (En->Pt) | 58.61 | [link](https://github.com/espnet/espnet/blob/master/egs/how2/mt1/RESULTS.md#trainpt_tc_tc_pytorch_train_pytorch_transformer_bpe8000) | | Must-C tst-COMMON (En->De) | 27.63 | [link](https://github.com/espnet/espnet/blob/master/egs/must_c/mt1/RESULTS.md#summary-4-gram-bleu) | | IWSLT'14 test2014 (En->De) | 24.70 | [link](https://github.com/espnet/espnet/blob/master/egs/iwslt16/mt1/RESULTS.md#result) | | IWSLT'14 test2014 (De->En) | 29.22 | [link](https://github.com/espnet/espnet/blob/master/egs/iwslt16/mt1/RESULTS.md#result) | | IWSLT'14 test2014 (De->En) | 32.2 | [link](https://github.com/espnet/espnet/blob/master/egs2/iwslt14/mt1/README.md) | | IWSLT'16 test2014 (En->De) | 24.05 | [link](https://github.com/espnet/espnet/blob/master/egs/iwslt16/mt1/RESULTS.md#result) | | IWSLT'16 test2014 (De->En) | 29.13 | [link](https://github.com/espnet/espnet/blob/master/egs/iwslt16/mt1/RESULTS.md#result) |
### TTS results
ESPnet2
You can listen to the generated samples in the following URL. - [ESPnet2 TTS generated samples](https://drive.google.com/drive/folders/1H3fnlBbWMEkQUfrHqosKN_ZX_WjO29ma?usp=sharing) > Note that in the generation we use Griffin-Lim (`wav/`) and [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) (`wav_pwg/`). You can download pretrained models via `espnet_model_zoo`. - [ESPnet model zoo](https://github.com/espnet/espnet_model_zoo) - [Pretrained model list](https://github.com/espnet/espnet_model_zoo/blob/master/espnet_model_zoo/table.csv) You can download pretrained vocoders via `kan-bayashi/ParallelWaveGAN`. - [kan-bayashi/ParallelWaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) - [Pretrained vocoder list](https://github.com/kan-bayashi/ParallelWaveGAN#results)
ESPnet1
> NOTE: We are moving on ESPnet2-based development for TTS. Please check the latest results in the above ESPnet2 results. You can listen to our samples in demo HP [espnet-tts-sample](https://espnet.github.io/espnet-tts-sample/). Here we list some notable ones: - [Single English speaker Tacotron2](https://drive.google.com/open?id=18JgsOCWiP_JkhONasTplnHS7yaF_konr) - [Single Japanese speaker Tacotron2](https://drive.google.com/open?id=1fEgS4-K4dtgVxwI4Pr7uOA1h4PE-zN7f) - [Single other language speaker Tacotron2](https://drive.google.com/open?id=1q_66kyxVZGU99g8Xb5a0Q8yZ1YVm2tN0) - [Multi English speaker Tacotron2](https://drive.google.com/open?id=18S_B8Ogogij34rIfJOeNF8D--uG7amz2) - [Single English speaker Transformer](https://drive.google.com/open?id=14EboYVsMVcAq__dFP1p6lyoZtdobIL1X) - [Single English speaker FastSpeech](https://drive.google.com/open?id=1PSxs1VauIndwi8d5hJmZlppGRVu2zuy5) - [Multi English speaker Transformer](https://drive.google.com/open?id=1_vrdqjM43DdN1Qz7HJkvMQ6lCMmWLeGp) - [Single Italian speaker FastSpeech](https://drive.google.com/open?id=13I5V2w7deYFX4DlVk1-0JfaXmUR2rNOv) - [Single Mandarin speaker Transformer](https://drive.google.com/open?id=1mEnZfBKqA4eT6Bn0eRZuP6lNzL-IL3VD) - [Single Mandarin speaker FastSpeech](https://drive.google.com/open?id=1Ol_048Tuy6BgvYm1RpjhOX4HfhUeBqdK) - [Multi Japanese speaker Transformer](https://drive.google.com/open?id=1fFMQDF6NV5Ysz48QLFYE8fEvbAxCsMBw) - [Single English speaker models with Parallel WaveGAN](https://drive.google.com/open?id=1HvB0_LDf1PVinJdehiuCt5gWmXGguqtx) - [Single English speaker knowledge distillation-based FastSpeech](https://drive.google.com/open?id=1wG-Y0itVYalxuLAHdkAHO7w1CWFfRPF4) You can download all of the pretrained models and generated samples: - [All of the pretrained E2E-TTS models](https://drive.google.com/open?id=1k9RRyc06Zl0mM2A7mi-hxNiNMFb_YzTF) - [All of the generated samples](https://drive.google.com/open?id=1bQGuqH92xuxOX__reWLP4-cif0cbpMLX) Note that in the generated samples we use the following vocoders: Griffin-Lim (**GL**), WaveNet vocoder (**WaveNet**), Parallel WaveGAN (**ParallelWaveGAN**), and MelGAN (**MelGAN**). The neural vocoders are based on following repositories. - [kan-bayashi/ParallelWaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN): Parallel WaveGAN / MelGAN / Multi-band MelGAN - [r9y9/wavenet_vocoder](https://github.com/r9y9/wavenet_vocoder): 16 bit mixture of Logistics WaveNet vocoder - [kan-bayashi/PytorchWaveNetVocoder](https://github.com/kan-bayashi/PytorchWaveNetVocoder): 8 bit Softmax WaveNet Vocoder with the noise shaping If you want to build your own neural vocoder, please check the above repositories. [kan-bayashi/ParallelWaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) provides [the manual](https://github.com/kan-bayashi/ParallelWaveGAN#decoding-with-espnet-tts-models-features) about how to decode ESPnet-TTS model's features with neural vocoders. Please check it. Here we list all of the pretrained neural vocoders. Please download and enjoy the generation of high quality speech! | Model link | Lang | Fs [Hz] | Mel range [Hz] | FFT / Shift / Win [pt] | Model type | | :--------------------------------------------------------------------------------------------------- | :---: | :-----: | :------------: | :--------------------: | :---------------------------------------------------------------------- | | [ljspeech.wavenet.softmax.ns.v1](https://drive.google.com/open?id=1eA1VcRS9jzFa-DovyTgJLQ_jmwOLIi8L) | EN | 22.05k | None | 1024 / 256 / None | [Softmax WaveNet](https://github.com/kan-bayashi/PytorchWaveNetVocoder) | | [ljspeech.wavenet.mol.v1](https://drive.google.com/open?id=1sY7gEUg39QaO1szuN62-Llst9TrFno2t) | EN | 22.05k | None | 1024 / 256 / None | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [ljspeech.parallel_wavegan.v1](https://drive.google.com/open?id=1tv9GKyRT4CDsvUWKwH3s_OfXkiTi0gw7) | EN | 22.05k | None | 1024 / 256 / None | [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [ljspeech.wavenet.mol.v2](https://drive.google.com/open?id=1es2HuKUeKVtEdq6YDtAsLNpqCy4fhIXr) | EN | 22.05k | 80-7600 | 1024 / 256 / None | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [ljspeech.parallel_wavegan.v2](https://drive.google.com/open?id=1Grn7X9wD35UcDJ5F7chwdTqTa4U7DeVB) | EN | 22.05k | 80-7600 | 1024 / 256 / None | [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [ljspeech.melgan.v1](https://drive.google.com/open?id=1ipPWYl8FBNRlBFaKj1-i23eQpW_W_YcR) | EN | 22.05k | 80-7600 | 1024 / 256 / None | [MelGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [ljspeech.melgan.v3](https://drive.google.com/open?id=1_a8faVA5OGCzIcJNw4blQYjfG4oA9VEt) | EN | 22.05k | 80-7600 | 1024 / 256 / None | [MelGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [libritts.wavenet.mol.v1](https://drive.google.com/open?id=1jHUUmQFjWiQGyDd7ZeiCThSjjpbF_B4h) | EN | 24k | None | 1024 / 256 / None | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [jsut.wavenet.mol.v1](https://drive.google.com/open?id=187xvyNbmJVZ0EZ1XHCdyjZHTXK9EcfkK) | JP | 24k | 80-7600 | 2048 / 300 / 1200 | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [jsut.parallel_wavegan.v1](https://drive.google.com/open?id=1OwrUQzAmvjj1x9cDhnZPp6dqtsEqGEJM) | JP | 24k | 80-7600 | 2048 / 300 / 1200 | [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [csmsc.wavenet.mol.v1](https://drive.google.com/open?id=1PsjFRV5eUP0HHwBaRYya9smKy5ghXKzj) | ZH | 24k | 80-7600 | 2048 / 300 / 1200 | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [csmsc.parallel_wavegan.v1](https://drive.google.com/open?id=10M6H88jEUGbRWBmU1Ff2VaTmOAeL8CEy) | ZH | 24k | 80-7600 | 2048 / 300 / 1200 | [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | If you want to use the above pretrained vocoders, please exactly match the feature setting with them.
### TTS demo
ESPnet2
You can try the real-time demo in Google Colab. Please access the notebook from the following button and enjoy the real-time synthesis! - Real-time TTS demo with ESPnet2 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/espnet/notebook/blob/master/espnet2_tts_realtime_demo.ipynb) English, Japanese, and Mandarin models are available in the demo.
ESPnet1
> NOTE: We are moving on ESPnet2-based development for TTS. Please check the latest demo in the above ESPnet2 demo. You can try the real-time demo in Google Colab. Please access the notebook from the following button and enjoy the real-time synthesis. - Real-time TTS demo with ESPnet1 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/espnet/notebook/blob/master/tts_realtime_demo.ipynb) We also provide shell script to perform synthesize. Go to a recipe directory and run `utils/synth_wav.sh` as follows: ```sh # 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 ``` You can change the pretrained model as follows: ```sh synth_wav.sh --models ljspeech.fastspeech.v1 example.txt ``` Waveform synthesis is performed with Griffin-Lim algorithm and neural vocoders (WaveNet and ParallelWaveGAN). You can change the pretrained vocoder model as follows: ```sh synth_wav.sh --vocoder_models ljspeech.wavenet.mol.v1 example.txt ``` WaveNet vocoder provides very high quality speech but it takes time to generate. See more details or available models via `--help`. ```sh synth_wav.sh --help ```
### VC results
expand
- Transformer and Tacotron2 based VC You can listen to some samples on the [demo webpage](https://unilight.github.io/Publication-Demos/publications/transformer-vc/). - Cascade ASR+TTS as one of the baseline systems of VCC2020 The [Voice Conversion Challenge 2020](http://www.vc-challenge.org/) (VCC2020) adopts ESPnet to build an end-to-end based baseline system. In VCC2020, the objective is intra/cross lingual nonparallel VC. You can download converted samples of the cascade ASR+TTS baseline system [here](https://drive.google.com/drive/folders/1oeZo83GrOgtqxGwF7KagzIrfjr8X59Ue?usp=sharing).
### SLU results
expand
We list the performance on various SLU tasks and dataset using the metric reported in the original dataset paper | Task | Dataset | Metric | Result | Pretrained Model | | ----------------------------------------------------------------- | :-------------: | :-------------: | :-------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | | Intent Classification | SLURP | Acc | 86.3 | [link](https://github.com/espnet/espnet/tree/master/egs2/slurp/asr1/README.md) | | Intent Classification | FSC | Acc | 99.6 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc/asr1/README.md) | | Intent Classification | FSC Unseen Speaker Set | Acc | 98.6 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc_unseen/asr1/README.md) | | Intent Classification | FSC Unseen Utterance Set | Acc | 86.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc_unseen/asr1/README.md) | | Intent Classification | FSC Challenge Speaker Set | Acc | 97.5 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc_challenge/asr1/README.md) | | Intent Classification | FSC Challenge Utterance Set | Acc | 78.5 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc_challenge/asr1/README.md) | | Intent Classification | SNIPS | F1 | 91.7 | [link](https://github.com/espnet/espnet/tree/master/egs2/snips/asr1/README.md) | | Intent Classification | Grabo (Nl) | Acc | 97.2 | [link](https://github.com/espnet/espnet/tree/master/egs2/grabo/asr1/README.md) | | Intent Classification | CAT SLU MAP (Zn) | Acc | 78.9 | [link](https://github.com/espnet/espnet/tree/master/egs2/catslu/asr1/README.md) | | Intent Classification | Google Speech Commands | Acc | 98.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/speechcommands/asr1/README.md) | | Slot Filling | SLURP | SLU-F1 | 71.9 | [link](https://github.com/espnet/espnet/tree/master/egs2/slurp_entity/asr1/README.md) | | Dialogue Act Classification | Switchboard | Acc | 67.5 | [link](https://github.com/espnet/espnet/tree/master/egs2/swbd_da/asr1/README.md) | | Dialogue Act Classification | Jdcinal (Jp) | Acc | 67.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/jdcinal/asr1/README.md) | | Emotion Recognition | IEMOCAP | Acc | 69.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/iemocap/asr1/README.md) | | Emotion Recognition | swbd_sentiment | Macro F1 | 61.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/swbd_sentiment/asr1/README.md) | | Emotion Recognition | slue_voxceleb | Macro F1 | 44.0 | [link](https://github.com/espnet/espnet/tree/master/egs2/slue-voxceleb/asr1/README.md) | If you want to check the results of the other recipes, please check `egs2//asr1/RESULTS.md`.
### CTC Segmentation demo
ESPnet1
[CTC segmentation](https://arxiv.org/abs/2007.09127) determines utterance segments within audio files. Aligned utterance segments constitute the labels of speech datasets. As demo, we align start and end of utterances within the audio file `ctc_align_test.wav`, using the example script `utils/asr_align_wav.sh`. For preparation, set up a data directory: ```sh 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 ``` Here, `utt_text` is the file containing the list of utterances. Choose a pre-trained ASR model that includes a CTC layer to find utterance segments: ```sh # pre-trained ASR model model=wsj.transformer_small.v1 mkdir ./conf && cp ../../wsj/asr1/conf/no_preprocess.yaml ./conf --models ${model} \ --align_dir ${align_dir} \ --align_config ${align_dir}/align.yaml \ ${wav} ${align_dir}/utt_text ``` Segments are written to `aligned_segments` as a list of file/utterance name, utterance start and end times in seconds and a confidence score. The confidence score is a probability in log space that indicates how good the utterance was aligned. If needed, remove bad utterances: ```sh min_confidence_score=-5 awk -v ms=${min_confidence_score} '{ if ($5 > ms) {print} }' ${align_dir}/aligned_segments ``` The demo script `utils/ctc_align_wav.sh` uses an already pretrained ASR model (see list above for more models). It is recommended to use models with RNN-based encoders (such as BLSTMP) for aligning large audio files; rather than using Transformer models that have a high memory consumption on longer audio data. The sample rate of the audio must be consistent with that of the data used in training; adjust with `sox` if needed. A full example recipe is in `egs/tedlium2/align1/`.
ESPnet2
[CTC segmentation](https://arxiv.org/abs/2007.09127) determines utterance segments within audio files. Aligned utterance segments constitute the labels of speech datasets. As demo, we align start and end of utterances within the audio file `ctc_align_test.wav`. This can be done either directly from the Python command line or using the script `espnet2/bin/asr_align.py`. From the Python command line interface: ```python # 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 ``` Aligning also works with fragments of the text. For this, set the `gratis_blank` option that allows skipping unrelated audio sections without penalty. It's also possible to omit the utterance names at the beginning of each line, by setting `kaldi_style_text` to False. ```python 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 ``` The script `espnet2/bin/asr_align.py` uses a similar interface. To align utterances: ```sh # ASR model and config files from pretrained model (e.g. from cachedir): asr_config=/config.yaml asr_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 ${text} # utt1 ctc_align_test 0.26 1.73 -0.0154 THE SALE OF THE HOTELS # utt2 ctc_align_test 1.73 3.19 -0.7674 IS PART OF HOLIDAY'S STRATEGY # utt3 ctc_align_test 3.19 4.20 -0.7433 TO SELL OFF ASSETS # utt4 ctc_align_test 4.20 4.97 -0.6017 AND CONCENTRATE # utt5 ctc_align_test 4.97 6.10 -0.3477 ON PROPERTY MANAGEMENT ``` The output of the script can be redirected to a `segments` file by adding the argument `--output segments`. Each line contains file/utterance name, utterance start and end times in seconds and a confidence score; optionally also the utterance text. The confidence score is a probability in log space that indicates how good the utterance was aligned. If needed, remove bad utterances: ```sh min_confidence_score=-7 # here, we assume that the output was written to the file `segments` awk -v ms=${min_confidence_score} '{ if ($5 > ms) {print} }' segments ``` See the module documentation for more information. It is recommended to use models with RNN-based encoders (such as BLSTMP) for aligning large audio files; rather than using Transformer models that have a high memory consumption on longer audio data. The sample rate of the audio must be consistent with that of the data used in training; adjust with `sox` if needed. Also, we can use this tool to provide token-level segmentation information if we prepare a list of tokens instead of that of utterances in the `text` file. See the discussion in https://github.com/espnet/espnet/issues/4278#issuecomment-1100756463.
## 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} } ``` %package help Summary: Development documents and examples for espnet Provides: python3-espnet-doc %description help You can translate speech in a WAV file using pretrained models. Go to a recipe directory and run `utils/translate_wav.sh` as follows: ```sh # 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 ``` where `test.wav` is a WAV file to be translated. The sampling rate must be consistent with that of data used in training. Available pretrained models in the demo script are listed as below. | Model | Notes | | :----------------------------------------------------------------------------------------------------------- | :------------------------------------------------------- | | [fisher_callhome_spanish.transformer.v1](https://drive.google.com/open?id=1hawp5ZLw4_SIHIT3edglxbKIIkPVe8n3) | Transformer-ST trained on Fisher-CallHome Spanish Es->En | ### MT results
expand
| Task | BLEU | Pretrained model | | ------------------------------------------------- | :---: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------: | | Fisher-CallHome Spanish fisher_test (Es->En) | 61.45 | [link](https://github.com/espnet/espnet/blob/master/egs/fisher_callhome_spanish/mt1/RESULTS.md#trainen_lcrm_lcrm_pytorch_train_pytorch_transformer_bpe_bpe1000) | | Fisher-CallHome Spanish callhome_evltest (Es->En) | 29.86 | [link](https://github.com/espnet/espnet/blob/master/egs/fisher_callhome_spanish/mt1/RESULTS.md#trainen_lcrm_lcrm_pytorch_train_pytorch_transformer_bpe_bpe1000) | | Libri-trans test (En->Fr) | 18.09 | [link](https://github.com/espnet/espnet/blob/master/egs/libri_trans/mt1/RESULTS.md#trainfr_lcrm_tc_pytorch_train_pytorch_transformer_bpe1000) | | How2 dev5 (En->Pt) | 58.61 | [link](https://github.com/espnet/espnet/blob/master/egs/how2/mt1/RESULTS.md#trainpt_tc_tc_pytorch_train_pytorch_transformer_bpe8000) | | Must-C tst-COMMON (En->De) | 27.63 | [link](https://github.com/espnet/espnet/blob/master/egs/must_c/mt1/RESULTS.md#summary-4-gram-bleu) | | IWSLT'14 test2014 (En->De) | 24.70 | [link](https://github.com/espnet/espnet/blob/master/egs/iwslt16/mt1/RESULTS.md#result) | | IWSLT'14 test2014 (De->En) | 29.22 | [link](https://github.com/espnet/espnet/blob/master/egs/iwslt16/mt1/RESULTS.md#result) | | IWSLT'14 test2014 (De->En) | 32.2 | [link](https://github.com/espnet/espnet/blob/master/egs2/iwslt14/mt1/README.md) | | IWSLT'16 test2014 (En->De) | 24.05 | [link](https://github.com/espnet/espnet/blob/master/egs/iwslt16/mt1/RESULTS.md#result) | | IWSLT'16 test2014 (De->En) | 29.13 | [link](https://github.com/espnet/espnet/blob/master/egs/iwslt16/mt1/RESULTS.md#result) |
### TTS results
ESPnet2
You can listen to the generated samples in the following URL. - [ESPnet2 TTS generated samples](https://drive.google.com/drive/folders/1H3fnlBbWMEkQUfrHqosKN_ZX_WjO29ma?usp=sharing) > Note that in the generation we use Griffin-Lim (`wav/`) and [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) (`wav_pwg/`). You can download pretrained models via `espnet_model_zoo`. - [ESPnet model zoo](https://github.com/espnet/espnet_model_zoo) - [Pretrained model list](https://github.com/espnet/espnet_model_zoo/blob/master/espnet_model_zoo/table.csv) You can download pretrained vocoders via `kan-bayashi/ParallelWaveGAN`. - [kan-bayashi/ParallelWaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) - [Pretrained vocoder list](https://github.com/kan-bayashi/ParallelWaveGAN#results)
ESPnet1
> NOTE: We are moving on ESPnet2-based development for TTS. Please check the latest results in the above ESPnet2 results. You can listen to our samples in demo HP [espnet-tts-sample](https://espnet.github.io/espnet-tts-sample/). Here we list some notable ones: - [Single English speaker Tacotron2](https://drive.google.com/open?id=18JgsOCWiP_JkhONasTplnHS7yaF_konr) - [Single Japanese speaker Tacotron2](https://drive.google.com/open?id=1fEgS4-K4dtgVxwI4Pr7uOA1h4PE-zN7f) - [Single other language speaker Tacotron2](https://drive.google.com/open?id=1q_66kyxVZGU99g8Xb5a0Q8yZ1YVm2tN0) - [Multi English speaker Tacotron2](https://drive.google.com/open?id=18S_B8Ogogij34rIfJOeNF8D--uG7amz2) - [Single English speaker Transformer](https://drive.google.com/open?id=14EboYVsMVcAq__dFP1p6lyoZtdobIL1X) - [Single English speaker FastSpeech](https://drive.google.com/open?id=1PSxs1VauIndwi8d5hJmZlppGRVu2zuy5) - [Multi English speaker Transformer](https://drive.google.com/open?id=1_vrdqjM43DdN1Qz7HJkvMQ6lCMmWLeGp) - [Single Italian speaker FastSpeech](https://drive.google.com/open?id=13I5V2w7deYFX4DlVk1-0JfaXmUR2rNOv) - [Single Mandarin speaker Transformer](https://drive.google.com/open?id=1mEnZfBKqA4eT6Bn0eRZuP6lNzL-IL3VD) - [Single Mandarin speaker FastSpeech](https://drive.google.com/open?id=1Ol_048Tuy6BgvYm1RpjhOX4HfhUeBqdK) - [Multi Japanese speaker Transformer](https://drive.google.com/open?id=1fFMQDF6NV5Ysz48QLFYE8fEvbAxCsMBw) - [Single English speaker models with Parallel WaveGAN](https://drive.google.com/open?id=1HvB0_LDf1PVinJdehiuCt5gWmXGguqtx) - [Single English speaker knowledge distillation-based FastSpeech](https://drive.google.com/open?id=1wG-Y0itVYalxuLAHdkAHO7w1CWFfRPF4) You can download all of the pretrained models and generated samples: - [All of the pretrained E2E-TTS models](https://drive.google.com/open?id=1k9RRyc06Zl0mM2A7mi-hxNiNMFb_YzTF) - [All of the generated samples](https://drive.google.com/open?id=1bQGuqH92xuxOX__reWLP4-cif0cbpMLX) Note that in the generated samples we use the following vocoders: Griffin-Lim (**GL**), WaveNet vocoder (**WaveNet**), Parallel WaveGAN (**ParallelWaveGAN**), and MelGAN (**MelGAN**). The neural vocoders are based on following repositories. - [kan-bayashi/ParallelWaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN): Parallel WaveGAN / MelGAN / Multi-band MelGAN - [r9y9/wavenet_vocoder](https://github.com/r9y9/wavenet_vocoder): 16 bit mixture of Logistics WaveNet vocoder - [kan-bayashi/PytorchWaveNetVocoder](https://github.com/kan-bayashi/PytorchWaveNetVocoder): 8 bit Softmax WaveNet Vocoder with the noise shaping If you want to build your own neural vocoder, please check the above repositories. [kan-bayashi/ParallelWaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) provides [the manual](https://github.com/kan-bayashi/ParallelWaveGAN#decoding-with-espnet-tts-models-features) about how to decode ESPnet-TTS model's features with neural vocoders. Please check it. Here we list all of the pretrained neural vocoders. Please download and enjoy the generation of high quality speech! | Model link | Lang | Fs [Hz] | Mel range [Hz] | FFT / Shift / Win [pt] | Model type | | :--------------------------------------------------------------------------------------------------- | :---: | :-----: | :------------: | :--------------------: | :---------------------------------------------------------------------- | | [ljspeech.wavenet.softmax.ns.v1](https://drive.google.com/open?id=1eA1VcRS9jzFa-DovyTgJLQ_jmwOLIi8L) | EN | 22.05k | None | 1024 / 256 / None | [Softmax WaveNet](https://github.com/kan-bayashi/PytorchWaveNetVocoder) | | [ljspeech.wavenet.mol.v1](https://drive.google.com/open?id=1sY7gEUg39QaO1szuN62-Llst9TrFno2t) | EN | 22.05k | None | 1024 / 256 / None | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [ljspeech.parallel_wavegan.v1](https://drive.google.com/open?id=1tv9GKyRT4CDsvUWKwH3s_OfXkiTi0gw7) | EN | 22.05k | None | 1024 / 256 / None | [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [ljspeech.wavenet.mol.v2](https://drive.google.com/open?id=1es2HuKUeKVtEdq6YDtAsLNpqCy4fhIXr) | EN | 22.05k | 80-7600 | 1024 / 256 / None | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [ljspeech.parallel_wavegan.v2](https://drive.google.com/open?id=1Grn7X9wD35UcDJ5F7chwdTqTa4U7DeVB) | EN | 22.05k | 80-7600 | 1024 / 256 / None | [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [ljspeech.melgan.v1](https://drive.google.com/open?id=1ipPWYl8FBNRlBFaKj1-i23eQpW_W_YcR) | EN | 22.05k | 80-7600 | 1024 / 256 / None | [MelGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [ljspeech.melgan.v3](https://drive.google.com/open?id=1_a8faVA5OGCzIcJNw4blQYjfG4oA9VEt) | EN | 22.05k | 80-7600 | 1024 / 256 / None | [MelGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [libritts.wavenet.mol.v1](https://drive.google.com/open?id=1jHUUmQFjWiQGyDd7ZeiCThSjjpbF_B4h) | EN | 24k | None | 1024 / 256 / None | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [jsut.wavenet.mol.v1](https://drive.google.com/open?id=187xvyNbmJVZ0EZ1XHCdyjZHTXK9EcfkK) | JP | 24k | 80-7600 | 2048 / 300 / 1200 | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [jsut.parallel_wavegan.v1](https://drive.google.com/open?id=1OwrUQzAmvjj1x9cDhnZPp6dqtsEqGEJM) | JP | 24k | 80-7600 | 2048 / 300 / 1200 | [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | | [csmsc.wavenet.mol.v1](https://drive.google.com/open?id=1PsjFRV5eUP0HHwBaRYya9smKy5ghXKzj) | ZH | 24k | 80-7600 | 2048 / 300 / 1200 | [MoL WaveNet](https://github.com/r9y9/wavenet_vocoder) | | [csmsc.parallel_wavegan.v1](https://drive.google.com/open?id=10M6H88jEUGbRWBmU1Ff2VaTmOAeL8CEy) | ZH | 24k | 80-7600 | 2048 / 300 / 1200 | [Parallel WaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN) | If you want to use the above pretrained vocoders, please exactly match the feature setting with them.
### TTS demo
ESPnet2
You can try the real-time demo in Google Colab. Please access the notebook from the following button and enjoy the real-time synthesis! - Real-time TTS demo with ESPnet2 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/espnet/notebook/blob/master/espnet2_tts_realtime_demo.ipynb) English, Japanese, and Mandarin models are available in the demo.
ESPnet1
> NOTE: We are moving on ESPnet2-based development for TTS. Please check the latest demo in the above ESPnet2 demo. You can try the real-time demo in Google Colab. Please access the notebook from the following button and enjoy the real-time synthesis. - Real-time TTS demo with ESPnet1 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/espnet/notebook/blob/master/tts_realtime_demo.ipynb) We also provide shell script to perform synthesize. Go to a recipe directory and run `utils/synth_wav.sh` as follows: ```sh # 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 ``` You can change the pretrained model as follows: ```sh synth_wav.sh --models ljspeech.fastspeech.v1 example.txt ``` Waveform synthesis is performed with Griffin-Lim algorithm and neural vocoders (WaveNet and ParallelWaveGAN). You can change the pretrained vocoder model as follows: ```sh synth_wav.sh --vocoder_models ljspeech.wavenet.mol.v1 example.txt ``` WaveNet vocoder provides very high quality speech but it takes time to generate. See more details or available models via `--help`. ```sh synth_wav.sh --help ```
### VC results
expand
- Transformer and Tacotron2 based VC You can listen to some samples on the [demo webpage](https://unilight.github.io/Publication-Demos/publications/transformer-vc/). - Cascade ASR+TTS as one of the baseline systems of VCC2020 The [Voice Conversion Challenge 2020](http://www.vc-challenge.org/) (VCC2020) adopts ESPnet to build an end-to-end based baseline system. In VCC2020, the objective is intra/cross lingual nonparallel VC. You can download converted samples of the cascade ASR+TTS baseline system [here](https://drive.google.com/drive/folders/1oeZo83GrOgtqxGwF7KagzIrfjr8X59Ue?usp=sharing).
### SLU results
expand
We list the performance on various SLU tasks and dataset using the metric reported in the original dataset paper | Task | Dataset | Metric | Result | Pretrained Model | | ----------------------------------------------------------------- | :-------------: | :-------------: | :-------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | | Intent Classification | SLURP | Acc | 86.3 | [link](https://github.com/espnet/espnet/tree/master/egs2/slurp/asr1/README.md) | | Intent Classification | FSC | Acc | 99.6 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc/asr1/README.md) | | Intent Classification | FSC Unseen Speaker Set | Acc | 98.6 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc_unseen/asr1/README.md) | | Intent Classification | FSC Unseen Utterance Set | Acc | 86.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc_unseen/asr1/README.md) | | Intent Classification | FSC Challenge Speaker Set | Acc | 97.5 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc_challenge/asr1/README.md) | | Intent Classification | FSC Challenge Utterance Set | Acc | 78.5 | [link](https://github.com/espnet/espnet/tree/master/egs2/fsc_challenge/asr1/README.md) | | Intent Classification | SNIPS | F1 | 91.7 | [link](https://github.com/espnet/espnet/tree/master/egs2/snips/asr1/README.md) | | Intent Classification | Grabo (Nl) | Acc | 97.2 | [link](https://github.com/espnet/espnet/tree/master/egs2/grabo/asr1/README.md) | | Intent Classification | CAT SLU MAP (Zn) | Acc | 78.9 | [link](https://github.com/espnet/espnet/tree/master/egs2/catslu/asr1/README.md) | | Intent Classification | Google Speech Commands | Acc | 98.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/speechcommands/asr1/README.md) | | Slot Filling | SLURP | SLU-F1 | 71.9 | [link](https://github.com/espnet/espnet/tree/master/egs2/slurp_entity/asr1/README.md) | | Dialogue Act Classification | Switchboard | Acc | 67.5 | [link](https://github.com/espnet/espnet/tree/master/egs2/swbd_da/asr1/README.md) | | Dialogue Act Classification | Jdcinal (Jp) | Acc | 67.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/jdcinal/asr1/README.md) | | Emotion Recognition | IEMOCAP | Acc | 69.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/iemocap/asr1/README.md) | | Emotion Recognition | swbd_sentiment | Macro F1 | 61.4 | [link](https://github.com/espnet/espnet/tree/master/egs2/swbd_sentiment/asr1/README.md) | | Emotion Recognition | slue_voxceleb | Macro F1 | 44.0 | [link](https://github.com/espnet/espnet/tree/master/egs2/slue-voxceleb/asr1/README.md) | If you want to check the results of the other recipes, please check `egs2//asr1/RESULTS.md`.
### CTC Segmentation demo
ESPnet1
[CTC segmentation](https://arxiv.org/abs/2007.09127) determines utterance segments within audio files. Aligned utterance segments constitute the labels of speech datasets. As demo, we align start and end of utterances within the audio file `ctc_align_test.wav`, using the example script `utils/asr_align_wav.sh`. For preparation, set up a data directory: ```sh 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 ``` Here, `utt_text` is the file containing the list of utterances. Choose a pre-trained ASR model that includes a CTC layer to find utterance segments: ```sh # pre-trained ASR model model=wsj.transformer_small.v1 mkdir ./conf && cp ../../wsj/asr1/conf/no_preprocess.yaml ./conf --models ${model} \ --align_dir ${align_dir} \ --align_config ${align_dir}/align.yaml \ ${wav} ${align_dir}/utt_text ``` Segments are written to `aligned_segments` as a list of file/utterance name, utterance start and end times in seconds and a confidence score. The confidence score is a probability in log space that indicates how good the utterance was aligned. If needed, remove bad utterances: ```sh min_confidence_score=-5 awk -v ms=${min_confidence_score} '{ if ($5 > ms) {print} }' ${align_dir}/aligned_segments ``` The demo script `utils/ctc_align_wav.sh` uses an already pretrained ASR model (see list above for more models). It is recommended to use models with RNN-based encoders (such as BLSTMP) for aligning large audio files; rather than using Transformer models that have a high memory consumption on longer audio data. The sample rate of the audio must be consistent with that of the data used in training; adjust with `sox` if needed. A full example recipe is in `egs/tedlium2/align1/`.
ESPnet2
[CTC segmentation](https://arxiv.org/abs/2007.09127) determines utterance segments within audio files. Aligned utterance segments constitute the labels of speech datasets. As demo, we align start and end of utterances within the audio file `ctc_align_test.wav`. This can be done either directly from the Python command line or using the script `espnet2/bin/asr_align.py`. From the Python command line interface: ```python # 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 ``` Aligning also works with fragments of the text. For this, set the `gratis_blank` option that allows skipping unrelated audio sections without penalty. It's also possible to omit the utterance names at the beginning of each line, by setting `kaldi_style_text` to False. ```python 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 ``` The script `espnet2/bin/asr_align.py` uses a similar interface. To align utterances: ```sh # ASR model and config files from pretrained model (e.g. from cachedir): asr_config=/config.yaml asr_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 ${text} # utt1 ctc_align_test 0.26 1.73 -0.0154 THE SALE OF THE HOTELS # utt2 ctc_align_test 1.73 3.19 -0.7674 IS PART OF HOLIDAY'S STRATEGY # utt3 ctc_align_test 3.19 4.20 -0.7433 TO SELL OFF ASSETS # utt4 ctc_align_test 4.20 4.97 -0.6017 AND CONCENTRATE # utt5 ctc_align_test 4.97 6.10 -0.3477 ON PROPERTY MANAGEMENT ``` The output of the script can be redirected to a `segments` file by adding the argument `--output segments`. Each line contains file/utterance name, utterance start and end times in seconds and a confidence score; optionally also the utterance text. The confidence score is a probability in log space that indicates how good the utterance was aligned. If needed, remove bad utterances: ```sh min_confidence_score=-7 # here, we assume that the output was written to the file `segments` awk -v ms=${min_confidence_score} '{ if ($5 > ms) {print} }' segments ``` See the module documentation for more information. It is recommended to use models with RNN-based encoders (such as BLSTMP) for aligning large audio files; rather than using Transformer models that have a high memory consumption on longer audio data. The sample rate of the audio must be consistent with that of the data used in training; adjust with `sox` if needed. Also, we can use this tool to provide token-level segmentation information if we prepare a list of tokens instead of that of utterances in the `text` file. See the discussion in https://github.com/espnet/espnet/issues/4278#issuecomment-1100756463.
## 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} } ``` %prep %autosetup -n espnet-202304 %build %py3_build %install %py3_install install -d -m755 %{buildroot}/%{_pkgdocdir} if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi pushd %{buildroot} if [ -d usr/lib ]; then find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst fi if [ -d usr/lib64 ]; then find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst fi if [ -d usr/bin ]; then find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst fi if [ -d usr/sbin ]; then find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst fi touch doclist.lst if [ -d usr/share/man ]; then find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst fi popd mv %{buildroot}/filelist.lst . mv %{buildroot}/doclist.lst . %files -n python3-espnet -f filelist.lst %dir %{python3_sitelib}/* %files help -f doclist.lst %{_docdir}/* %changelog * Fri May 05 2023 Python_Bot - 202304-1 - Package Spec generated