Skip to main content
Tutorials
Full ESPnet installation
ESPnet2
ESPnet1
Training configurations
Recipe tips
Audio formatting
Task class and data input system
Docker
Job scheduling system
Distributed training
Document Generation
ESPnet3
Docs hub
Provider / Runner
Dataset pipeline
Data preparation
System entry point
Recipe layout
Callbacks
Optimizer configuration
Multiple optimizers & schedulers
Multi-GPU / multi-node
Evaluation
Config
Demos
Roadmap
ESPnet2
Demo
Course
ESPnet1 (Legacy)
ESPnet1
Recipes
What is a recipe template?
Automatic Speech Recognition (Multi-tasking)
Automatic Speech Recognition with Discrete Units
Speaker Verification Spoofing and Countermeasures
Classification
Speech Codec
Speaker Diarisation
Speech Enhancement
Speech Recognition with Speech Enhancement
Speaker Diarisation with Speech Enhancement
Speech-to-Text Translation with Speech Enhancement
Self-supervised Learning
Language Identification
Language Modeling
Machine Translation
Speech-to-Speech Translation
Weakly-supervised Learning (Speech-to-Text)
ESPnet-SDS
Spoken Language Understanding
Speech Language Model
Speaker Representation
Self-supervised Learning
Speech-to-Text Translation
Singing Voice Synthesis
ESPnet2 SVS2 Recipe TEMPLATE
Text-to-Speech
Text-to-Speech with Discrete Units
Unsupervised Automatic Speech Recognition
Python API
espnet2
asr
asr_transducer
asvspoof
cls
diar
enh
fileio
fst
gan_codec
gan_svs
gan_tts
hubert
iterators
layers
legacy
lid
lm
main_funcs
mt
optimizers
ps2st
s2st
s2t
samplers
schedulers
sds
slu
speechlm
spk
ssl
st
svs
tasks
text
torch_utils
train
tts
tts2
uasr
utils
espnet3
components
parallel
systems
utils
Shell API
espnet2_bin
spm
utils
utils_py
Search
Ctrl
K
Legacy
Less than 1 minute
Catalog
espnet2.legacy.nets.batch_beam_search_online_sim.BatchBeamSearchOnlineSim
espnet2.legacy.nets.batch_beam_search_online.BatchBeamSearchOnline
espnet2.legacy.nets.batch_beam_search.BatchBeamSearch
espnet2.legacy.nets.batch_beam_search.BatchHypothesis
espnet2.legacy.nets.beam_search_partially_AR.PartiallyARBeamSearch
espnet2.legacy.nets.beam_search_partially_AR.PartiallyARHypothesis
espnet2.legacy.nets.beam_search_timesync_streaming.BeamSearchTimeSyncStreaming
espnet2.legacy.nets.beam_search_timesync_streaming.CacheItem
espnet2.legacy.nets.beam_search_timesync.BeamSearchTimeSync
espnet2.legacy.nets.beam_search.beam_search
espnet2.legacy.nets.beam_search.BeamSearch
espnet2.legacy.nets.ctc_prefix_score.CTCPrefixScore
espnet2.legacy.nets.ctc_prefix_score.CTCPrefixScoreTH
espnet2.legacy.nets.e2e_asr_common.end_detect
espnet2.legacy.nets.e2e_asr_common.get_vgg2l_odim
espnet2.legacy.nets.e2e_mt_common.ErrorCalculator
espnet2.legacy.nets.pytorch_backend.conformer.convolution.ConvolutionModule
espnet2.legacy.nets.pytorch_backend.conformer.swish.Swish
espnet2.legacy.nets.pytorch_backend.e2e_tts_fastspeech.FeedForwardTransformerLoss
espnet2.legacy.nets.pytorch_backend.e2e_tts_tacotron2.GuidedAttentionLoss
espnet2.legacy.nets.pytorch_backend.e2e_tts_tacotron2.Tacotron2Loss
espnet2.legacy.nets.pytorch_backend.e2e_tts_transformer.GuidedMultiHeadAttentionLoss
espnet2.legacy.nets.pytorch_backend.fastspeech.duration_predictor.DurationPredictor
espnet2.legacy.nets.pytorch_backend.fastspeech.duration_predictor.DurationPredictorLoss
espnet2.legacy.nets.pytorch_backend.fastspeech.length_regulator.LengthRegulator
espnet2.legacy.nets.pytorch_backend.frontends.frontend.Frontend
espnet2.legacy.nets.pytorch_backend.frontends.frontend.frontend_for
espnet2.legacy.nets.pytorch_backend.gtn_ctc.GTNCTCLossFunction
espnet2.legacy.nets.pytorch_backend.maskctc.add_mask_token.mask_uniform
espnet2.legacy.nets.pytorch_backend.nets_utils.get_activation
espnet2.legacy.nets.pytorch_backend.nets_utils.get_subsample
espnet2.legacy.nets.pytorch_backend.nets_utils.make_non_pad_mask
espnet2.legacy.nets.pytorch_backend.nets_utils.make_pad_mask
espnet2.legacy.nets.pytorch_backend.nets_utils.mask_by_length
espnet2.legacy.nets.pytorch_backend.nets_utils.pad_list
espnet2.legacy.nets.pytorch_backend.nets_utils.rename_state_dict
espnet2.legacy.nets.pytorch_backend.nets_utils.roll_tensor
espnet2.legacy.nets.pytorch_backend.nets_utils.th_accuracy
espnet2.legacy.nets.pytorch_backend.nets_utils.to_device
espnet2.legacy.nets.pytorch_backend.nets_utils.to_torch_tensor
espnet2.legacy.nets.pytorch_backend.nets_utils.trim_by_ctc_posterior
espnet2.legacy.nets.pytorch_backend.nets_utils.triu_onnx
espnet2.legacy.nets.pytorch_backend.rnn.attentions.att_for
espnet2.legacy.nets.pytorch_backend.rnn.attentions.att_to_numpy
espnet2.legacy.nets.pytorch_backend.rnn.attentions.AttAdd
espnet2.legacy.nets.pytorch_backend.rnn.attentions.AttCov
espnet2.legacy.nets.pytorch_backend.rnn.attentions.AttCovLoc
espnet2.legacy.nets.pytorch_backend.rnn.attentions.AttDot
espnet2.legacy.nets.pytorch_backend.rnn.attentions.AttForward
espnet2.legacy.nets.pytorch_backend.rnn.attentions.AttForwardTA
espnet2.legacy.nets.pytorch_backend.rnn.attentions.AttLoc
espnet2.legacy.nets.pytorch_backend.rnn.attentions.AttLoc2D
espnet2.legacy.nets.pytorch_backend.rnn.attentions.AttLocRec
espnet2.legacy.nets.pytorch_backend.rnn.attentions.AttMultiHeadAdd
espnet2.legacy.nets.pytorch_backend.rnn.attentions.AttMultiHeadDot
espnet2.legacy.nets.pytorch_backend.rnn.attentions.AttMultiHeadLoc
espnet2.legacy.nets.pytorch_backend.rnn.attentions.AttMultiHeadMultiResLoc
espnet2.legacy.nets.pytorch_backend.rnn.attentions.GDCAttLoc
espnet2.legacy.nets.pytorch_backend.rnn.attentions.initial_att
espnet2.legacy.nets.pytorch_backend.rnn.attentions.NoAtt
espnet2.legacy.nets.pytorch_backend.rnn.encoders.encoder_for
espnet2.legacy.nets.pytorch_backend.rnn.encoders.reset_backward_rnn_state
espnet2.legacy.nets.pytorch_backend.rnn.encoders.RNN
espnet2.legacy.nets.pytorch_backend.rnn.encoders.RNNP
espnet2.legacy.nets.pytorch_backend.tacotron2.decoder.decoder_init
espnet2.legacy.nets.pytorch_backend.tacotron2.decoder.Postnet
espnet2.legacy.nets.pytorch_backend.tacotron2.decoder.Prenet
espnet2.legacy.nets.pytorch_backend.tacotron2.decoder.ZoneOutCell
espnet2.legacy.nets.pytorch_backend.tacotron2.encoder.encoder_init
espnet2.legacy.nets.pytorch_backend.transducer.blocks.build_blocks
espnet2.legacy.nets.pytorch_backend.transducer.blocks.build_conformer_block
espnet2.legacy.nets.pytorch_backend.transducer.blocks.build_conv1d_block
espnet2.legacy.nets.pytorch_backend.transducer.blocks.build_input_layer
espnet2.legacy.nets.pytorch_backend.transducer.blocks.build_transformer_block
espnet2.legacy.nets.pytorch_backend.transducer.blocks.get_pos_enc_and_att_class
espnet2.legacy.nets.pytorch_backend.transducer.blocks.prepare_body_model
espnet2.legacy.nets.pytorch_backend.transducer.blocks.prepare_input_layer
espnet2.legacy.nets.pytorch_backend.transducer.blocks.verify_block_arguments
espnet2.legacy.nets.pytorch_backend.transducer.conv1d_nets.Conv1d
espnet2.legacy.nets.pytorch_backend.transducer.custom_decoder.CustomDecoder
espnet2.legacy.nets.pytorch_backend.transducer.joint_network.JointNetwork
espnet2.legacy.nets.pytorch_backend.transducer.rnn_decoder.RNNDecoder
espnet2.legacy.nets.pytorch_backend.transducer.transformer_decoder_layer.TransformerDecoderLayer
espnet2.legacy.nets.pytorch_backend.transducer.utils.check_batch_states
espnet2.legacy.nets.pytorch_backend.transducer.utils.check_state
espnet2.legacy.nets.pytorch_backend.transducer.utils.create_lm_batch_states
espnet2.legacy.nets.pytorch_backend.transducer.utils.custom_torch_load
espnet2.legacy.nets.pytorch_backend.transducer.utils.get_decoder_input
espnet2.legacy.nets.pytorch_backend.transducer.utils.init_lm_state
espnet2.legacy.nets.pytorch_backend.transducer.utils.is_prefix
espnet2.legacy.nets.pytorch_backend.transducer.utils.pad_sequence
espnet2.legacy.nets.pytorch_backend.transducer.utils.recombine_hyps
espnet2.legacy.nets.pytorch_backend.transducer.utils.select_k_expansions
espnet2.legacy.nets.pytorch_backend.transducer.utils.select_lm_state
espnet2.legacy.nets.pytorch_backend.transducer.utils.subtract
espnet2.legacy.nets.pytorch_backend.transducer.utils.valid_aux_encoder_output_layers
espnet2.legacy.nets.pytorch_backend.transducer.vgg2l.VGG2L
espnet2.legacy.nets.pytorch_backend.transformer.add_sos_eos.add_sos_eos
espnet2.legacy.nets.pytorch_backend.transformer.attention.LegacyRelPositionMultiHeadedAttention
espnet2.legacy.nets.pytorch_backend.transformer.attention.MultiHeadedAttention
espnet2.legacy.nets.pytorch_backend.transformer.attention.RelPositionMultiHeadedAttention
espnet2.legacy.nets.pytorch_backend.transformer.contextual_block_encoder_layer.ContextualBlockEncoderLayer
espnet2.legacy.nets.pytorch_backend.transformer.decoder_layer.DecoderLayer
espnet2.legacy.nets.pytorch_backend.transformer.decoder.Decoder
espnet2.legacy.nets.pytorch_backend.transformer.dynamic_conv.DynamicConvolution
espnet2.legacy.nets.pytorch_backend.transformer.dynamic_conv2d.DynamicConvolution2D
espnet2.legacy.nets.pytorch_backend.transformer.embedding.ConvolutionalPositionalEmbedding
espnet2.legacy.nets.pytorch_backend.transformer.embedding.LearnableFourierPosEnc
espnet2.legacy.nets.pytorch_backend.transformer.embedding.LegacyRelPositionalEncoding
espnet2.legacy.nets.pytorch_backend.transformer.embedding.PositionalEncoding
espnet2.legacy.nets.pytorch_backend.transformer.embedding.RelPositionalEncoding
espnet2.legacy.nets.pytorch_backend.transformer.embedding.ScaledPositionalEncoding
espnet2.legacy.nets.pytorch_backend.transformer.embedding.StreamPositionalEncoding
espnet2.legacy.nets.pytorch_backend.transformer.encoder_layer.EncoderLayer
espnet2.legacy.nets.pytorch_backend.transformer.encoder.Encoder
espnet2.legacy.nets.pytorch_backend.transformer.label_smoothing_loss.LabelSmoothingLoss
espnet2.legacy.nets.pytorch_backend.transformer.layer_norm.LayerNorm
espnet2.legacy.nets.pytorch_backend.transformer.lightconv.LightweightConvolution
espnet2.legacy.nets.pytorch_backend.transformer.lightconv2d.LightweightConvolution2D
espnet2.legacy.nets.pytorch_backend.transformer.longformer_attention.LongformerAttention
espnet2.legacy.nets.pytorch_backend.transformer.mask.subsequent_mask
espnet2.legacy.nets.pytorch_backend.transformer.multi_layer_conv.Conv1dLinear
espnet2.legacy.nets.pytorch_backend.transformer.multi_layer_conv.MultiLayeredConv1d
espnet2.legacy.nets.pytorch_backend.transformer.positionwise_feed_forward.PositionwiseFeedForward
espnet2.legacy.nets.pytorch_backend.transformer.repeat.MultiSequential
espnet2.legacy.nets.pytorch_backend.transformer.repeat.repeat
espnet2.legacy.nets.pytorch_backend.transformer.subsampling_without_posenc.Conv2dSubsamplingWOPosEnc
espnet2.legacy.nets.pytorch_backend.transformer.subsampling.check_short_utt
espnet2.legacy.nets.pytorch_backend.transformer.subsampling.Conv1dSubsampling1
espnet2.legacy.nets.pytorch_backend.transformer.subsampling.Conv1dSubsampling2
espnet2.legacy.nets.pytorch_backend.transformer.subsampling.Conv1dSubsampling3
espnet2.legacy.nets.pytorch_backend.transformer.subsampling.Conv2dSubsampling
espnet2.legacy.nets.pytorch_backend.transformer.subsampling.Conv2dSubsampling1
espnet2.legacy.nets.pytorch_backend.transformer.subsampling.Conv2dSubsampling2
espnet2.legacy.nets.pytorch_backend.transformer.subsampling.Conv2dSubsampling6
espnet2.legacy.nets.pytorch_backend.transformer.subsampling.Conv2dSubsampling8
espnet2.legacy.nets.pytorch_backend.transformer.subsampling.TooShortUttError
espnet2.legacy.nets.pytorch_backend.wavenet.CausalConv1d
espnet2.legacy.nets.pytorch_backend.wavenet.decode_mu_law
espnet2.legacy.nets.pytorch_backend.wavenet.encode_mu_law
espnet2.legacy.nets.pytorch_backend.wavenet.initialize
espnet2.legacy.nets.pytorch_backend.wavenet.OneHot
espnet2.legacy.nets.pytorch_backend.wavenet.UpSampling
espnet2.legacy.nets.pytorch_backend.wavenet.WaveNet
espnet2.legacy.nets.scorer_interface.BatchPartialScorerInterface
espnet2.legacy.nets.scorer_interface.BatchScorerInterface
espnet2.legacy.nets.scorer_interface.MaskParallelScorerInterface
espnet2.legacy.nets.scorer_interface.PartialScorerInterface
espnet2.legacy.nets.scorer_interface.ScorerInterface
espnet2.legacy.nets.scorers.ctc.CTCPrefixScorer
espnet2.legacy.nets.scorers.length_bonus.LengthBonus
espnet2.legacy.nets.scorers.ngram.Ngrambase
espnet2.legacy.nets.scorers.ngram.NgramFullScorer
espnet2.legacy.nets.scorers.ngram.NgramPartScorer
espnet2.legacy.nets.scorers.uasr.UASRPrefixScorer
espnet2.legacy.nets.transducer_decoder_interface.ExtendedHypothesis
espnet2.legacy.nets.transducer_decoder_interface.Hypothesis
espnet2.legacy.nets.transducer_decoder_interface.TransducerDecoderInterface
espnet2.legacy.transform.add_deltas.add_deltas
espnet2.legacy.transform.add_deltas.AddDeltas
espnet2.legacy.transform.add_deltas.delta
espnet2.legacy.transform.channel_selector.ChannelSelector
espnet2.legacy.transform.cmvn.CMVN
espnet2.legacy.transform.cmvn.UtteranceCMVN
espnet2.legacy.transform.functional.FuncTrans
espnet2.legacy.transform.perturb.BandpassPerturbation
espnet2.legacy.transform.perturb.NoiseInjection
espnet2.legacy.transform.perturb.RIRConvolve
espnet2.legacy.transform.perturb.SpeedPerturbation
espnet2.legacy.transform.perturb.VolumePerturbation
espnet2.legacy.transform.spec_augment.freq_mask
espnet2.legacy.transform.spec_augment.FreqMask
espnet2.legacy.transform.spec_augment.spec_augment
espnet2.legacy.transform.spec_augment.SpecAugment
espnet2.legacy.transform.spec_augment.time_mask
espnet2.legacy.transform.spec_augment.time_warp
espnet2.legacy.transform.spec_augment.TimeMask
espnet2.legacy.transform.spec_augment.TimeWarp
espnet2.legacy.transform.spectrogram.IStft
espnet2.legacy.transform.spectrogram.LogMelSpectrogram
espnet2.legacy.transform.spectrogram.Spectrogram
espnet2.legacy.transform.spectrogram.Stft
espnet2.legacy.transform.spectrogram.Stft2LogMelSpectrogram
espnet2.legacy.transform.transform_interface.Identity
espnet2.legacy.transform.transform_interface.TransformInterface
espnet2.legacy.transform.transformation.Transformation
espnet2.legacy.transform.wpe.WPE
espnet2.legacy.utils.cli_readers.file_reader_helper
espnet2.legacy.utils.cli_readers.HDF5Reader
espnet2.legacy.utils.cli_readers.KaldiReader
espnet2.legacy.utils.cli_readers.SoundHDF5Reader
espnet2.legacy.utils.cli_readers.SoundReader
espnet2.legacy.utils.cli_utils.assert_scipy_wav_style
espnet2.legacy.utils.cli_utils.get_commandline_args
espnet2.legacy.utils.cli_utils.is_scipy_wav_style
espnet2.legacy.utils.cli_writers.BaseWriter
espnet2.legacy.utils.cli_writers.file_writer_helper
espnet2.legacy.utils.cli_writers.get_num_frames_writer
espnet2.legacy.utils.cli_writers.HDF5Writer
espnet2.legacy.utils.cli_writers.KaldiWriter
espnet2.legacy.utils.cli_writers.parse_wspecifier
espnet2.legacy.utils.cli_writers.SoundHDF5Writer
espnet2.legacy.utils.cli_writers.SoundWriter
espnet2.legacy.utils.dummy_chainer.Evaluator
espnet2.legacy.utils.dummy_chainer.Extension
espnet2.legacy.utils.dummy_chainer.Iterator
espnet2.legacy.utils.dummy_chainer.MultiprocessIterator
espnet2.legacy.utils.dummy_chainer.Reporter
espnet2.legacy.utils.dummy_chainer.SerialIterator
espnet2.legacy.utils.dummy_chainer.StandardUpdater
espnet2.legacy.utils.dynamic_import.dynamic_import
espnet2.legacy.utils.io_utils.SoundHDF5File
Prev
Layers
Next
Lid