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
Demos
Roadmap
ESPnet2
Demo
Course
ESPnet-EZ
ESPnet EZ
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 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
espnet
asr
distributed
lm
mt
nets
optimizer
scheduler
st
transform
tts
utils
vc
espnet2
asr
asr_transducer
asvspoof
cls
diar
enh
fileio
fst
gan_codec
gan_svs
gan_tts
hubert
iterators
layers
lm
main_funcs
mt
optimizers
s2st
s2t
samplers
schedulers
sds
slu
speechlm
spk
ssl
st
svs
tasks
text
torch_utils
train
tts
tts2
uasr
utils
espnetez
config
data
dataloader
dataset
preprocess
task
trainer
Shell API
espnet2_bin
espnet_bin
spm
utils
utils_py
Search
Ctrl
K
Enh
Less than 1 minute
Catalog
espnet2.enh.abs_enh.AbsEnhancement
espnet2.enh.decoder.abs_decoder.AbsDecoder
espnet2.enh.decoder.conv_decoder.ConvDecoder
espnet2.enh.decoder.null_decoder.NullDecoder
espnet2.enh.decoder.stft_decoder.STFTDecoder
espnet2.enh.diffusion_enh.ESPnetDiffusionModel
espnet2.enh.diffusion.abs_diffusion.AbsDiffusion
espnet2.enh.diffusion.sampling.correctors.AnnealedLangevinDynamics
espnet2.enh.diffusion.sampling.correctors.Corrector
espnet2.enh.diffusion.sampling.correctors.LangevinCorrector
espnet2.enh.diffusion.sampling.correctors.NoneCorrector
espnet2.enh.diffusion.sampling.predictors.EulerMaruyamaPredictor
espnet2.enh.diffusion.sampling.predictors.NonePredictor
espnet2.enh.diffusion.sampling.predictors.Predictor
espnet2.enh.diffusion.sampling.predictors.ReverseDiffusionPredictor
espnet2.enh.diffusion.score_based_diffusion.ScoreModel
espnet2.enh.diffusion.sdes.batch_broadcast
espnet2.enh.diffusion.sdes.OUVESDE
espnet2.enh.diffusion.sdes.OUVPSDE
espnet2.enh.diffusion.sdes.SDE
espnet2.enh.encoder.abs_encoder.AbsEncoder
espnet2.enh.encoder.conv_encoder.ConvEncoder
espnet2.enh.encoder.null_encoder.NullEncoder
espnet2.enh.encoder.stft_encoder.STFTEncoder
espnet2.enh.espnet_enh_s2t_model.ESPnetEnhS2TModel
espnet2.enh.espnet_model_tse.ESPnetExtractionModel
espnet2.enh.espnet_model.ESPnetEnhancementModel
espnet2.enh.extractor.abs_extractor.AbsExtractor
espnet2.enh.extractor.td_speakerbeam_extractor.TDSpeakerBeamExtractor
espnet2.enh.layers.adapt_layers.ConcatAdaptLayer
espnet2.enh.layers.adapt_layers.into_orig_type
espnet2.enh.layers.adapt_layers.into_tuple
espnet2.enh.layers.adapt_layers.make_adapt_layer
espnet2.enh.layers.adapt_layers.MulAddAdaptLayer
espnet2.enh.layers.beamformer.apply_beamforming_vector
espnet2.enh.layers.beamformer.blind_analytic_normalization
espnet2.enh.layers.beamformer.generalized_eigenvalue_decomposition
espnet2.enh.layers.beamformer.get_covariances
espnet2.enh.layers.beamformer.get_gev_vector
espnet2.enh.layers.beamformer.get_lcmv_vector_with_rtf
espnet2.enh.layers.beamformer.get_mvdr_vector
espnet2.enh.layers.beamformer.get_mvdr_vector_with_rtf
espnet2.enh.layers.beamformer.get_mwf_vector
espnet2.enh.layers.beamformer.get_power_spectral_density_matrix
espnet2.enh.layers.beamformer.get_rank1_mwf_vector
espnet2.enh.layers.beamformer.get_rtf
espnet2.enh.layers.beamformer.get_rtf_matrix
espnet2.enh.layers.beamformer.get_sdw_mwf_vector
espnet2.enh.layers.beamformer.get_WPD_filter
espnet2.enh.layers.beamformer.get_WPD_filter_v2
espnet2.enh.layers.beamformer.get_WPD_filter_with_rtf
espnet2.enh.layers.beamformer.gev_phase_correction
espnet2.enh.layers.beamformer.perform_WPD_filtering
espnet2.enh.layers.beamformer.prepare_beamformer_stats
espnet2.enh.layers.beamformer.signal_framing
espnet2.enh.layers.beamformer.tik_reg
espnet2.enh.layers.bsrnn.BandSplit
espnet2.enh.layers.bsrnn.BSRNN
espnet2.enh.layers.bsrnn.ChannelFreqwiseLayerNorm
espnet2.enh.layers.bsrnn.ChannelwiseLayerNorm
espnet2.enh.layers.bsrnn.choose_norm
espnet2.enh.layers.bsrnn.get_erb_subbands
espnet2.enh.layers.bsrnn.get_mel_subbands
espnet2.enh.layers.bsrnn.MaskDecoder
espnet2.enh.layers.complex_utils.cat
espnet2.enh.layers.complex_utils.complex_norm
espnet2.enh.layers.complex_utils.einsum
espnet2.enh.layers.complex_utils.inverse
espnet2.enh.layers.complex_utils.is_complex
espnet2.enh.layers.complex_utils.is_torch_complex_tensor
espnet2.enh.layers.complex_utils.matmul
espnet2.enh.layers.complex_utils.new_complex_like
espnet2.enh.layers.complex_utils.reverse
espnet2.enh.layers.complex_utils.solve
espnet2.enh.layers.complex_utils.stack
espnet2.enh.layers.complex_utils.to_complex
espnet2.enh.layers.complex_utils.to_double
espnet2.enh.layers.complex_utils.to_float
espnet2.enh.layers.complex_utils.trace
espnet2.enh.layers.complexnn.complex_cat
espnet2.enh.layers.complexnn.ComplexConv2d
espnet2.enh.layers.complexnn.ComplexConvTranspose2d
espnet2.enh.layers.complexnn.NavieComplexLSTM
espnet2.enh.layers.conv_utils.conv2d_output_shape
espnet2.enh.layers.conv_utils.convtransp2d_output_shape
espnet2.enh.layers.conv_utils.num2tuple
espnet2.enh.layers.dc_crn.DC_CRN
espnet2.enh.layers.dc_crn.DenselyConnectedBlock
espnet2.enh.layers.dc_crn.GLSTM
espnet2.enh.layers.dc_crn.GluConv2d
espnet2.enh.layers.dc_crn.GluConvTranspose2d
espnet2.enh.layers.dcunet.ArgsComplexMultiplicationWrapper
espnet2.enh.layers.dcunet.BatchNorm
espnet2.enh.layers.dcunet.ComplexBatchNorm
espnet2.enh.layers.dcunet.ComplexLinear
espnet2.enh.layers.dcunet.DCUNet
espnet2.enh.layers.dcunet.DCUNetComplexDecoderBlock
espnet2.enh.layers.dcunet.DCUNetComplexEncoderBlock
espnet2.enh.layers.dcunet.DiffusionStepEmbedding
espnet2.enh.layers.dcunet.FeatureMapDense
espnet2.enh.layers.dcunet.GaussianFourierProjection
espnet2.enh.layers.dcunet.get_activation
espnet2.enh.layers.dcunet.make_unet_encoder_decoder_args
espnet2.enh.layers.dcunet.OnReIm
espnet2.enh.layers.dcunet.torch_complex_from_reim
espnet2.enh.layers.dcunet.unet_decoder_args
espnet2.enh.layers.dnn_beamformer.AttentionReference
espnet2.enh.layers.dnn_beamformer.DNN_Beamformer
espnet2.enh.layers.dnn_wpe.DNN_WPE
espnet2.enh.layers.dnsmos.DNSMOS_local
espnet2.enh.layers.dnsmos.DNSMOS_web
espnet2.enh.layers.dnsmos.poly1d
espnet2.enh.layers.dpmulcat.DPMulCat
espnet2.enh.layers.dpmulcat.MulCatBlock
espnet2.enh.layers.dprnn.DPRNN
espnet2.enh.layers.dprnn.DPRNN_TAC
espnet2.enh.layers.dprnn.merge_feature
espnet2.enh.layers.dprnn.SingleRNN
espnet2.enh.layers.dprnn.split_feature
espnet2.enh.layers.dptnet.DPTNet
espnet2.enh.layers.dptnet.ImprovedTransformerLayer
espnet2.enh.layers.fasnet.BF_module
espnet2.enh.layers.fasnet.FaSNet_base
espnet2.enh.layers.fasnet.FaSNet_TAC
espnet2.enh.layers.ifasnet.iFaSNet
espnet2.enh.layers.ifasnet.test_model
espnet2.enh.layers.mask_estimator.MaskEstimator
espnet2.enh.layers.ncsnpp_utils.layers.AttnBlock
espnet2.enh.layers.ncsnpp_utils.layers.CondCRPBlock
espnet2.enh.layers.ncsnpp_utils.layers.ConditionalResidualBlock
espnet2.enh.layers.ncsnpp_utils.layers.CondMSFBlock
espnet2.enh.layers.ncsnpp_utils.layers.CondRCUBlock
espnet2.enh.layers.ncsnpp_utils.layers.CondRefineBlock
espnet2.enh.layers.ncsnpp_utils.layers.contract_inner
espnet2.enh.layers.ncsnpp_utils.layers.ConvMeanPool
espnet2.enh.layers.ncsnpp_utils.layers.CRPBlock
espnet2.enh.layers.ncsnpp_utils.layers.ddpm_conv1x1
espnet2.enh.layers.ncsnpp_utils.layers.ddpm_conv3x3
espnet2.enh.layers.ncsnpp_utils.layers.default_init
espnet2.enh.layers.ncsnpp_utils.layers.Dense
espnet2.enh.layers.ncsnpp_utils.layers.get_act
espnet2.enh.layers.ncsnpp_utils.layers.MeanPoolConv
espnet2.enh.layers.ncsnpp_utils.layers.MSFBlock
espnet2.enh.layers.ncsnpp_utils.layers.ncsn_conv1x1
espnet2.enh.layers.ncsnpp_utils.layers.ncsn_conv3x3
espnet2.enh.layers.ncsnpp_utils.layers.NIN
espnet2.enh.layers.ncsnpp_utils.layers.RCUBlock
espnet2.enh.layers.ncsnpp_utils.layers.RefineBlock
espnet2.enh.layers.ncsnpp_utils.layers.ResidualBlock
espnet2.enh.layers.ncsnpp_utils.layers.ResnetBlockDDPM
espnet2.enh.layers.ncsnpp_utils.layers.UpsampleConv
espnet2.enh.layers.ncsnpp_utils.layers.variance_scaling
espnet2.enh.layers.ncsnpp_utils.layerspp.AttnBlockpp
espnet2.enh.layers.ncsnpp_utils.layerspp.Combine
espnet2.enh.layers.ncsnpp_utils.layerspp.Downsample
espnet2.enh.layers.ncsnpp_utils.layerspp.ResnetBlockBigGANpp
espnet2.enh.layers.ncsnpp_utils.layerspp.ResnetBlockDDPMpp
espnet2.enh.layers.ncsnpp_utils.layerspp.Upsample
espnet2.enh.layers.ncsnpp_utils.normalization.ConditionalBatchNorm2d
espnet2.enh.layers.ncsnpp_utils.normalization.ConditionalInstanceNorm2d
espnet2.enh.layers.ncsnpp_utils.normalization.ConditionalInstanceNorm2dPlus
espnet2.enh.layers.ncsnpp_utils.normalization.ConditionalNoneNorm2d
espnet2.enh.layers.ncsnpp_utils.normalization.ConditionalVarianceNorm2d
espnet2.enh.layers.ncsnpp_utils.normalization.get_normalization
espnet2.enh.layers.ncsnpp_utils.normalization.InstanceNorm2dPlus
espnet2.enh.layers.ncsnpp_utils.normalization.NoneNorm2d
espnet2.enh.layers.ncsnpp_utils.normalization.VarianceNorm2d
espnet2.enh.layers.ncsnpp_utils.up_or_down_sampling.conv_downsample_2d
espnet2.enh.layers.ncsnpp_utils.up_or_down_sampling.Conv2d
espnet2.enh.layers.ncsnpp_utils.up_or_down_sampling.downsample_2d
espnet2.enh.layers.ncsnpp_utils.up_or_down_sampling.get_weight
espnet2.enh.layers.ncsnpp_utils.up_or_down_sampling.naive_downsample_2d
espnet2.enh.layers.ncsnpp_utils.up_or_down_sampling.naive_upsample_2d
espnet2.enh.layers.ncsnpp_utils.up_or_down_sampling.upsample_2d
espnet2.enh.layers.ncsnpp_utils.up_or_down_sampling.upsample_conv_2d
espnet2.enh.layers.ncsnpp_utils.upfirdn2d.upfirdn2d
espnet2.enh.layers.ncsnpp_utils.upfirdn2d.upfirdn2d_native
espnet2.enh.layers.ncsnpp.NCSNpp
espnet2.enh.layers.skim.MemLSTM
espnet2.enh.layers.skim.SegLSTM
espnet2.enh.layers.skim.SkiM
espnet2.enh.layers.swin_transformer.BasicLayer
espnet2.enh.layers.swin_transformer.DropPath
espnet2.enh.layers.swin_transformer.Mlp
espnet2.enh.layers.swin_transformer.SwinTransformerBlock
espnet2.enh.layers.swin_transformer.to_2tuple
espnet2.enh.layers.swin_transformer.window_partition
espnet2.enh.layers.swin_transformer.window_reverse
espnet2.enh.layers.swin_transformer.WindowAttention
espnet2.enh.layers.tcn.check_nonlinear
espnet2.enh.layers.tcn.Chomp1d
espnet2.enh.layers.tcn.DepthwiseSeparableConv
espnet2.enh.layers.tcn.GlobalLayerNorm
espnet2.enh.layers.tcn.TemporalBlock
espnet2.enh.layers.tcn.TemporalConvNet
espnet2.enh.layers.tcn.TemporalConvNetInformed
espnet2.enh.layers.tcndenseunet.Conv2DActNorm
espnet2.enh.layers.tcndenseunet.DenseBlock
espnet2.enh.layers.tcndenseunet.FreqWiseBlock
espnet2.enh.layers.tcndenseunet.TCNDenseUNet
espnet2.enh.layers.tcndenseunet.TCNResBlock
espnet2.enh.layers.uses.ChannelAttention
espnet2.enh.layers.uses.ChannelTAC
espnet2.enh.layers.uses.USES
espnet2.enh.layers.uses2_comp.ATFBlock
espnet2.enh.layers.uses2_comp.USES2_Comp
espnet2.enh.layers.uses2_swin.ChannelAttentionTAC
espnet2.enh.layers.uses2_swin.ResSwinBlock
espnet2.enh.layers.uses2_swin.USES2_Swin
espnet2.enh.layers.wpe.get_correlations
espnet2.enh.layers.wpe.get_filter_matrix_conj
espnet2.enh.layers.wpe.get_power
espnet2.enh.layers.wpe.perform_filter_operation
espnet2.enh.layers.wpe.wpe
espnet2.enh.layers.wpe.wpe_one_iteration
espnet2.enh.loss.criterions.abs_loss.AbsEnhLoss
espnet2.enh.loss.criterions.tf_domain.FrequencyDomainAbsCoherence
espnet2.enh.loss.criterions.tf_domain.FrequencyDomainCrossEntropy
espnet2.enh.loss.criterions.tf_domain.FrequencyDomainDPCL
espnet2.enh.loss.criterions.tf_domain.FrequencyDomainL1
espnet2.enh.loss.criterions.tf_domain.FrequencyDomainLoss
espnet2.enh.loss.criterions.tf_domain.FrequencyDomainMSE
espnet2.enh.loss.criterions.time_domain.CISDRLoss
espnet2.enh.loss.criterions.time_domain.MultiResL1SpecLoss
espnet2.enh.loss.criterions.time_domain.SDRLoss
espnet2.enh.loss.criterions.time_domain.SISNRLoss
espnet2.enh.loss.criterions.time_domain.SNRLoss
espnet2.enh.loss.criterions.time_domain.TimeDomainL1
espnet2.enh.loss.criterions.time_domain.TimeDomainLoss
espnet2.enh.loss.criterions.time_domain.TimeDomainMSE
espnet2.enh.loss.wrappers.abs_wrapper.AbsLossWrapper
espnet2.enh.loss.wrappers.dpcl_solver.DPCLSolver
espnet2.enh.loss.wrappers.fixed_order.FixedOrderSolver
espnet2.enh.loss.wrappers.mixit_solver.MixITSolver
espnet2.enh.loss.wrappers.multilayer_pit_solver.MultiLayerPITSolver
espnet2.enh.loss.wrappers.pit_solver.PITSolver
espnet2.enh.separator.abs_separator.AbsSeparator
espnet2.enh.separator.asteroid_models.AsteroidModel_Converter
espnet2.enh.separator.bsrnn_separator.BSRNNSeparator
espnet2.enh.separator.conformer_separator.ConformerSeparator
espnet2.enh.separator.dan_separator.DANSeparator
espnet2.enh.separator.dc_crn_separator.DC_CRNSeparator
espnet2.enh.separator.dccrn_separator.DCCRNSeparator
espnet2.enh.separator.dpcl_e2e_separator.DPCLE2ESeparator
espnet2.enh.separator.dpcl_separator.DPCLSeparator
espnet2.enh.separator.dprnn_separator.DPRNNSeparator
espnet2.enh.separator.dptnet_separator.DPTNetSeparator
espnet2.enh.separator.fasnet_separator.FaSNetSeparator
espnet2.enh.separator.ineube_separator.iNeuBe
espnet2.enh.separator.neural_beamformer.NeuralBeamformer
espnet2.enh.separator.rnn_separator.RNNSeparator
espnet2.enh.separator.skim_separator.SkiMSeparator
espnet2.enh.separator.svoice_separator.Decoder
espnet2.enh.separator.svoice_separator.Encoder
espnet2.enh.separator.svoice_separator.overlap_and_add
espnet2.enh.separator.svoice_separator.SVoiceSeparator
espnet2.enh.separator.tcn_separator.TCNSeparator
espnet2.enh.separator.tfgridnet_separator.GridNetBlock
espnet2.enh.separator.tfgridnet_separator.LayerNormalization4D
espnet2.enh.separator.tfgridnet_separator.LayerNormalization4DCF
espnet2.enh.separator.tfgridnet_separator.TFGridNet
espnet2.enh.separator.tfgridnetv2_separator.AllHeadPReLULayerNormalization4DCF
espnet2.enh.separator.tfgridnetv2_separator.GridNetV2Block
espnet2.enh.separator.tfgridnetv2_separator.TFGridNetV2
espnet2.enh.separator.tfgridnetv3_separator.AllHeadPReLULayerNormalization4DC
espnet2.enh.separator.tfgridnetv3_separator.GridNetV3Block
espnet2.enh.separator.tfgridnetv3_separator.LayerNormalization
espnet2.enh.separator.tfgridnetv3_separator.TFGridNetV3
espnet2.enh.separator.transformer_separator.TransformerSeparator
espnet2.enh.separator.uses_separator.USESSeparator
espnet2.enh.separator.uses2_separator.USES2Separator
Prev
Diar
Next
Fileio