Espnet2

Catalog

• #Asr

  • #espnet2.asr.bayes_risk_ctc.BayesRiskCTC
  • #espnet2.asr.bayes_risk_ctc.log_substraction_exp
  • #espnet2.asr.ctc.CTC
  • #espnet2.asr.decoder.abs_decoder.AbsDecoder
  • #espnet2.asr.decoder.hugging_face_transformers_decoder.get_hugging_face_model_lm_head
  • #espnet2.asr.decoder.hugging_face_transformers_decoder.get_hugging_face_model_network
  • #espnet2.asr.decoder.hugging_face_transformers_decoder.HuggingFaceTransformersDecoder
  • #espnet2.asr.decoder.mlm_decoder.MLMDecoder
  • #espnet2.asr.decoder.rnn_decoder.build_attention_list
  • #espnet2.asr.decoder.rnn_decoder.RNNDecoder
  • #espnet2.asr.decoder.s4_decoder.S4Decoder
  • #espnet2.asr.decoder.transducer_decoder.TransducerDecoder
  • #espnet2.asr.decoder.transformer_decoder.BaseTransformerDecoder
  • #espnet2.asr.decoder.transformer_decoder.DynamicConvolution2DTransformerDecoder
  • #espnet2.asr.decoder.transformer_decoder.DynamicConvolutionTransformerDecoder
  • #espnet2.asr.decoder.transformer_decoder.LightweightConvolution2DTransformerDecoder
  • #espnet2.asr.decoder.transformer_decoder.LightweightConvolutionTransformerDecoder
  • #espnet2.asr.decoder.transformer_decoder.TransformerDecoder
  • #espnet2.asr.decoder.transformer_decoder.TransformerMDDecoder
  • #espnet2.asr.decoder.whisper_decoder.ExpandedTokenEmbedding
  • #espnet2.asr.decoder.whisper_decoder.OpenAIWhisperDecoder
  • #espnet2.asr.discrete_asr_espnet_model.ESPnetDiscreteASRModel
  • #espnet2.asr.encoder.abs_encoder.AbsEncoder
  • #espnet2.asr.encoder.avhubert_encoder.AVHubertConfig
  • #espnet2.asr.encoder.avhubert_encoder.AVHubertModel
  • #espnet2.asr.encoder.avhubert_encoder.BasicBlock
  • #espnet2.asr.encoder.avhubert_encoder.conv3x3
  • #espnet2.asr.encoder.avhubert_encoder.download_avhubert
  • #espnet2.asr.encoder.avhubert_encoder.downsample_basic_block
  • #espnet2.asr.encoder.avhubert_encoder.downsample_basic_block_v2
  • #espnet2.asr.encoder.avhubert_encoder.FairseqAVHubertEncoder
  • #espnet2.asr.encoder.avhubert_encoder.index_put
  • #espnet2.asr.encoder.avhubert_encoder.is_xla_tensor
  • #espnet2.asr.encoder.avhubert_encoder.ResEncoder
  • #espnet2.asr.encoder.avhubert_encoder.ResNet
  • #espnet2.asr.encoder.avhubert_encoder.SubModel
  • #espnet2.asr.encoder.avhubert_encoder.time_masking
  • #espnet2.asr.encoder.beats_encoder.BeatsConfig
  • #espnet2.asr.encoder.beats_encoder.BeatsEncoder
  • #espnet2.asr.encoder.beats_encoder.gelu
  • #espnet2.asr.encoder.beats_encoder.gelu_accurate
  • #espnet2.asr.encoder.beats_encoder.get_activation_fn
  • #espnet2.asr.encoder.beats_encoder.GLU_Linear
  • #espnet2.asr.encoder.beats_encoder.GradMultiply
  • #espnet2.asr.encoder.beats_encoder.init_bert_params
  • #espnet2.asr.encoder.beats_encoder.MultiheadAttention
  • #espnet2.asr.encoder.beats_encoder.quant_noise
  • #espnet2.asr.encoder.beats_encoder.SamePad
  • #espnet2.asr.encoder.beats_encoder.Swish
  • #espnet2.asr.encoder.beats_encoder.TransformerSentenceEncoderLayer
  • #espnet2.asr.encoder.branchformer_encoder.BranchformerEncoder
  • #espnet2.asr.encoder.branchformer_encoder.BranchformerEncoderLayer
  • #espnet2.asr.encoder.conformer_encoder.ConformerEncoder
  • #espnet2.asr.encoder.contextual_block_conformer_encoder.ContextualBlockConformerEncoder
  • #espnet2.asr.encoder.contextual_block_transformer_encoder.ContextualBlockTransformerEncoder
  • #espnet2.asr.encoder.e_branchformer_ctc_encoder.EBranchformerCTCEncoder
  • #espnet2.asr.encoder.e_branchformer_encoder.EBranchformerEncoder
  • #espnet2.asr.encoder.e_branchformer_encoder.EBranchformerEncoderLayer
  • #espnet2.asr.encoder.hubert_encoder.download_hubert
  • #espnet2.asr.encoder.hubert_encoder.FairseqHubertEncoder
  • #espnet2.asr.encoder.hubert_encoder.FairseqHubertPretrainEncoder
  • #espnet2.asr.encoder.hubert_encoder.TorchAudioHuBERTPretrainEncoder
  • #espnet2.asr.encoder.hugging_face_transformers_encoder.HuggingFaceTransformersEncoder
  • #espnet2.asr.encoder.linear_encoder.LinearEncoder
  • #espnet2.asr.encoder.longformer_encoder.LongformerEncoder
  • #espnet2.asr.encoder.multiconvformer_encoder.MultiConvConformerEncoder
  • #espnet2.asr.encoder.rnn_encoder.RNNEncoder
  • #espnet2.asr.encoder.transformer_encoder_multispkr.TransformerEncoder
  • #espnet2.asr.encoder.vgg_rnn_encoder.VGGRNNEncoder
  • #espnet2.asr.encoder.wav2vec2_encoder.download_w2v
  • #espnet2.asr.encoder.wav2vec2_encoder.FairSeqWav2Vec2Encoder
  • #espnet2.asr.encoder.whisper_encoder.OpenAIWhisperEncoder
  • #espnet2.asr.espnet_model.ESPnetASRModel
  • #espnet2.asr.frontend.abs_frontend.AbsFrontend
  • #espnet2.asr.frontend.asteroid_frontend.AsteroidFrontend
  • #espnet2.asr.frontend.default.DefaultFrontend
  • #espnet2.asr.frontend.fused.FusedFrontends
  • #espnet2.asr.frontend.melspec_torch.MelSpectrogramTorch
  • #espnet2.asr.frontend.s3prl.S3prlFrontend
  • #espnet2.asr.frontend.whisper.WhisperFrontend
  • #espnet2.asr.frontend.windowing.SlidingWindow
  • #espnet2.asr.layers.cgmlp.ConvolutionalGatingMLP
  • #espnet2.asr.layers.cgmlp.ConvolutionalSpatialGatingUnit
  • #espnet2.asr.layers.fastformer.FastSelfAttention
  • #espnet2.asr.layers.multiconv_cgmlp.MultiConvolutionalGatingMLP
  • #espnet2.asr.layers.multiconv_cgmlp.MultiConvolutionalSpatialGatingUnit
  • #espnet2.asr.maskctc_model.MaskCTCInference
  • #espnet2.asr.maskctc_model.MaskCTCModel
  • #espnet2.asr.partially_AR_model.PartiallyARInference
  • #espnet2.asr.pit_espnet_model.PITLossWrapper
  • #espnet2.asr.postencoder.abs_postencoder.AbsPostEncoder
  • #espnet2.asr.postencoder.hugging_face_transformers_postencoder.HuggingFaceTransformersPostEncoder
  • #espnet2.asr.postencoder.length_adaptor_postencoder.LengthAdaptorPostEncoder
  • #espnet2.asr.preencoder.abs_preencoder.AbsPreEncoder
  • #espnet2.asr.preencoder.linear.LinearProjection
  • #espnet2.asr.preencoder.sinc.LightweightSincConvs
  • #espnet2.asr.preencoder.sinc.SpatialDropout
  • #espnet2.asr.specaug.abs_specaug.AbsSpecAug
  • #espnet2.asr.specaug.specaug.SpecAug
  • #espnet2.asr.state_spaces.attention.MultiHeadedAttention
  • #espnet2.asr.state_spaces.base.SequenceIdentity
  • #espnet2.asr.state_spaces.base.SequenceModule
  • #espnet2.asr.state_spaces.base.TransposedModule
  • #espnet2.asr.state_spaces.block.SequenceResidualBlock
  • #espnet2.asr.state_spaces.cauchy.cauchy_mult
  • #espnet2.asr.state_spaces.cauchy.cauchy_mult_keops
  • #espnet2.asr.state_spaces.cauchy.cauchy_mult_torch
  • #espnet2.asr.state_spaces.cauchy.CauchyMultiply
  • #espnet2.asr.state_spaces.cauchy.CauchyMultiplySymmetric
  • #espnet2.asr.state_spaces.components.Activation
  • #espnet2.asr.state_spaces.components.DropoutNd
  • #espnet2.asr.state_spaces.components.get_initializer
  • #espnet2.asr.state_spaces.components.LinearActivation
  • #espnet2.asr.state_spaces.components.Normalization
  • #espnet2.asr.state_spaces.components.ReversibleInstanceNorm1dInput
  • #espnet2.asr.state_spaces.components.ReversibleInstanceNorm1dOutput
  • #espnet2.asr.state_spaces.components.SquaredReLU
  • #espnet2.asr.state_spaces.components.stochastic_depth
  • #espnet2.asr.state_spaces.components.StochasticDepth
  • #espnet2.asr.state_spaces.components.TransposedLinear
  • #espnet2.asr.state_spaces.components.TransposedLN
  • #espnet2.asr.state_spaces.components.TSInverseNormalization
  • #espnet2.asr.state_spaces.components.TSNormalization
  • #espnet2.asr.state_spaces.ff.FF
  • #espnet2.asr.state_spaces.model.SequenceModel
  • #espnet2.asr.state_spaces.pool.DownAvgPool
  • #espnet2.asr.state_spaces.pool.DownLinearPool
  • #espnet2.asr.state_spaces.pool.DownPool
  • #espnet2.asr.state_spaces.pool.DownPool2d
  • #espnet2.asr.state_spaces.pool.downsample
  • #espnet2.asr.state_spaces.pool.DownSample
  • #espnet2.asr.state_spaces.pool.DownSpectralPool
  • #espnet2.asr.state_spaces.pool.UpPool
  • #espnet2.asr.state_spaces.pool.upsample
  • #espnet2.asr.state_spaces.pool.UpSample
  • #espnet2.asr.state_spaces.residual.Affine
  • #espnet2.asr.state_spaces.residual.DecayResidual
  • #espnet2.asr.state_spaces.residual.Feedforward
  • #espnet2.asr.state_spaces.residual.Highway
  • #espnet2.asr.state_spaces.residual.Residual
  • #espnet2.asr.state_spaces.s4.combination
  • #espnet2.asr.state_spaces.s4.dplr
  • #espnet2.asr.state_spaces.s4.get_logger
  • #espnet2.asr.state_spaces.s4.nplr
  • #espnet2.asr.state_spaces.s4.OptimModule
  • #espnet2.asr.state_spaces.s4.power
  • #espnet2.asr.state_spaces.s4.rank_correction
  • #espnet2.asr.state_spaces.s4.rank_zero_only
  • #espnet2.asr.state_spaces.s4.S4
  • #espnet2.asr.state_spaces.s4.SSKernel
  • #espnet2.asr.state_spaces.s4.SSKernelDiag
  • #espnet2.asr.state_spaces.s4.SSKernelNPLR
  • #espnet2.asr.state_spaces.s4.ssm
  • #espnet2.asr.state_spaces.s4.transition
  • #espnet2.asr.state_spaces.utils.extract_attrs_from_obj
  • #espnet2.asr.state_spaces.utils.get_class
  • #espnet2.asr.state_spaces.utils.instantiate
  • #espnet2.asr.state_spaces.utils.is_dict
  • #espnet2.asr.state_spaces.utils.is_list
  • #espnet2.asr.state_spaces.utils.omegaconf_filter_keys
  • #espnet2.asr.state_spaces.utils.to_dict
  • #espnet2.asr.state_spaces.utils.to_list
  • #espnet2.asr.transducer.beam_search_transducer_streaming.BeamSearchTransducerStreaming
  • #espnet2.asr.transducer.beam_search_transducer_streaming.ExtendedHypothesis
  • #espnet2.asr.transducer.beam_search_transducer_streaming.Hypothesis
  • #espnet2.asr.transducer.beam_search_transducer.BeamSearchTransducer
  • #espnet2.asr.transducer.error_calculator.ErrorCalculatorTransducer
  • #espnet2.asr.transducer.rnnt_multi_blank.rnnt_multi_blank._MultiblankRNNTNumba
  • #espnet2.asr.transducer.rnnt_multi_blank.rnnt_multi_blank._RNNTNumba
  • #espnet2.asr.transducer.rnnt_multi_blank.rnnt_multi_blank.certify_inputs
  • #espnet2.asr.transducer.rnnt_multi_blank.rnnt_multi_blank.check_contiguous
  • #espnet2.asr.transducer.rnnt_multi_blank.rnnt_multi_blank.check_dim
  • #espnet2.asr.transducer.rnnt_multi_blank.rnnt_multi_blank.check_type
  • #espnet2.asr.transducer.rnnt_multi_blank.rnnt_multi_blank.multiblank_rnnt_loss
  • #espnet2.asr.transducer.rnnt_multi_blank.rnnt_multi_blank.MultiblankRNNTLossNumba
  • #espnet2.asr.transducer.rnnt_multi_blank.rnnt_multi_blank.rnnt_loss
  • #espnet2.asr.transducer.rnnt_multi_blank.rnnt_multi_blank.RNNTLossNumba
  • #espnet2.asr.transducer.rnnt_multi_blank.rnnt.multiblank_rnnt_loss_gpu
  • #espnet2.asr.transducer.rnnt_multi_blank.rnnt.rnnt_loss_cpu
  • #espnet2.asr.transducer.rnnt_multi_blank.rnnt.rnnt_loss_gpu
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cpu_utils.cpu_rnnt.CPURNNT
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cpu_utils.cpu_rnnt.CpuRNNT_index
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cpu_utils.cpu_rnnt.CpuRNNT_metadata
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cpu_utils.cpu_rnnt.LogSoftmaxGradModification
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.gpu_rnnt_kernel.compute_alphas_kernel
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.gpu_rnnt_kernel.compute_betas_kernel
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.gpu_rnnt_kernel.compute_grad_kernel
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.gpu_rnnt_kernel.compute_multiblank_alphas_kernel
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.gpu_rnnt_kernel.compute_multiblank_betas_kernel
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.gpu_rnnt_kernel.compute_multiblank_grad_kernel
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.gpu_rnnt_kernel.logp
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.gpu_rnnt.GPURNNT
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.gpu_rnnt.MultiblankGPURNNT
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.reduce.CTAReduce
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.reduce.I_Op
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.reduce.R_Op
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.reduce.reduce_exp
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.reduce.reduce_max
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.cuda_utils.reduce.ReduceHelper
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.global_constants.dtype
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.global_constants.RNNTStatus
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.global_constants.threads_per_block
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.global_constants.warp_size
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.rnnt_helper.add
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.rnnt_helper.compute_costs_data
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.rnnt_helper.copy_data_1d
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.rnnt_helper.div_up
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.rnnt_helper.exponential
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.rnnt_helper.flatten_tensor
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.rnnt_helper.get_workspace_size
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.rnnt_helper.identity
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.rnnt_helper.log_plus
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.rnnt_helper.log_sum_exp
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.rnnt_helper.maximum
  • #espnet2.asr.transducer.rnnt_multi_blank.utils.rnnt_helper.negate

• #Asr Transducer

  • #espnet2.asr_transducer.activation.FTSwish
  • #espnet2.asr_transducer.activation.get_activation
  • #espnet2.asr_transducer.activation.Mish
  • #espnet2.asr_transducer.activation.Smish
  • #espnet2.asr_transducer.activation.Swish
  • #espnet2.asr_transducer.beam_search_transducer.BeamSearchTransducer
  • #espnet2.asr_transducer.beam_search_transducer.ExtendedHypothesis
  • #espnet2.asr_transducer.beam_search_transducer.Hypothesis
  • #espnet2.asr_transducer.decoder.abs_decoder.AbsDecoder
  • #espnet2.asr_transducer.decoder.blocks.mega.MEGA
  • #espnet2.asr_transducer.decoder.blocks.rwkv.RWKV
  • #espnet2.asr_transducer.decoder.mega_decoder.MEGADecoder
  • #espnet2.asr_transducer.decoder.modules.mega.feed_forward.NormalizedPositionwiseFeedForward
  • #espnet2.asr_transducer.decoder.modules.mega.multi_head_damped_ema.MultiHeadDampedEMA
  • #espnet2.asr_transducer.decoder.modules.mega.positional_bias.RelativePositionBias
  • #espnet2.asr_transducer.decoder.modules.mega.positional_bias.RotaryRelativePositionBias
  • #espnet2.asr_transducer.decoder.modules.rwkv.attention.load_wkv_kernel
  • #espnet2.asr_transducer.decoder.modules.rwkv.attention.SelfAttention
  • #espnet2.asr_transducer.decoder.modules.rwkv.attention.WKVLinearAttention
  • #espnet2.asr_transducer.decoder.modules.rwkv.feed_forward.FeedForward
  • #espnet2.asr_transducer.decoder.rnn_decoder.RNNDecoder
  • #espnet2.asr_transducer.decoder.rwkv_decoder.RWKVDecoder
  • #espnet2.asr_transducer.decoder.stateless_decoder.StatelessDecoder
  • #espnet2.asr_transducer.encoder.blocks.branchformer.Branchformer
  • #espnet2.asr_transducer.encoder.blocks.conformer.Conformer
  • #espnet2.asr_transducer.encoder.blocks.conv_input.ConvInput
  • #espnet2.asr_transducer.encoder.blocks.conv1d.Conv1d
  • #espnet2.asr_transducer.encoder.blocks.ebranchformer.EBranchformer
  • #espnet2.asr_transducer.encoder.building.build_body_blocks
  • #espnet2.asr_transducer.encoder.building.build_branchformer_block
  • #espnet2.asr_transducer.encoder.building.build_conformer_block
  • #espnet2.asr_transducer.encoder.building.build_conv1d_block
  • #espnet2.asr_transducer.encoder.building.build_ebranchformer_block
  • #espnet2.asr_transducer.encoder.building.build_input_block
  • #espnet2.asr_transducer.encoder.building.build_main_parameters
  • #espnet2.asr_transducer.encoder.building.build_positional_encoding
  • #espnet2.asr_transducer.encoder.encoder.Encoder
  • #espnet2.asr_transducer.encoder.modules.attention.RelPositionMultiHeadedAttention
  • #espnet2.asr_transducer.encoder.modules.convolution.ConformerConvolution
  • #espnet2.asr_transducer.encoder.modules.convolution.ConvolutionalSpatialGatingUnit
  • #espnet2.asr_transducer.encoder.modules.convolution.DepthwiseConvolution
  • #espnet2.asr_transducer.encoder.modules.multi_blocks.MultiBlocks
  • #espnet2.asr_transducer.encoder.modules.positional_encoding.RelPositionalEncoding
  • #espnet2.asr_transducer.encoder.validation.validate_architecture
  • #espnet2.asr_transducer.encoder.validation.validate_block_arguments
  • #espnet2.asr_transducer.encoder.validation.validate_input_block
  • #espnet2.asr_transducer.error_calculator.ErrorCalculator
  • #espnet2.asr_transducer.espnet_transducer_model.ESPnetASRTransducerModel
  • #espnet2.asr_transducer.frontend.online_audio_processor.OnlineAudioProcessor
  • #espnet2.asr_transducer.joint_network.JointNetwork
  • #espnet2.asr_transducer.normalization.BasicNorm
  • #espnet2.asr_transducer.normalization.get_normalization
  • #espnet2.asr_transducer.normalization.RMSNorm
  • #espnet2.asr_transducer.normalization.ScaleNorm
  • #espnet2.asr_transducer.utils.check_short_utt
  • #espnet2.asr_transducer.utils.get_convinput_module_parameters
  • #espnet2.asr_transducer.utils.get_transducer_task_io
  • #espnet2.asr_transducer.utils.make_chunk_mask
  • #espnet2.asr_transducer.utils.make_source_mask
  • #espnet2.asr_transducer.utils.TooShortUttError

• #Asvspoof

  • #espnet2.asvspoof.decoder.abs_decoder.AbsDecoder
  • #espnet2.asvspoof.decoder.linear_decoder.LinearDecoder
  • #espnet2.asvspoof.espnet_model.ESPnetASVSpoofModel
  • #espnet2.asvspoof.loss.abs_loss.AbsASVSpoofLoss
  • #espnet2.asvspoof.loss.am_softmax_loss.ASVSpoofAMSoftmaxLoss
  • #espnet2.asvspoof.loss.binary_loss.ASVSpoofBinaryLoss
  • #espnet2.asvspoof.loss.oc_softmax_loss.ASVSpoofOCSoftmaxLoss

• #Diar

  • #espnet2.diar.abs_diar.AbsDiarization
  • #espnet2.diar.attractor.abs_attractor.AbsAttractor
  • #espnet2.diar.attractor.rnn_attractor.RnnAttractor
  • #espnet2.diar.decoder.abs_decoder.AbsDecoder
  • #espnet2.diar.decoder.linear_decoder.LinearDecoder
  • #espnet2.diar.espnet_model.ESPnetDiarizationModel
  • #espnet2.diar.label_processor.LabelProcessor
  • #espnet2.diar.layers.abs_mask.AbsMask
  • #espnet2.diar.layers.multi_mask.MultiMask
  • #espnet2.diar.layers.tcn_nomask.ChannelwiseLayerNorm
  • #espnet2.diar.layers.tcn_nomask.check_nonlinear
  • #espnet2.diar.layers.tcn_nomask.Chomp1d
  • #espnet2.diar.layers.tcn_nomask.chose_norm
  • #espnet2.diar.layers.tcn_nomask.DepthwiseSeparableConv
  • #espnet2.diar.layers.tcn_nomask.GlobalLayerNorm
  • #espnet2.diar.layers.tcn_nomask.TemporalBlock
  • #espnet2.diar.layers.tcn_nomask.TemporalConvNet
  • #espnet2.diar.separator.tcn_separator_nomask.TCNSeparatorNomask

• #Enh

  • #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_th.apply_beamforming_vector
  • #espnet2.enh.layers.beamformer_th.blind_analytic_normalization
  • #espnet2.enh.layers.beamformer_th.generalized_eigenvalue_decomposition
  • #espnet2.enh.layers.beamformer_th.get_covariances
  • #espnet2.enh.layers.beamformer_th.get_gev_vector
  • #espnet2.enh.layers.beamformer_th.get_lcmv_vector_with_rtf
  • #espnet2.enh.layers.beamformer_th.get_mvdr_vector
  • #espnet2.enh.layers.beamformer_th.get_mvdr_vector_with_rtf
  • #espnet2.enh.layers.beamformer_th.get_mwf_vector
  • #espnet2.enh.layers.beamformer_th.get_rank1_mwf_vector
  • #espnet2.enh.layers.beamformer_th.get_rtf
  • #espnet2.enh.layers.beamformer_th.get_rtf_matrix
  • #espnet2.enh.layers.beamformer_th.get_sdw_mwf_vector
  • #espnet2.enh.layers.beamformer_th.get_WPD_filter
  • #espnet2.enh.layers.beamformer_th.get_WPD_filter_v2
  • #espnet2.enh.layers.beamformer_th.get_WPD_filter_with_rtf
  • #espnet2.enh.layers.beamformer_th.gev_phase_correction
  • #espnet2.enh.layers.beamformer_th.perform_WPD_filtering
  • #espnet2.enh.layers.beamformer_th.prepare_beamformer_stats
  • #espnet2.enh.layers.beamformer_th.tik_reg
  • #espnet2.enh.layers.beamformer.get_power_spectral_density_matrix
  • #espnet2.enh.layers.bsrnn.BandSplit
  • #espnet2.enh.layers.bsrnn.BSRNN
  • #espnet2.enh.layers.bsrnn.ChannelFreqwiseLayerNorm
  • #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.ComplexBatchNorm
  • #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.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.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.fasnet.test_model
  • #espnet2.enh.layers.ifasnet.iFaSNet
  • #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.GaussianFourierProjection
  • #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.tcn.ChannelwiseLayerNorm
  • #espnet2.enh.layers.tcn.check_nonlinear
  • #espnet2.enh.layers.tcn.Chomp1d
  • #espnet2.enh.layers.tcn.choose_norm
  • #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.ATFBlock
  • #espnet2.enh.layers.uses.ChannelAttention
  • #espnet2.enh.layers.uses.ChannelTAC
  • #espnet2.enh.layers.uses.USES
  • #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.signal_framing
  • #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.TFGridNet
  • #espnet2.enh.separator.tfgridnetv2_separator.AllHeadPReLULayerNormalization4DCF
  • #espnet2.enh.separator.tfgridnetv2_separator.GridNetV2Block
  • #espnet2.enh.separator.tfgridnetv2_separator.LayerNormalization4DCF
  • #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

• #Fileio

  • #espnet2.fileio.datadir_writer.DatadirWriter
  • #espnet2.fileio.multi_sound_scp.MultiSoundScpReader
  • #espnet2.fileio.npy_scp.NpyScpReader
  • #espnet2.fileio.npy_scp.NpyScpWriter
  • #espnet2.fileio.rand_gen_dataset.FloatRandomGenerateDataset
  • #espnet2.fileio.rand_gen_dataset.IntRandomGenerateDataset
  • #espnet2.fileio.read_text.load_num_sequence_text
  • #espnet2.fileio.read_text.RandomTextReader
  • #espnet2.fileio.read_text.read_2columns_text
  • #espnet2.fileio.read_text.read_label
  • #espnet2.fileio.read_text.read_multi_columns_text
  • #espnet2.fileio.rttm.load_rttm_text
  • #espnet2.fileio.rttm.RttmReader
  • #espnet2.fileio.score_scp.MIDReader
  • #espnet2.fileio.score_scp.NOTE
  • #espnet2.fileio.score_scp.SingingScoreReader
  • #espnet2.fileio.score_scp.SingingScoreWriter
  • #espnet2.fileio.score_scp.XMLReader
  • #espnet2.fileio.score_scp.XMLWriter
  • #espnet2.fileio.sound_scp.soundfile_read
  • #espnet2.fileio.sound_scp.SoundScpReader
  • #espnet2.fileio.sound_scp.SoundScpWriter
  • #espnet2.fileio.vad_scp.VADScpReader
  • #espnet2.fileio.vad_scp.VADScpWriter

• #Fst

  • #espnet2.fst.lm_rescore.compute_am_scores_and_lm_scores
  • #espnet2.fst.lm_rescore.nbest_am_lm_scores
  • #espnet2.fst.lm_rescore.remove_repeated_and_leq

• #Gan Codec

  • #espnet2.gan_codec.abs_gan_codec.AbsGANCodec
  • #espnet2.gan_codec.dac.dac.DAC
  • #espnet2.gan_codec.dac.dac.DACDiscriminator
  • #espnet2.gan_codec.dac.dac.DACGenerator
  • #espnet2.gan_codec.encodec.encodec.Encodec
  • #espnet2.gan_codec.encodec.encodec.EncodecDiscriminator
  • #espnet2.gan_codec.espnet_model.ESPnetGANCodecModel
  • #espnet2.gan_codec.funcodec.funcodec.FunCodec
  • #espnet2.gan_codec.funcodec.funcodec.FunCodecDiscriminator
  • #espnet2.gan_codec.funcodec.funcodec.FunCodecGenerator
  • #espnet2.gan_codec.hificodec.hificodec.HiFiCodec
  • #espnet2.gan_codec.hificodec.hificodec.HiFiCodecDiscriminator
  • #espnet2.gan_codec.hificodec.hificodec.HiFiCodecGenerator
  • #espnet2.gan_codec.hificodec.module.Encoder
  • #espnet2.gan_codec.hificodec.module.Generator
  • #espnet2.gan_codec.hificodec.module.get_padding
  • #espnet2.gan_codec.hificodec.module.GroupResidualVectorQuantization
  • #espnet2.gan_codec.hificodec.module.init_weights
  • #espnet2.gan_codec.hificodec.module.QuantizedResult
  • #espnet2.gan_codec.hificodec.module.ResBlock1
  • #espnet2.gan_codec.hificodec.module.ResBlock2
  • #espnet2.gan_codec.shared.decoder.seanet_2d.NormConvTranspose2d
  • #espnet2.gan_codec.shared.decoder.seanet_2d.ReshapeModule
  • #espnet2.gan_codec.shared.decoder.seanet_2d.SConvTranspose2d
  • #espnet2.gan_codec.shared.decoder.seanet_2d.SEANetDecoder2d
  • #espnet2.gan_codec.shared.decoder.seanet_2d.SEANetResnetBlock2d
  • #espnet2.gan_codec.shared.decoder.seanet_2d.unpad2d
  • #espnet2.gan_codec.shared.decoder.seanet.NormConvTranspose1d
  • #espnet2.gan_codec.shared.decoder.seanet.SConvTranspose1d
  • #espnet2.gan_codec.shared.decoder.seanet.SEANetDecoder
  • #espnet2.gan_codec.shared.decoder.seanet.unpad1d
  • #espnet2.gan_codec.shared.discriminator.msmpmb_discriminator.MultiBandDiscriminator
  • #espnet2.gan_codec.shared.discriminator.msmpmb_discriminator.MultiScaleDiscriminator
  • #espnet2.gan_codec.shared.discriminator.msmpmb_discriminator.MultiScaleMultiPeriodMultiBandDiscriminator
  • #espnet2.gan_codec.shared.discriminator.msmpmb_discriminator.WNConv1d
  • #espnet2.gan_codec.shared.discriminator.msmpmb_discriminator.WNConv2d
  • #espnet2.gan_codec.shared.discriminator.msstft_conv.NormConv2d
  • #espnet2.gan_codec.shared.discriminator.msstft_discriminator.DiscriminatorSTFT
  • #espnet2.gan_codec.shared.discriminator.msstft_discriminator.get_2d_padding
  • #espnet2.gan_codec.shared.discriminator.msstft_discriminator.MultiDiscriminator
  • #espnet2.gan_codec.shared.discriminator.msstft_discriminator.MultiScaleSTFTDiscriminator
  • #espnet2.gan_codec.shared.discriminator.stft_discriminator.ComplexConv2d
  • #espnet2.gan_codec.shared.discriminator.stft_discriminator.ComplexSTFTDiscriminator
  • #espnet2.gan_codec.shared.discriminator.stft_discriminator.ComplexSTFTResidualUnit
  • #espnet2.gan_codec.shared.discriminator.stft_discriminator.ModReLU
  • #espnet2.gan_codec.shared.encoder.seanet_2d.get_activation
  • #espnet2.gan_codec.shared.encoder.seanet_2d.pad2d
  • #espnet2.gan_codec.shared.encoder.seanet_2d.SConv2d
  • #espnet2.gan_codec.shared.encoder.seanet_2d.SEANetEncoder2d
  • #espnet2.gan_codec.shared.encoder.seanet_2d.tuple_it
  • #espnet2.gan_codec.shared.encoder.seanet.apply_parametrization_norm
  • #espnet2.gan_codec.shared.encoder.seanet.ConvLayerNorm
  • #espnet2.gan_codec.shared.encoder.seanet.get_extra_padding_for_conv1d
  • #espnet2.gan_codec.shared.encoder.seanet.get_norm_module
  • #espnet2.gan_codec.shared.encoder.seanet.NormConv1d
  • #espnet2.gan_codec.shared.encoder.seanet.pad1d
  • #espnet2.gan_codec.shared.encoder.seanet.SConv1d
  • #espnet2.gan_codec.shared.encoder.seanet.SEANetEncoder
  • #espnet2.gan_codec.shared.encoder.seanet.SEANetResnetBlock
  • #espnet2.gan_codec.shared.encoder.seanet.SLSTM
  • #espnet2.gan_codec.shared.encoder.snake_activation.snake
  • #espnet2.gan_codec.shared.encoder.snake_activation.Snake1d
  • #espnet2.gan_codec.shared.loss.freq_loss.MultiScaleMelSpectrogramLoss
  • #espnet2.gan_codec.shared.loss.loss_balancer.Balancer
  • #espnet2.gan_codec.shared.loss.loss_balancer.EMA
  • #espnet2.gan_codec.shared.quantizer.modules.core_vq.default
  • #espnet2.gan_codec.shared.quantizer.modules.core_vq.ema_inplace
  • #espnet2.gan_codec.shared.quantizer.modules.core_vq.EuclideanCodebook
  • #espnet2.gan_codec.shared.quantizer.modules.core_vq.kmeans
  • #espnet2.gan_codec.shared.quantizer.modules.core_vq.laplace_smoothing
  • #espnet2.gan_codec.shared.quantizer.modules.core_vq.ResidualVectorQuantization
  • #espnet2.gan_codec.shared.quantizer.modules.core_vq.sample_vectors
  • #espnet2.gan_codec.shared.quantizer.modules.core_vq.uniform_init
  • #espnet2.gan_codec.shared.quantizer.modules.core_vq.VectorQuantization
  • #espnet2.gan_codec.shared.quantizer.modules.distrib.all_reduce
  • #espnet2.gan_codec.shared.quantizer.modules.distrib.average_metrics
  • #espnet2.gan_codec.shared.quantizer.modules.distrib.broadcast_tensors
  • #espnet2.gan_codec.shared.quantizer.modules.distrib.is_distributed
  • #espnet2.gan_codec.shared.quantizer.modules.distrib.rank
  • #espnet2.gan_codec.shared.quantizer.modules.distrib.sync_buffer
  • #espnet2.gan_codec.shared.quantizer.modules.distrib.sync_grad
  • #espnet2.gan_codec.shared.quantizer.modules.distrib.world_size
  • #espnet2.gan_codec.shared.quantizer.residual_vq.ResidualVectorQuantizer
  • #espnet2.gan_codec.soundstream.soundstream.SoundStream
  • #espnet2.gan_codec.soundstream.soundstream.SoundStreamDiscriminator
  • #espnet2.gan_codec.soundstream.soundstream.SoundStreamGenerator

• #Gan Svs

  • #espnet2.gan_svs.abs_gan_svs.AbsGANSVS
  • #espnet2.gan_svs.avocodo.avocodo.AvocodoDiscriminator
  • #espnet2.gan_svs.avocodo.avocodo.AvocodoDiscriminatorPlus
  • #espnet2.gan_svs.avocodo.avocodo.AvocodoGenerator
  • #espnet2.gan_svs.avocodo.avocodo.CoMBD
  • #espnet2.gan_svs.avocodo.avocodo.CoMBDBlock
  • #espnet2.gan_svs.avocodo.avocodo.get_padding
  • #espnet2.gan_svs.avocodo.avocodo.MDC
  • #espnet2.gan_svs.avocodo.avocodo.MDCDConfig
  • #espnet2.gan_svs.avocodo.avocodo.SBD
  • #espnet2.gan_svs.avocodo.avocodo.SBDBlock
  • #espnet2.gan_svs.espnet_model.ESPnetGANSVSModel
  • #espnet2.gan_svs.joint.joint_score2wav.JointScore2Wav
  • #espnet2.gan_svs.pits.modules.WN
  • #espnet2.gan_svs.pits.ying_decoder.YingDecoder
  • #espnet2.gan_svs.post_frontend.fused.FusedPostFrontends
  • #espnet2.gan_svs.post_frontend.s3prl.S3prlPostFrontend
  • #espnet2.gan_svs.uhifigan.sine_generator.SineGen
  • #espnet2.gan_svs.uhifigan.uhifigan.UHiFiGANGenerator
  • #espnet2.gan_svs.utils.expand_f0.expand_f0
  • #espnet2.gan_svs.visinger2.ddsp.amp_to_impulse_response
  • #espnet2.gan_svs.visinger2.ddsp.extract_loudness
  • #espnet2.gan_svs.visinger2.ddsp.extract_pitch
  • #espnet2.gan_svs.visinger2.ddsp.fft_convolve
  • #espnet2.gan_svs.visinger2.ddsp.gru
  • #espnet2.gan_svs.visinger2.ddsp.harmonic_synth
  • #espnet2.gan_svs.visinger2.ddsp.init_kernels
  • #espnet2.gan_svs.visinger2.ddsp.mean_std_loudness
  • #espnet2.gan_svs.visinger2.ddsp.mlp
  • #espnet2.gan_svs.visinger2.ddsp.multiscale_fft
  • #espnet2.gan_svs.visinger2.ddsp.remove_above_nyquist
  • #espnet2.gan_svs.visinger2.ddsp.resample
  • #espnet2.gan_svs.visinger2.ddsp.safe_log
  • #espnet2.gan_svs.visinger2.ddsp.scale_function
  • #espnet2.gan_svs.visinger2.ddsp.upsample
  • #espnet2.gan_svs.visinger2.visinger2_vocoder.BaseFrequenceDiscriminator
  • #espnet2.gan_svs.visinger2.visinger2_vocoder.ConvReluNorm
  • #espnet2.gan_svs.visinger2.visinger2_vocoder.create_fb_matrix
  • #espnet2.gan_svs.visinger2.visinger2_vocoder.Generator_Harm
  • #espnet2.gan_svs.visinger2.visinger2_vocoder.Generator_Noise
  • #espnet2.gan_svs.visinger2.visinger2_vocoder.LayerNorm
  • #espnet2.gan_svs.visinger2.visinger2_vocoder.MelScale
  • #espnet2.gan_svs.visinger2.visinger2_vocoder.MultiFrequencyDiscriminator
  • #espnet2.gan_svs.visinger2.visinger2_vocoder.TorchSTFT
  • #espnet2.gan_svs.visinger2.visinger2_vocoder.VISinger2Discriminator
  • #espnet2.gan_svs.visinger2.visinger2_vocoder.VISinger2VocoderGenerator
  • #espnet2.gan_svs.vits.duration_predictor.DurationPredictor
  • #espnet2.gan_svs.vits.generator.VISingerGenerator
  • #espnet2.gan_svs.vits.length_regulator.LengthRegulator
  • #espnet2.gan_svs.vits.modules.Projection
  • #espnet2.gan_svs.vits.modules.sequence_mask
  • #espnet2.gan_svs.vits.phoneme_predictor.PhonemePredictor
  • #espnet2.gan_svs.vits.pitch_predictor.Decoder
  • #espnet2.gan_svs.vits.prior_decoder.PriorDecoder
  • #espnet2.gan_svs.vits.text_encoder.TextEncoder
  • #espnet2.gan_svs.vits.vits.VITS

• #Gan Tts

  • #espnet2.gan_tts.abs_gan_tts.AbsGANTTS
  • #espnet2.gan_tts.espnet_model.ESPnetGANTTSModel
  • #espnet2.gan_tts.hifigan.hifigan.HiFiGANGenerator
  • #espnet2.gan_tts.hifigan.hifigan.HiFiGANMultiPeriodDiscriminator
  • #espnet2.gan_tts.hifigan.hifigan.HiFiGANMultiScaleDiscriminator
  • #espnet2.gan_tts.hifigan.hifigan.HiFiGANMultiScaleMultiPeriodDiscriminator
  • #espnet2.gan_tts.hifigan.hifigan.HiFiGANPeriodDiscriminator
  • #espnet2.gan_tts.hifigan.hifigan.HiFiGANScaleDiscriminator
  • #espnet2.gan_tts.hifigan.loss.DiscriminatorAdversarialLoss
  • #espnet2.gan_tts.hifigan.loss.FeatureMatchLoss
  • #espnet2.gan_tts.hifigan.loss.GeneratorAdversarialLoss
  • #espnet2.gan_tts.hifigan.loss.MelSpectrogramLoss
  • #espnet2.gan_tts.jets.alignments.AlignmentModule
  • #espnet2.gan_tts.jets.alignments.average_by_duration
  • #espnet2.gan_tts.jets.alignments.viterbi_decode
  • #espnet2.gan_tts.jets.generator.JETSGenerator
  • #espnet2.gan_tts.jets.jets.JETS
  • #espnet2.gan_tts.jets.length_regulator.GaussianUpsampling
  • #espnet2.gan_tts.jets.loss.ForwardSumLoss
  • #espnet2.gan_tts.jets.loss.VarianceLoss
  • #espnet2.gan_tts.joint.joint_text2wav.JointText2Wav
  • #espnet2.gan_tts.melgan.melgan.MelGANDiscriminator
  • #espnet2.gan_tts.melgan.melgan.MelGANGenerator
  • #espnet2.gan_tts.melgan.melgan.MelGANMultiScaleDiscriminator
  • #espnet2.gan_tts.melgan.pqmf.design_prototype_filter
  • #espnet2.gan_tts.melgan.pqmf.PQMF
  • #espnet2.gan_tts.melgan.residual_stack.ResidualStack
  • #espnet2.gan_tts.parallel_wavegan.parallel_wavegan.ParallelWaveGANDiscriminator
  • #espnet2.gan_tts.parallel_wavegan.parallel_wavegan.ParallelWaveGANGenerator
  • #espnet2.gan_tts.parallel_wavegan.upsample.Conv2d
  • #espnet2.gan_tts.parallel_wavegan.upsample.ConvInUpsampleNetwork
  • #espnet2.gan_tts.parallel_wavegan.upsample.Stretch2d
  • #espnet2.gan_tts.parallel_wavegan.upsample.UpsampleNetwork
  • #espnet2.gan_tts.style_melgan.style_melgan.StyleMelGANDiscriminator
  • #espnet2.gan_tts.style_melgan.style_melgan.StyleMelGANGenerator
  • #espnet2.gan_tts.style_melgan.tade_res_block.TADELayer
  • #espnet2.gan_tts.style_melgan.tade_res_block.TADEResBlock
  • #espnet2.gan_tts.utils.get_random_segments.get_random_segments
  • #espnet2.gan_tts.utils.get_random_segments.get_segments
  • #espnet2.gan_tts.vits.duration_predictor.StochasticDurationPredictor
  • #espnet2.gan_tts.vits.flow.ConvFlow
  • #espnet2.gan_tts.vits.flow.DilatedDepthSeparableConv
  • #espnet2.gan_tts.vits.flow.ElementwiseAffineFlow
  • #espnet2.gan_tts.vits.flow.FlipFlow
  • #espnet2.gan_tts.vits.flow.LogFlow
  • #espnet2.gan_tts.vits.flow.Transpose
  • #espnet2.gan_tts.vits.generator.VITSGenerator
  • #espnet2.gan_tts.vits.loss.KLDivergenceLoss
  • #espnet2.gan_tts.vits.loss.KLDivergenceLossWithoutFlow
  • #espnet2.gan_tts.vits.monotonic_align.setup.build_ext
  • #espnet2.gan_tts.vits.posterior_encoder.PosteriorEncoder
  • #espnet2.gan_tts.vits.residual_coupling.ResidualAffineCouplingBlock
  • #espnet2.gan_tts.vits.residual_coupling.ResidualAffineCouplingLayer
  • #espnet2.gan_tts.vits.text_encoder.TextEncoder
  • #espnet2.gan_tts.vits.transform.piecewise_rational_quadratic_transform
  • #espnet2.gan_tts.vits.transform.rational_quadratic_spline
  • #espnet2.gan_tts.vits.transform.unconstrained_rational_quadratic_spline
  • #espnet2.gan_tts.vits.vits.VITS
  • #espnet2.gan_tts.wavenet.residual_block.Conv1d
  • #espnet2.gan_tts.wavenet.residual_block.Conv1d1x1
  • #espnet2.gan_tts.wavenet.residual_block.ResidualBlock
  • #espnet2.gan_tts.wavenet.wavenet.WaveNet

• #Hubert

  • #espnet2.hubert.espnet_model.HubertPretrainModel
  • #espnet2.hubert.espnet_model.TorchAudioHubertPretrainModel
  • #espnet2.hubert.hubert_loss.HubertPretrainLoss

• #Iterators

  • #espnet2.iterators.abs_iter_factory.AbsIterFactory
  • #espnet2.iterators.category_chunk_iter_factory.CategoryChunkIterFactory
  • #espnet2.iterators.category_iter_factory.CategoryIterFactory
  • #espnet2.iterators.chunk_iter_factory.ChunkIterFactory
  • #espnet2.iterators.multiple_iter_factory.MultipleIterFactory
  • #espnet2.iterators.sequence_iter_factory.RawSampler
  • #espnet2.iterators.sequence_iter_factory.SequenceIterFactory
  • #espnet2.iterators.sequence_iter_factory.worker_init_fn

• #Layers

  • #espnet2.layers.abs_normalize.AbsNormalize
  • #espnet2.layers.augmentation.bandpass_filtering
  • #espnet2.layers.augmentation.bandreject_filtering
  • #espnet2.layers.augmentation.bandwidth_limitation
  • #espnet2.layers.augmentation.clipping
  • #espnet2.layers.augmentation.codecs
  • #espnet2.layers.augmentation.contrast
  • #espnet2.layers.augmentation.corrupt_phase
  • #espnet2.layers.augmentation.DataAugmentation
  • #espnet2.layers.augmentation.deemphasis
  • #espnet2.layers.augmentation.equalization_filtering
  • #espnet2.layers.augmentation.highpass_filtering
  • #espnet2.layers.augmentation.lowpass_filtering
  • #espnet2.layers.augmentation.pitch_shift
  • #espnet2.layers.augmentation.polarity_inverse
  • #espnet2.layers.augmentation.preemphasis
  • #espnet2.layers.augmentation.reverse
  • #espnet2.layers.augmentation.speed_perturb
  • #espnet2.layers.augmentation.time_stretch
  • #espnet2.layers.augmentation.weighted_sample_without_replacement
  • #espnet2.layers.create_adapter_fn.create_houlsby_adapter
  • #espnet2.layers.create_adapter_fn.create_lora_adapter
  • #espnet2.layers.create_adapter_fn.create_new_houlsby_module
  • #espnet2.layers.create_adapter_fn.create_new_lora_module
  • #espnet2.layers.create_adapter_utils.check_target_module_exists
  • #espnet2.layers.create_adapter_utils.get_submodules
  • #espnet2.layers.create_adapter_utils.replace_module
  • #espnet2.layers.create_adapter.create_adapter
  • #espnet2.layers.global_mvn.GlobalMVN
  • #espnet2.layers.houlsby_adapter_layer.Houlsby_Adapter
  • #espnet2.layers.inversible_interface.InversibleInterface
  • #espnet2.layers.label_aggregation.LabelAggregate
  • #espnet2.layers.log_mel.LogMel
  • #espnet2.layers.mask_along_axis.mask_along_axis
  • #espnet2.layers.mask_along_axis.MaskAlongAxis
  • #espnet2.layers.mask_along_axis.MaskAlongAxisVariableMaxWidth
  • #espnet2.layers.sinc_conv.BarkScale
  • #espnet2.layers.sinc_conv.LogCompression
  • #espnet2.layers.sinc_conv.MelScale
  • #espnet2.layers.sinc_conv.SincConv
  • #espnet2.layers.stft.Stft
  • #espnet2.layers.time_warp.time_warp
  • #espnet2.layers.time_warp.TimeWarp
  • #espnet2.layers.utterance_mvn.utterance_mvn
  • #espnet2.layers.utterance_mvn.UtteranceMVN

• #Lm

  • #espnet2.lm.abs_model.AbsLM
  • #espnet2.lm.espnet_model_multitask.ESPnetMultitaskLanguageModel
  • #espnet2.lm.espnet_model.ESPnetLanguageModel
  • #espnet2.lm.huggingface_pretrained_opt_lm.HuggingfaceOPTModel
  • #espnet2.lm.seq_rnn_lm.SequentialRNNLM
  • #espnet2.lm.transformer_lm.TransformerLM

• #Main Funcs

  • #espnet2.main_funcs.average_nbest_models.average_nbest_models
  • #espnet2.main_funcs.calculate_all_attentions.calculate_all_attentions
  • #espnet2.main_funcs.collect_stats.collect_stats
  • #espnet2.main_funcs.pack_funcs.Archiver
  • #espnet2.main_funcs.pack_funcs.find_path_and_change_it_recursive
  • #espnet2.main_funcs.pack_funcs.get_dict_from_cache
  • #espnet2.main_funcs.pack_funcs.pack
  • #espnet2.main_funcs.pack_funcs.unpack

• #Mt

  • #espnet2.mt.espnet_model.ESPnetMTModel
  • #espnet2.mt.frontend.embedding.CodecEmbedding
  • #espnet2.mt.frontend.embedding.Embedding
  • #espnet2.mt.frontend.embedding.PatchEmbedding

• #Optimizers

  • #espnet2.optimizers.optim_groups.add_optimizer_hooks
  • #espnet2.optimizers.optim_groups.configure_optimizer
  • #espnet2.optimizers.sgd.SGD

• #S2st

  • #espnet2.s2st.aux_attention.abs_aux_attention.AbsS2STAuxAttention
  • #espnet2.s2st.aux_attention.multihead.MultiHeadAttention
  • #espnet2.s2st.espnet_model.ESPnetS2STModel
  • #espnet2.s2st.losses.abs_loss.AbsS2STLoss
  • #espnet2.s2st.losses.attention_loss.S2STAttentionLoss
  • #espnet2.s2st.losses.ctc_loss.S2STCTCLoss
  • #espnet2.s2st.losses.guided_attention_loss.S2STGuidedAttentionLoss
  • #espnet2.s2st.losses.tacotron_loss.S2STTacotron2Loss
  • #espnet2.s2st.synthesizer.abs_synthesizer.AbsSynthesizer
  • #espnet2.s2st.synthesizer.discrete_synthesizer.TransformerDiscreteSynthesizer
  • #espnet2.s2st.synthesizer.translatotron.Translatotron
  • #espnet2.s2st.synthesizer.translatotron2.DurationPredictor
  • #espnet2.s2st.synthesizer.translatotron2.GaussianUpsampling
  • #espnet2.s2st.synthesizer.translatotron2.Prenet
  • #espnet2.s2st.synthesizer.translatotron2.Translatotron2
  • #espnet2.s2st.synthesizer.unity_synthesizer.UnitYSynthesizer
  • #espnet2.s2st.tgt_feats_extract.abs_tgt_feats_extract.AbsTgtFeatsExtract
  • #espnet2.s2st.tgt_feats_extract.linear_spectrogram.LinearSpectrogram
  • #espnet2.s2st.tgt_feats_extract.log_mel_fbank.LogMelFbank
  • #espnet2.s2st.tgt_feats_extract.log_spectrogram.LogSpectrogram

• #S2t

  • #espnet2.s2t.espnet_ctc_model.ESPnetS2TCTCModel
  • #espnet2.s2t.espnet_model.ESPnetS2TModel

• #Samplers

  • #espnet2.samplers.abs_sampler.AbsSampler
  • #espnet2.samplers.build_batch_sampler.build_batch_sampler
  • #espnet2.samplers.category_balanced_sampler.CategoryBalancedSampler
  • #espnet2.samplers.category_balanced_sampler.round_down
  • #espnet2.samplers.folded_batch_sampler.FoldedBatchSampler
  • #espnet2.samplers.length_batch_sampler.LengthBatchSampler
  • #espnet2.samplers.num_elements_batch_sampler.NumElementsBatchSampler
  • #espnet2.samplers.sorted_batch_sampler.SortedBatchSampler
  • #espnet2.samplers.unsorted_batch_sampler.UnsortedBatchSampler

• #Schedulers

  • #espnet2.schedulers.abs_scheduler.AbsBatchStepScheduler
  • #espnet2.schedulers.abs_scheduler.AbsEpochStepScheduler
  • #espnet2.schedulers.abs_scheduler.AbsScheduler
  • #espnet2.schedulers.abs_scheduler.AbsValEpochStepScheduler
  • #espnet2.schedulers.cosine_anneal_warmup_restart.CosineAnnealingWarmupRestarts
  • #espnet2.schedulers.noam_lr.NoamLR
  • #espnet2.schedulers.piecewise_linear_warmup_lr.PiecewiseLinearWarmupLR
  • #espnet2.schedulers.warmup_lr.WarmupLR
  • #espnet2.schedulers.warmup_reducelronplateau.WarmupReduceLROnPlateau
  • #espnet2.schedulers.warmup_step_lr.WarmupStepLR

• #Slu

  • #espnet2.slu.espnet_model.ESPnetSLUModel
  • #espnet2.slu.postdecoder.abs_postdecoder.AbsPostDecoder
  • #espnet2.slu.postdecoder.hugging_face_transformers_postdecoder.HuggingFaceTransformersPostDecoder
  • #espnet2.slu.postencoder.conformer_postencoder.ConformerPostEncoder
  • #espnet2.slu.postencoder.transformer_postencoder.TransformerPostEncoder

• #Speechlm

  • #espnet2.speechlm.core_lm.abs_core_lm.AbsCoreLM
  • #espnet2.speechlm.core_lm.abs_core_lm.SpeechLMInferenceOptions
  • #espnet2.speechlm.core_lm.ar_multiscale.MultiScaleLM
  • #espnet2.speechlm.core_lm.valle.ValleLM
  • #espnet2.speechlm.definitions.Modality
  • #espnet2.speechlm.definitions.pad_until
  • #espnet2.speechlm.definitions.SpeechLMTask
  • #espnet2.speechlm.espnet_model.ESPnetSpeechLMModel
  • #espnet2.speechlm.module.transformer.LayerNorm
  • #espnet2.speechlm.module.transformer.Linear
  • #espnet2.speechlm.module.transformer.MultiHeadAttention
  • #espnet2.speechlm.module.transformer.ResidualAttentionBlock
  • #espnet2.speechlm.module.transformer.TransformerDecoder
  • #espnet2.speechlm.module.valle.AdaLN
  • #espnet2.speechlm.module.valle.ResidualAttentionBlockAdaLM
  • #espnet2.speechlm.module.valle.ValleNARDecoder
  • #espnet2.speechlm.net_utils.causal_mask
  • #espnet2.speechlm.net_utils.ce_loss
  • #espnet2.speechlm.net_utils.install_kv_cache_hook
  • #espnet2.speechlm.net_utils.length_mask
  • #espnet2.speechlm.net_utils.logits_to_tokens
  • #espnet2.speechlm.tokenizer.abs_tokenizer.AbsTokenizer
  • #espnet2.speechlm.tokenizer.codec_tokenizer.CodecTokenizer

• #Spk

  • #espnet2.spk.encoder.conformer_encoder.MfaConformerEncoder
  • #espnet2.spk.encoder.ecapa_tdnn_encoder.EcapaTdnnEncoder
  • #espnet2.spk.encoder.identity_encoder.IdentityEncoder
  • #espnet2.spk.encoder.rawnet3_encoder.RawNet3Encoder
  • #espnet2.spk.encoder.ska_tdnn_encoder.Bottle2neck
  • #espnet2.spk.encoder.ska_tdnn_encoder.cwSKAttention
  • #espnet2.spk.encoder.ska_tdnn_encoder.fwSKAttention
  • #espnet2.spk.encoder.ska_tdnn_encoder.ResBlock
  • #espnet2.spk.encoder.ska_tdnn_encoder.SEModule
  • #espnet2.spk.encoder.ska_tdnn_encoder.SkaTdnnEncoder
  • #espnet2.spk.encoder.ska_tdnn_encoder.SKAttentionModule
  • #espnet2.spk.encoder.xvector_encoder.XvectorEncoder
  • #espnet2.spk.espnet_model.ESPnetSpeakerModel
  • #espnet2.spk.layers.ecapa_block.EcapaBlock
  • #espnet2.spk.layers.rawnet_block.AFMS
  • #espnet2.spk.loss.aamsoftmax_subcenter_intertopk.ArcMarginProduct_intertopk_subcenter
  • #espnet2.spk.loss.aamsoftmax.AAMSoftmax
  • #espnet2.spk.loss.abs_loss.AbsLoss
  • #espnet2.spk.pooling.abs_pooling.AbsPooling
  • #espnet2.spk.pooling.chn_attn_stat_pooling.ChnAttnStatPooling
  • #espnet2.spk.pooling.mean_pooling.MeanPooling
  • #espnet2.spk.pooling.stat_pooling.StatsPooling
  • #espnet2.spk.projector.abs_projector.AbsProjector
  • #espnet2.spk.projector.rawnet3_projector.RawNet3Projector
  • #espnet2.spk.projector.ska_tdnn_projector.SkaTdnnProjector
  • #espnet2.spk.projector.xvector_projector.XvectorProjector

• #St

  • #espnet2.st.espnet_model.ESPnetSTModel

• #Svs

  • #espnet2.svs.abs_svs.AbsSVS
  • #espnet2.svs.espnet_model.ESPnetSVSModel
  • #espnet2.svs.feats_extract.score_feats_extract.expand_to_frame
  • #espnet2.svs.feats_extract.score_feats_extract.FrameScoreFeats
  • #espnet2.svs.feats_extract.score_feats_extract.ListsToTensor
  • #espnet2.svs.feats_extract.score_feats_extract.SyllableScoreFeats
  • #espnet2.svs.naive_rnn.naive_rnn_dp.NaiveRNNDP
  • #espnet2.svs.naive_rnn.naive_rnn.NaiveRNN
  • #espnet2.svs.naive_rnn.naive_rnn.NaiveRNNLoss
  • #espnet2.svs.singing_tacotron.decoder.Decoder
  • #espnet2.svs.singing_tacotron.decoder.decoder_init
  • #espnet2.svs.singing_tacotron.encoder.Duration_Encoder
  • #espnet2.svs.singing_tacotron.encoder.Encoder
  • #espnet2.svs.singing_tacotron.encoder.encoder_init
  • #espnet2.svs.singing_tacotron.singing_tacotron.singing_tacotron
  • #espnet2.svs.xiaoice.loss.XiaoiceSing2Loss
  • #espnet2.svs.xiaoice.XiaoiceSing.XiaoiceSing

• #Tasks

  • #espnet2.tasks.abs_task.AbsTask
  • #espnet2.tasks.abs_task.IteratorOptions
  • #espnet2.tasks.asr_transducer.ASRTransducerTask
  • #espnet2.tasks.asr.ASRTask
  • #espnet2.tasks.asvspoof.ASVSpoofTask
  • #espnet2.tasks.diar.DiarizationTask
  • #espnet2.tasks.enh_s2t.EnhS2TTask
  • #espnet2.tasks.enh_tse.TargetSpeakerExtractionTask
  • #espnet2.tasks.enh.EnhancementTask
  • #espnet2.tasks.gan_codec.GANCodecTask
  • #espnet2.tasks.gan_svs.GANSVSTask
  • #espnet2.tasks.gan_tts.GANTTSTask
  • #espnet2.tasks.hubert.HubertTask
  • #espnet2.tasks.lm.LMTask
  • #espnet2.tasks.mt.MTTask
  • #espnet2.tasks.s2st.S2STTask
  • #espnet2.tasks.s2t_ctc.S2TTask
  • #espnet2.tasks.slu.SLUTask
  • #espnet2.tasks.speechlm.SpeechLMTask
  • #espnet2.tasks.spk.SpeakerTask
  • #espnet2.tasks.st.STTask
  • #espnet2.tasks.svs.SVSTask
  • #espnet2.tasks.tts.TTSTask
  • #espnet2.tasks.tts2.TTS2Task
  • #espnet2.tasks.uasr.UASRTask

• #Text

  • #espnet2.text.abs_tokenizer.AbsTokenizer
  • #espnet2.text.build_tokenizer.build_tokenizer
  • #espnet2.text.char_tokenizer.CharTokenizer
  • #espnet2.text.cleaner.TextCleaner
  • #espnet2.text.hugging_face_token_id_converter.HuggingFaceTokenIDConverter
  • #espnet2.text.hugging_face_tokenizer.HuggingFaceTokenizer
  • #espnet2.text.korean_cleaner.KoreanCleaner
  • #espnet2.text.phoneme_tokenizer.G2p_en
  • #espnet2.text.phoneme_tokenizer.G2pk
  • #espnet2.text.phoneme_tokenizer.IsG2p
  • #espnet2.text.phoneme_tokenizer.Jaso
  • #espnet2.text.phoneme_tokenizer.PhonemeTokenizer
  • #espnet2.text.phoneme_tokenizer.Phonemizer
  • #espnet2.text.phoneme_tokenizer.pyopenjtalk_g2p
  • #espnet2.text.phoneme_tokenizer.pyopenjtalk_g2p_accent
  • #espnet2.text.phoneme_tokenizer.pyopenjtalk_g2p_accent_with_pause
  • #espnet2.text.phoneme_tokenizer.pyopenjtalk_g2p_kana
  • #espnet2.text.phoneme_tokenizer.pyopenjtalk_g2p_prosody
  • #espnet2.text.phoneme_tokenizer.pypinyin_g2p
  • #espnet2.text.phoneme_tokenizer.pypinyin_g2p_phone
  • #espnet2.text.phoneme_tokenizer.pypinyin_g2p_phone_without_prosody
  • #espnet2.text.phoneme_tokenizer.split_by_space
  • #espnet2.text.sentencepiece_tokenizer.SentencepiecesTokenizer
  • #espnet2.text.token_id_converter.TokenIDConverter
  • #espnet2.text.whisper_token_id_converter.OpenAIWhisperTokenIDConverter
  • #espnet2.text.whisper_tokenizer.OpenAIWhisperTokenizer
  • #espnet2.text.word_tokenizer.WordTokenizer

• #Torch Utils

  • #espnet2.torch_utils.add_gradient_noise.add_gradient_noise
  • #espnet2.torch_utils.device_funcs.force_gatherable
  • #espnet2.torch_utils.device_funcs.to_device
  • #espnet2.torch_utils.forward_adaptor.ForwardAdaptor
  • #espnet2.torch_utils.get_flash_attn_compatability.is_flash_attn_supported
  • #espnet2.torch_utils.get_layer_from_string.get_layer
  • #espnet2.torch_utils.initialize.initialize
  • #espnet2.torch_utils.load_pretrained_model.filter_state_dict
  • #espnet2.torch_utils.load_pretrained_model.load_pretrained_model
  • #espnet2.torch_utils.model_summary.get_human_readable_count
  • #espnet2.torch_utils.model_summary.model_summary
  • #espnet2.torch_utils.model_summary.to_bytes
  • #espnet2.torch_utils.pytorch_version.pytorch_cudnn_version
  • #espnet2.torch_utils.recursive_op.recursive_average
  • #espnet2.torch_utils.recursive_op.recursive_divide
  • #espnet2.torch_utils.recursive_op.recursive_sum
  • #espnet2.torch_utils.set_all_random_seed.set_all_random_seed

• #Train

  • #espnet2.train.abs_espnet_model.AbsESPnetModel
  • #espnet2.train.abs_gan_espnet_model.AbsGANESPnetModel
  • #espnet2.train.class_choices.ClassChoices
  • #espnet2.train.collate_fn.common_collate_fn
  • #espnet2.train.collate_fn.CommonCollateFn
  • #espnet2.train.collate_fn.HuBERTCollateFn
  • #espnet2.train.dataset.AbsDataset
  • #espnet2.train.dataset.AdapterForLabelScpReader
  • #espnet2.train.dataset.AdapterForSingingScoreScpReader
  • #espnet2.train.dataset.AdapterForSoundScpReader
  • #espnet2.train.dataset.ESPnetDataset
  • #espnet2.train.dataset.ESPnetMultiTaskDataset
  • #espnet2.train.dataset.ESPnetSpeechLMDataset
  • #espnet2.train.dataset.H5FileWrapper
  • #espnet2.train.dataset.kaldi_loader
  • #espnet2.train.dataset.label_loader
  • #espnet2.train.dataset.multi_columns_sound_loader
  • #espnet2.train.dataset.rand_int_loader
  • #espnet2.train.dataset.score_loader
  • #espnet2.train.dataset.sound_loader
  • #espnet2.train.dataset.variable_columns_sound_loader
  • #espnet2.train.deepspeed_trainer.DeepSpeedTrainer
  • #espnet2.train.deepspeed_trainer.DeepSpeedTrainerOptions
  • #espnet2.train.distributed_utils.DistributedOption
  • #espnet2.train.distributed_utils.free_port
  • #espnet2.train.distributed_utils.get_local_rank
  • #espnet2.train.distributed_utils.get_master_addr
  • #espnet2.train.distributed_utils.get_master_port
  • #espnet2.train.distributed_utils.get_node_rank
  • #espnet2.train.distributed_utils.get_num_nodes
  • #espnet2.train.distributed_utils.get_rank
  • #espnet2.train.distributed_utils.get_world_size
  • #espnet2.train.distributed_utils.is_in_slurm_job
  • #espnet2.train.distributed_utils.is_in_slurm_step
  • #espnet2.train.distributed_utils.resolve_distributed_mode
  • #espnet2.train.gan_trainer.GANTrainer
  • #espnet2.train.gan_trainer.GANTrainerOptions
  • #espnet2.train.iterable_dataset.IterableESPnetDataset
  • #espnet2.train.iterable_dataset.load_kaldi
  • #espnet2.train.iterable_dataset.SplicedIterableESPnetDataset
  • #espnet2.train.preprocessor.AbsPreprocessor
  • #espnet2.train.preprocessor.any_allzero
  • #espnet2.train.preprocessor.CommonPreprocessor
  • #espnet2.train.preprocessor.CommonPreprocessor_multi
  • #espnet2.train.preprocessor.detect_non_silence
  • #espnet2.train.preprocessor.DynamicMixingPreprocessor
  • #espnet2.train.preprocessor.EnhPreprocessor
  • #espnet2.train.preprocessor.framing
  • #espnet2.train.preprocessor.MutliTokenizerCommonPreprocessor
  • #espnet2.train.preprocessor.S2TCTCPreprocessor
  • #espnet2.train.preprocessor.S2TPreprocessor
  • #espnet2.train.preprocessor.SLUPreprocessor
  • #espnet2.train.preprocessor.SpeechLMPreprocessor
  • #espnet2.train.preprocessor.SpkPreprocessor
  • #espnet2.train.preprocessor.SVSPreprocessor
  • #espnet2.train.preprocessor.TSEPreprocessor
  • #espnet2.train.reporter.aggregate
  • #espnet2.train.reporter.Average
  • #espnet2.train.reporter.ReportedValue
  • #espnet2.train.reporter.Reporter
  • #espnet2.train.reporter.SubReporter
  • #espnet2.train.reporter.to_reported_value
  • #espnet2.train.reporter.wandb_get_prefix
  • #espnet2.train.reporter.WeightedAverage
  • #espnet2.train.spk_trainer.SpkTrainer
  • #espnet2.train.trainer.Trainer
  • #espnet2.train.trainer.TrainerOptions
  • #espnet2.train.uasr_trainer.UASRTrainer
  • #espnet2.train.uasr_trainer.UASRTrainerOptions

• #Tts

  • #espnet2.tts.abs_tts.AbsTTS
  • #espnet2.tts.espnet_model.ESPnetTTSModel
  • #espnet2.tts.fastspeech.fastspeech.FastSpeech
  • #espnet2.tts.fastspeech2.fastspeech2.FastSpeech2
  • #espnet2.tts.fastspeech2.loss.FastSpeech2Loss
  • #espnet2.tts.fastspeech2.variance_predictor.VariancePredictor
  • #espnet2.tts.feats_extract.abs_feats_extract.AbsFeatsExtract
  • #espnet2.tts.feats_extract.dio.Dio
  • #espnet2.tts.feats_extract.energy.Energy
  • #espnet2.tts.feats_extract.linear_spectrogram.LinearSpectrogram
  • #espnet2.tts.feats_extract.log_mel_fbank.LogMelFbank
  • #espnet2.tts.feats_extract.log_spectrogram.LogSpectrogram
  • #espnet2.tts.feats_extract.yin.cumulativeMeanNormalizedDifferenceFunction
  • #espnet2.tts.feats_extract.yin.cumulativeMeanNormalizedDifferenceFunctionTorch
  • #espnet2.tts.feats_extract.yin.differenceFunction
  • #espnet2.tts.feats_extract.yin.differenceFunction_np
  • #espnet2.tts.feats_extract.yin.differenceFunctionTorch
  • #espnet2.tts.feats_extract.ying.Ying
  • #espnet2.tts.gst.style_encoder.MultiHeadedAttention
  • #espnet2.tts.gst.style_encoder.ReferenceEncoder
  • #espnet2.tts.gst.style_encoder.StyleEncoder
  • #espnet2.tts.gst.style_encoder.StyleTokenLayer
  • #espnet2.tts.prodiff.denoiser.Mish
  • #espnet2.tts.prodiff.denoiser.noise_scheduler
  • #espnet2.tts.prodiff.denoiser.ResidualBlock
  • #espnet2.tts.prodiff.denoiser.SpectogramDenoiser
  • #espnet2.tts.prodiff.loss.gaussian
  • #espnet2.tts.prodiff.loss.ProDiffLoss
  • #espnet2.tts.prodiff.loss.SSimLoss
  • #espnet2.tts.prodiff.prodiff.ProDiff
  • #espnet2.tts.tacotron2.tacotron2.Tacotron2
  • #espnet2.tts.transformer.transformer.Transformer
  • #espnet2.tts.utils.duration_calculator.DurationCalculator
  • #espnet2.tts.utils.parallel_wavegan_pretrained_vocoder.ParallelWaveGANPretrainedVocoder

• #Tts2

  • #espnet2.tts2.abs_tts2.AbsTTS2
  • #espnet2.tts2.espnet_model.ESPnetTTS2Model
  • #espnet2.tts2.fastspeech2.fastspeech2_discrete.FastSpeech2Discrete
  • #espnet2.tts2.fastspeech2.loss.FastSpeech2LossDiscrete
  • #espnet2.tts2.feats_extract.abs_feats_extract.AbsFeatsExtractDiscrete
  • #espnet2.tts2.feats_extract.identity.IdentityFeatureExtract

• #Uasr

  • #espnet2.uasr.discriminator.abs_discriminator.AbsDiscriminator
  • #espnet2.uasr.discriminator.conv_discriminator.ConvDiscriminator
  • #espnet2.uasr.espnet_model.ESPnetUASRModel
  • #espnet2.uasr.generator.abs_generator.AbsGenerator
  • #espnet2.uasr.generator.conv_generator.ConvGenerator
  • #espnet2.uasr.generator.conv_generator.SamePad
  • #espnet2.uasr.generator.conv_generator.TransposeLast
  • #espnet2.uasr.loss.abs_loss.AbsUASRLoss
  • #espnet2.uasr.loss.discriminator_loss.UASRDiscriminatorLoss
  • #espnet2.uasr.loss.gradient_penalty.UASRGradientPenalty
  • #espnet2.uasr.loss.phoneme_diversity_loss.UASRPhonemeDiversityLoss
  • #espnet2.uasr.loss.pseudo_label_loss.UASRPseudoLabelLoss
  • #espnet2.uasr.loss.smoothness_penalty.UASRSmoothnessPenalty
  • #espnet2.uasr.segmenter.abs_segmenter.AbsSegmenter
  • #espnet2.uasr.segmenter.join_segmenter.JoinSegmenter
  • #espnet2.uasr.segmenter.random_segmenter.RandomSegmenter

• #Utils

  • #espnet2.utils.build_dataclass.build_dataclass
  • #espnet2.utils.config_argparse.ArgumentParser
  • #espnet2.utils.eer.ComputeErrorRates
  • #espnet2.utils.eer.ComputeMinDcf
  • #espnet2.utils.eer.tuneThresholdfromScore
  • #espnet2.utils.get_default_kwargs.get_default_kwargs
  • #espnet2.utils.get_default_kwargs.Invalid
  • #espnet2.utils.griffin_lim.griffin_lim
  • #espnet2.utils.griffin_lim.logmel2linear
  • #espnet2.utils.griffin_lim.Spectrogram2Waveform
  • #espnet2.utils.kwargs2args.func
  • #espnet2.utils.kwargs2args.kwargs2args
  • #espnet2.utils.nested_dict_action.NestedDictAction
  • #espnet2.utils.sized_dict.get_size
  • #espnet2.utils.sized_dict.SizedDict
  • #espnet2.utils.types.float_or_none
  • #espnet2.utils.types.humanfriendly_parse_size_or_none
  • #espnet2.utils.types.int_or_none
  • #espnet2.utils.types.remove_parenthesis
  • #espnet2.utils.types.remove_quotes
  • #espnet2.utils.types.str_or_int
  • #espnet2.utils.types.str_or_none
  • #espnet2.utils.types.str2bool
  • #espnet2.utils.types.str2pair_str
  • #espnet2.utils.types.str2triple_str
  • #espnet2.utils.yaml_no_alias_safe_dump.NoAliasSafeDumper
  • #espnet2.utils.yaml_no_alias_safe_dump.yaml_no_alias_safe_dump