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
Nets
Less than 1 minute
Catalog
espnet.nets.asr_interface.ASRInterface
espnet.nets.asr_interface.dynamic_import_asr
espnet.nets.batch_beam_search_online_sim.BatchBeamSearchOnlineSim
espnet.nets.batch_beam_search_online.BatchBeamSearchOnline
espnet.nets.batch_beam_search.BatchBeamSearch
espnet.nets.batch_beam_search.BatchHypothesis
espnet.nets.beam_search_partially_AR.Hypothesis
espnet.nets.beam_search_partially_AR.PartiallyARBeamSearch
espnet.nets.beam_search_partially_AR.PartiallyARHypothesis
espnet.nets.beam_search_timesync_streaming.BeamSearchTimeSyncStreaming
espnet.nets.beam_search_timesync.BeamSearchTimeSync
espnet.nets.beam_search_timesync.CacheItem
espnet.nets.beam_search_transducer.BeamSearchTransducer
espnet.nets.beam_search.beam_search
espnet.nets.beam_search.BeamSearch
espnet.nets.chainer_backend.asr_interface.ChainerASRInterface
espnet.nets.chainer_backend.deterministic_embed_id.embed_id
espnet.nets.chainer_backend.deterministic_embed_id.EmbedID
espnet.nets.chainer_backend.deterministic_embed_id.EmbedIDFunction
espnet.nets.chainer_backend.deterministic_embed_id.EmbedIDGrad
espnet.nets.chainer_backend.transformer.attention.MultiHeadAttention
espnet.nets.chainer_backend.transformer.mask.make_history_mask
espnet.nets.chainer_backend.transformer.subsampling.LinearSampling
espnet.nets.chainer_backend.transformer.training.CustomConverter
espnet.nets.chainer_backend.transformer.training.CustomParallelUpdater
espnet.nets.chainer_backend.transformer.training.CustomUpdater
espnet.nets.chainer_backend.transformer.training.sum_sqnorm
espnet.nets.chainer_backend.transformer.training.VaswaniRule
espnet.nets.ctc_prefix_score.CTCPrefixScore
espnet.nets.ctc_prefix_score.CTCPrefixScoreTH
espnet.nets.e2e_asr_common.end_detect
espnet.nets.e2e_asr_common.get_vgg2l_odim
espnet.nets.e2e_asr_common.label_smoothing_dist
espnet.nets.lm_interface.dynamic_import_lm
espnet.nets.lm_interface.LMInterface
espnet.nets.mt_interface.MTInterface
espnet.nets.pytorch_backend.conformer.argument.add_arguments_conformer_common
espnet.nets.pytorch_backend.conformer.argument.verify_rel_pos_type
espnet.nets.pytorch_backend.conformer.contextual_block_encoder_layer.ContextualBlockEncoderLayer
espnet.nets.pytorch_backend.conformer.convolution.ConvolutionModule
espnet.nets.pytorch_backend.conformer.encoder_layer.EncoderLayer
espnet.nets.pytorch_backend.conformer.swish.Swish
espnet.nets.pytorch_backend.ctc.CTC
espnet.nets.pytorch_backend.ctc.ctc_for
espnet.nets.pytorch_backend.e2e_asr_mix.PIT
espnet.nets.pytorch_backend.e2e_asr.Reporter
espnet.nets.pytorch_backend.e2e_st_transformer.E2E
espnet.nets.pytorch_backend.e2e_tts_fastspeech.FeedForwardTransformer
espnet.nets.pytorch_backend.e2e_tts_fastspeech.FeedForwardTransformerLoss
espnet.nets.pytorch_backend.e2e_tts_tacotron2.GuidedAttentionLoss
espnet.nets.pytorch_backend.e2e_tts_tacotron2.Tacotron2Loss
espnet.nets.pytorch_backend.e2e_tts_transformer.GuidedMultiHeadAttentionLoss
espnet.nets.pytorch_backend.e2e_tts_transformer.Transformer
espnet.nets.pytorch_backend.e2e_vc_tacotron2.Tacotron2
espnet.nets.pytorch_backend.fastspeech.duration_calculator.DurationCalculator
espnet.nets.pytorch_backend.fastspeech.duration_predictor.DurationPredictor
espnet.nets.pytorch_backend.fastspeech.duration_predictor.DurationPredictorLoss
espnet.nets.pytorch_backend.fastspeech.length_regulator.LengthRegulator
espnet.nets.pytorch_backend.frontends.beamformer.apply_beamforming_vector
espnet.nets.pytorch_backend.frontends.beamformer.get_mvdr_vector
espnet.nets.pytorch_backend.frontends.beamformer.get_power_spectral_density_matrix
espnet.nets.pytorch_backend.frontends.dnn_beamformer.AttentionReference
espnet.nets.pytorch_backend.frontends.dnn_beamformer.DNN_Beamformer
espnet.nets.pytorch_backend.frontends.dnn_wpe.DNN_WPE
espnet.nets.pytorch_backend.frontends.feature_transform.feature_transform_for
espnet.nets.pytorch_backend.frontends.feature_transform.FeatureTransform
espnet.nets.pytorch_backend.frontends.feature_transform.GlobalMVN
espnet.nets.pytorch_backend.frontends.feature_transform.LogMel
espnet.nets.pytorch_backend.frontends.feature_transform.utterance_mvn
espnet.nets.pytorch_backend.frontends.feature_transform.UtteranceMVN
espnet.nets.pytorch_backend.frontends.frontend.Frontend
espnet.nets.pytorch_backend.frontends.frontend.frontend_for
espnet.nets.pytorch_backend.frontends.mask_estimator.MaskEstimator
espnet.nets.pytorch_backend.gtn_ctc.GTNCTCLossFunction
espnet.nets.pytorch_backend.initialization.lecun_normal_init_parameters
espnet.nets.pytorch_backend.initialization.set_forget_bias_to_one
espnet.nets.pytorch_backend.initialization.uniform_init_parameters
espnet.nets.pytorch_backend.lm.default.ClassifierWithState
espnet.nets.pytorch_backend.lm.default.DefaultRNNLM
espnet.nets.pytorch_backend.lm.default.RNNLM
espnet.nets.pytorch_backend.lm.seq_rnn.SequentialRNNLM
espnet.nets.pytorch_backend.lm.transformer.TransformerLM
espnet.nets.pytorch_backend.maskctc.add_mask_token.mask_uniform
espnet.nets.pytorch_backend.maskctc.mask.square_mask
espnet.nets.pytorch_backend.nets_utils.get_activation
espnet.nets.pytorch_backend.nets_utils.get_subsample
espnet.nets.pytorch_backend.nets_utils.make_non_pad_mask
espnet.nets.pytorch_backend.nets_utils.make_pad_mask
espnet.nets.pytorch_backend.nets_utils.mask_by_length
espnet.nets.pytorch_backend.nets_utils.pad_list
espnet.nets.pytorch_backend.nets_utils.rename_state_dict
espnet.nets.pytorch_backend.nets_utils.roll_tensor
espnet.nets.pytorch_backend.nets_utils.th_accuracy
espnet.nets.pytorch_backend.nets_utils.to_device
espnet.nets.pytorch_backend.nets_utils.to_torch_tensor
espnet.nets.pytorch_backend.nets_utils.trim_by_ctc_posterior
espnet.nets.pytorch_backend.nets_utils.triu_onnx
espnet.nets.pytorch_backend.rnn.argument.add_arguments_rnn_attention_common
espnet.nets.pytorch_backend.rnn.argument.add_arguments_rnn_decoder_common
espnet.nets.pytorch_backend.rnn.argument.add_arguments_rnn_encoder_common
espnet.nets.pytorch_backend.rnn.attentions.att_for
espnet.nets.pytorch_backend.rnn.attentions.att_to_numpy
espnet.nets.pytorch_backend.rnn.attentions.AttAdd
espnet.nets.pytorch_backend.rnn.attentions.AttCov
espnet.nets.pytorch_backend.rnn.attentions.AttCovLoc
espnet.nets.pytorch_backend.rnn.attentions.AttDot
espnet.nets.pytorch_backend.rnn.attentions.AttForward
espnet.nets.pytorch_backend.rnn.attentions.AttForwardTA
espnet.nets.pytorch_backend.rnn.attentions.AttLoc
espnet.nets.pytorch_backend.rnn.attentions.AttLoc2D
espnet.nets.pytorch_backend.rnn.attentions.AttLocRec
espnet.nets.pytorch_backend.rnn.attentions.AttMultiHeadAdd
espnet.nets.pytorch_backend.rnn.attentions.AttMultiHeadDot
espnet.nets.pytorch_backend.rnn.attentions.AttMultiHeadLoc
espnet.nets.pytorch_backend.rnn.attentions.AttMultiHeadMultiResLoc
espnet.nets.pytorch_backend.rnn.attentions.GDCAttLoc
espnet.nets.pytorch_backend.rnn.attentions.initial_att
espnet.nets.pytorch_backend.rnn.attentions.NoAtt
espnet.nets.pytorch_backend.rnn.decoders.decoder_for
espnet.nets.pytorch_backend.streaming.segment.SegmentStreamingE2E
espnet.nets.pytorch_backend.streaming.window.WindowStreamingE2E
espnet.nets.pytorch_backend.tacotron2.cbhg.CBHG
espnet.nets.pytorch_backend.tacotron2.cbhg.CBHGLoss
espnet.nets.pytorch_backend.tacotron2.cbhg.HighwayNet
espnet.nets.pytorch_backend.tacotron2.decoder.decoder_init
espnet.nets.pytorch_backend.tacotron2.decoder.Postnet
espnet.nets.pytorch_backend.tacotron2.decoder.Prenet
espnet.nets.pytorch_backend.tacotron2.decoder.ZoneOutCell
espnet.nets.pytorch_backend.tacotron2.encoder.encoder_init
espnet.nets.pytorch_backend.transducer.arguments.add_auxiliary_task_arguments
espnet.nets.pytorch_backend.transducer.arguments.add_custom_decoder_arguments
espnet.nets.pytorch_backend.transducer.arguments.add_custom_encoder_arguments
espnet.nets.pytorch_backend.transducer.arguments.add_custom_training_arguments
espnet.nets.pytorch_backend.transducer.arguments.add_decoder_general_arguments
espnet.nets.pytorch_backend.transducer.arguments.add_encoder_general_arguments
espnet.nets.pytorch_backend.transducer.arguments.add_rnn_decoder_arguments
espnet.nets.pytorch_backend.transducer.arguments.add_rnn_encoder_arguments
espnet.nets.pytorch_backend.transducer.arguments.add_transducer_arguments
espnet.nets.pytorch_backend.transducer.blocks.build_blocks
espnet.nets.pytorch_backend.transducer.blocks.build_conformer_block
espnet.nets.pytorch_backend.transducer.blocks.build_conv1d_block
espnet.nets.pytorch_backend.transducer.blocks.build_input_layer
espnet.nets.pytorch_backend.transducer.blocks.build_transformer_block
espnet.nets.pytorch_backend.transducer.blocks.get_pos_enc_and_att_class
espnet.nets.pytorch_backend.transducer.blocks.prepare_body_model
espnet.nets.pytorch_backend.transducer.blocks.prepare_input_layer
espnet.nets.pytorch_backend.transducer.blocks.verify_block_arguments
espnet.nets.pytorch_backend.transducer.conv1d_nets.CausalConv1d
espnet.nets.pytorch_backend.transducer.conv1d_nets.Conv1d
espnet.nets.pytorch_backend.transducer.custom_decoder.CustomDecoder
espnet.nets.pytorch_backend.transducer.custom_encoder.CustomEncoder
espnet.nets.pytorch_backend.transducer.error_calculator.ErrorCalculator
espnet.nets.pytorch_backend.transducer.initializer.initializer
espnet.nets.pytorch_backend.transducer.joint_network.JointNetwork
espnet.nets.pytorch_backend.transducer.rnn_decoder.RNNDecoder
espnet.nets.pytorch_backend.transducer.rnn_encoder.Encoder
espnet.nets.pytorch_backend.transducer.rnn_encoder.encoder_for
espnet.nets.pytorch_backend.transducer.rnn_encoder.reset_backward_rnn_state
espnet.nets.pytorch_backend.transducer.rnn_encoder.RNN
espnet.nets.pytorch_backend.transducer.rnn_encoder.RNNP
espnet.nets.pytorch_backend.transducer.rnn_encoder.VGG2L
espnet.nets.pytorch_backend.transducer.transducer_tasks.TransducerTasks
espnet.nets.pytorch_backend.transducer.transformer_decoder_layer.TransformerDecoderLayer
espnet.nets.pytorch_backend.transducer.utils.check_batch_states
espnet.nets.pytorch_backend.transducer.utils.check_state
espnet.nets.pytorch_backend.transducer.utils.create_lm_batch_states
espnet.nets.pytorch_backend.transducer.utils.custom_torch_load
espnet.nets.pytorch_backend.transducer.utils.get_decoder_input
espnet.nets.pytorch_backend.transducer.utils.init_lm_state
espnet.nets.pytorch_backend.transducer.utils.is_prefix
espnet.nets.pytorch_backend.transducer.utils.pad_sequence
espnet.nets.pytorch_backend.transducer.utils.recombine_hyps
espnet.nets.pytorch_backend.transducer.utils.select_k_expansions
espnet.nets.pytorch_backend.transducer.utils.select_lm_state
espnet.nets.pytorch_backend.transducer.utils.subtract
espnet.nets.pytorch_backend.transducer.utils.valid_aux_encoder_output_layers
espnet.nets.pytorch_backend.transformer.add_sos_eos.add_sos_eos
espnet.nets.pytorch_backend.transformer.argument.add_arguments_transformer_common
espnet.nets.pytorch_backend.transformer.attention.LegacyRelPositionMultiHeadedAttention
espnet.nets.pytorch_backend.transformer.attention.MultiHeadedAttention
espnet.nets.pytorch_backend.transformer.attention.RelPositionMultiHeadedAttention
espnet.nets.pytorch_backend.transformer.decoder_layer.DecoderLayer
espnet.nets.pytorch_backend.transformer.decoder.Decoder
espnet.nets.pytorch_backend.transformer.dynamic_conv.DynamicConvolution
espnet.nets.pytorch_backend.transformer.dynamic_conv2d.DynamicConvolution2D
espnet.nets.pytorch_backend.transformer.embedding.ConvolutionalPositionalEmbedding
espnet.nets.pytorch_backend.transformer.embedding.LearnableFourierPosEnc
espnet.nets.pytorch_backend.transformer.embedding.LegacyRelPositionalEncoding
espnet.nets.pytorch_backend.transformer.embedding.PositionalEncoding
espnet.nets.pytorch_backend.transformer.embedding.RelPositionalEncoding
espnet.nets.pytorch_backend.transformer.embedding.ScaledPositionalEncoding
espnet.nets.pytorch_backend.transformer.embedding.StreamPositionalEncoding
espnet.nets.pytorch_backend.transformer.encoder_mix.EncoderMix
espnet.nets.pytorch_backend.transformer.initializer.initialize
espnet.nets.pytorch_backend.transformer.label_smoothing_loss.LabelSmoothingLoss
espnet.nets.pytorch_backend.transformer.layer_norm.LayerNorm
espnet.nets.pytorch_backend.transformer.lightconv.LightweightConvolution
espnet.nets.pytorch_backend.transformer.lightconv2d.LightweightConvolution2D
espnet.nets.pytorch_backend.transformer.longformer_attention.LongformerAttention
espnet.nets.pytorch_backend.transformer.mask.subsequent_mask
espnet.nets.pytorch_backend.transformer.mask.target_mask
espnet.nets.pytorch_backend.transformer.multi_layer_conv.Conv1dLinear
espnet.nets.pytorch_backend.transformer.multi_layer_conv.MultiLayeredConv1d
espnet.nets.pytorch_backend.transformer.optimizer.get_std_opt
espnet.nets.pytorch_backend.transformer.optimizer.NoamOpt
espnet.nets.pytorch_backend.transformer.plot.plot_multi_head_attention
espnet.nets.pytorch_backend.transformer.plot.PlotAttentionReport
espnet.nets.pytorch_backend.transformer.plot.savefig
espnet.nets.pytorch_backend.transformer.positionwise_feed_forward.PositionwiseFeedForward
espnet.nets.pytorch_backend.transformer.repeat.MultiSequential
espnet.nets.pytorch_backend.transformer.repeat.repeat
espnet.nets.pytorch_backend.transformer.subsampling_without_posenc.Conv2dSubsamplingWOPosEnc
espnet.nets.pytorch_backend.transformer.subsampling.check_short_utt
espnet.nets.pytorch_backend.transformer.subsampling.Conv1dSubsampling1
espnet.nets.pytorch_backend.transformer.subsampling.Conv1dSubsampling2
espnet.nets.pytorch_backend.transformer.subsampling.Conv1dSubsampling3
espnet.nets.pytorch_backend.transformer.subsampling.Conv2dSubsampling
espnet.nets.pytorch_backend.transformer.subsampling.Conv2dSubsampling1
espnet.nets.pytorch_backend.transformer.subsampling.Conv2dSubsampling2
espnet.nets.pytorch_backend.transformer.subsampling.Conv2dSubsampling6
espnet.nets.pytorch_backend.transformer.subsampling.Conv2dSubsampling8
espnet.nets.pytorch_backend.transformer.subsampling.TooShortUttError
espnet.nets.pytorch_backend.wavenet.decode_mu_law
espnet.nets.pytorch_backend.wavenet.encode_mu_law
espnet.nets.pytorch_backend.wavenet.OneHot
espnet.nets.pytorch_backend.wavenet.UpSampling
espnet.nets.pytorch_backend.wavenet.WaveNet
espnet.nets.scorer_interface.BatchPartialScorerInterface
espnet.nets.scorer_interface.BatchScorerInterface
espnet.nets.scorer_interface.MaskParallelScorerInterface
espnet.nets.scorer_interface.PartialScorerInterface
espnet.nets.scorer_interface.ScorerInterface
espnet.nets.scorers.ctc.CTCPrefixScorer
espnet.nets.scorers.length_bonus.LengthBonus
espnet.nets.scorers.ngram.Ngrambase
espnet.nets.scorers.ngram.NgramFullScorer
espnet.nets.scorers.ngram.NgramPartScorer
espnet.nets.scorers.uasr.UASRPrefixScorer
espnet.nets.st_interface.dynamic_import_st
espnet.nets.st_interface.STInterface
espnet.nets.transducer_decoder_interface.ExtendedHypothesis
espnet.nets.transducer_decoder_interface.TransducerDecoderInterface
espnet.nets.tts_interface.TTSInterface
Prev
Mt
Next
Optimizer