from espnet2.enh.separator.rnn_separator import RNNSeparator
from espnet2.enh.separator.tcn_separator import TCNSeparator
from espnet2.enh.separator.transformer_separator import TransformerSeparator
from espnet2.tasks.abs_task import AbsTask
from espnet2.torch_utils.initialize import initialize
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
encoder_choices = ClassChoices(
name="encoder",
classes=dict(stft=STFTEncoder, conv=ConvEncoder, same=NullEncoder),
type_check=AbsEncoder,
default="stft",
)
separator_choices = ClassChoices(
name="separator",
classes=dict(
rnn=RNNSeparator,
tcn=TCNSeparator,
dprnn=DPRNNSeparator,
transformer=TransformerSeparator,
conformer=ConformerSeparator,
wpe_beamformer=NeuralBeamformer,
asteroid=AsteroidModel_Converter,
),
type_check=AbsSeparator,
from espnet2.torch_utils.initialize import initialize
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.preprocessor import CommonPreprocessor
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import int_or_none
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
frontend_choices = ClassChoices(
name="frontend",
classes=dict(
default=DefaultFrontend,
sliding_window=SlidingWindow,
s3prl=S3prlFrontend,
),
type_check=AbsFrontend,
default="default",
)
normalize_choices = ClassChoices(
"normalize",
classes=dict(
global_mvn=GlobalMVN,
utterance_mvn=UtteranceMVN,
),
type_check=AbsNormalize,
default="utterance_mvn",
optional=True,
)
label_aggregator_choices = ClassChoices(
from espnet2.layers.utterance_mvn import UtteranceMVN
from espnet2.tasks.abs_task import AbsTask
from espnet2.text.phoneme_tokenizer import g2p_choices
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.preprocessor import CommonPreprocessor
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import float_or_none, int_or_none, str2bool, str_or_none
frontend_choices = ClassChoices(
name="frontend",
classes=dict(
default=DefaultFrontend,
sliding_window=SlidingWindow,
),
type_check=AbsFrontend,
default="default",
)
specaug_choices = ClassChoices(
"specaug",
classes=dict(specaug=SpecAug, ),
type_check=AbsSpecAug,
default=None,
optional=True,
)
normalize_choices = ClassChoices(
"normalize",
classes=dict(
global_mvn=GlobalMVN,
from espnet2.tts.feats_extract.log_spectrogram import LogSpectrogram
from espnet2.tts.tacotron2 import Tacotron2
from espnet2.tts.transformer import Transformer
from espnet2.tts.utils import ParallelWaveGANPretrainedVocoder
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.griffin_lim import Spectrogram2Waveform
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import int_or_none
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
feats_extractor_choices = ClassChoices(
"feats_extract",
classes=dict(
fbank=LogMelFbank,
spectrogram=LogSpectrogram,
linear_spectrogram=LinearSpectrogram,
),
type_check=AbsFeatsExtract,
default="fbank",
)
pitch_extractor_choices = ClassChoices(
"pitch_extract",
classes=dict(dio=Dio),
type_check=AbsFeatsExtract,
default=None,
optional=True,
)
energy_extractor_choices = ClassChoices(
"energy_extract",
classes=dict(energy=Energy),
type_check=AbsFeatsExtract,
from espnet2.enh.separator.skim_separator import SkiMSeparator
from espnet2.enh.separator.tcn_separator import TCNSeparator
from espnet2.enh.separator.transformer_separator import TransformerSeparator
from espnet2.tasks.abs_task import AbsTask
from espnet2.torch_utils.initialize import initialize
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
encoder_choices = ClassChoices(
name="encoder",
classes=dict(stft=STFTEncoder, conv=ConvEncoder, same=NullEncoder),
type_check=AbsEncoder,
default="stft",
)
separator_choices = ClassChoices(
name="separator",
classes=dict(
rnn=RNNSeparator,
skim=SkiMSeparator,
tcn=TCNSeparator,
dprnn=DPRNNSeparator,
dccrn=DCCRNSeparator,
transformer=TransformerSeparator,
conformer=ConformerSeparator,
wpe_beamformer=NeuralBeamformer,
asteroid=AsteroidModel_Converter,
from espnet2.enh.separator.svoice_separator import SVoiceSeparator
from espnet2.enh.separator.tcn_separator import TCNSeparator
from espnet2.enh.separator.transformer_separator import TransformerSeparator
from espnet2.tasks.abs_task import AbsTask
from espnet2.torch_utils.initialize import initialize
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
encoder_choices = ClassChoices(
name="encoder",
classes=dict(stft=STFTEncoder, conv=ConvEncoder, same=NullEncoder),
type_check=AbsEncoder,
default="stft",
)
separator_choices = ClassChoices(
name="separator",
classes=dict(
asteroid=AsteroidModel_Converter,
conformer=ConformerSeparator,
dan=DANSeparator,
dc_crn=DC_CRNSeparator,
dccrn=DCCRNSeparator,
dpcl=DPCLSeparator,
dpcl_e2e=DPCLE2ESeparator,
dprnn=DPRNNSeparator,
fasnet=FaSNetSeparator,
from espnet2.train.preprocessor import CommonPreprocessor
from espnet2.tts.feats_extract.abs_feats_extract import AbsFeatsExtract
from espnet2.tts.feats_extract.dio import Dio
from espnet2.tts.feats_extract.energy import Energy
from espnet2.tts.feats_extract.linear_spectrogram import LinearSpectrogram
from espnet2.tts.feats_extract.log_mel_fbank import LogMelFbank
from espnet2.tts.feats_extract.log_spectrogram import LogSpectrogram
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import int_or_none, str2bool, str_or_none
feats_extractor_choices = ClassChoices(
"feats_extract",
classes=dict(
fbank=LogMelFbank,
log_spectrogram=LogSpectrogram,
linear_spectrogram=LinearSpectrogram,
),
type_check=AbsFeatsExtract,
default="linear_spectrogram",
)
normalize_choices = ClassChoices(
"normalize",
classes=dict(
global_mvn=GlobalMVN,
utterance_mvn=UtteranceMVN,
),
type_check=AbsNormalize,
default=None,
optional=True,
)
tts_choices = ClassChoices(
from espnet2.tts.feats_extract.abs_feats_extract import AbsFeatsExtract
from espnet2.tts.feats_extract.dio import Dio
from espnet2.tts.feats_extract.energy import Energy
from espnet2.tts.feats_extract.log_mel_fbank import LogMelFbank
from espnet2.tts.feats_extract.log_spectrogram import LogSpectrogram
from espnet2.tts.tacotron2 import Tacotron2
from espnet2.tts.transformer import Transformer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import int_or_none
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
feats_extractor_choices = ClassChoices(
"feats_extract",
classes=dict(fbank=LogMelFbank, spectrogram=LogSpectrogram),
type_check=AbsFeatsExtract,
default="fbank",
)
pitch_extractor_choices = ClassChoices(
"pitch_extract",
classes=dict(dio=Dio),
type_check=AbsFeatsExtract,
default=None,
optional=True,
)
energy_extractor_choices = ClassChoices(
"energy_extract",
classes=dict(energy=Energy),
type_check=AbsFeatsExtract,
default=None,
optional=True,
from espnet2.tasks.abs_task import AbsTask
from espnet2.torch_utils.initialize import initialize
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.preprocessor import CommonPreprocessorPairedSpeech
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import float_or_none
from espnet2.utils.types import int_or_none
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
frontend_choices = ClassChoices(
name="frontend",
classes=dict(robust=RobustFrontend, ),
type_check=AbsFrontend,
default="robust",
)
encoder_choices = ClassChoices(
"encoder",
classes=dict(
conformer=ConformerEncoder,
transformer=TransformerEncoder,
contextual_block_transformer=ContextualBlockTransformerEncoder,
vgg_rnn=VGGRNNEncoder,
rnn=RNNEncoder,
wav2vec2=FairSeqWav2Vec2Encoder,
hubert=FairseqHubertEncoder,
hubert_pretrain=FairseqHubertPretrainEncoder,
),
from espnet2.mt.espnet_model import ESPnetMTModel
from espnet2.mt.frontend.embedding import Embedding
from espnet2.tasks.abs_task import AbsTask
from espnet2.text.phoneme_tokenizer import g2p_choices
from espnet2.torch_utils.initialize import initialize
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.preprocessor import MutliTokenizerCommonPreprocessor
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import int_or_none, str2bool, str_or_none
frontend_choices = ClassChoices(
name="frontend",
classes=dict(embed=Embedding, ),
type_check=AbsFrontend,
default="embed",
)
preencoder_choices = ClassChoices(
name="preencoder",
classes=dict(
sinc=LightweightSincConvs,
linear=LinearProjection,
),
type_check=AbsPreEncoder,
default=None,
optional=True,
)
encoder_choices = ClassChoices(
"encoder",
classes=dict(
from espnet2.text.phoneme_tokenizer import g2p_choices
from espnet2.torch_utils.initialize import initialize
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.preprocessor import CommonPreprocessor
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import float_or_none
from espnet2.utils.types import int_or_none
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
frontend_choices = ClassChoices(
name="frontend",
classes=dict(default=DefaultFrontend, sliding_window=SlidingWindow),
type_check=AbsFrontend,
default="default",
)
specaug_choices = ClassChoices(
name="specaug",
classes=dict(specaug=SpecAug),
type_check=AbsSpecAug,
default=None,
optional=True,
)
normalize_choices = ClassChoices(
"normalize",
classes=dict(
global_mvn=GlobalMVN,
utterance_mvn=UtteranceMVN,
),
from espnet2.lm.transformer_lm import TransformerLM
from hynet.main_funcs.collect_stats import collect_stats
from hynet.train.trainer import Trainer
from hynet.layers.fair_like_norm import FairNormalize
from hynet.asr.espnet_model import ESPnetASRModel
from hynet.asr.encoder.wav2vec2_encoder import FairSeqWav2VecCtc
from hynet.asr.ctc import CTC
from hynet.schedulers.tri_stage_lr import TriStageLR
frontend_choices = ClassChoices(
name="frontend",
classes=dict(default=DefaultFrontend, sliding_window=SlidingWindow),
type_check=AbsFrontend,
default="default",
)
specaug_choices = ClassChoices(
name="specaug",
classes=dict(specaug=SpecAug),
type_check=AbsSpecAug,
default=None,
optional=True,
)
normalize_choices = ClassChoices(
"normalize",
classes=dict(
global_mvn=GlobalMVN,
utterance_mvn=UtteranceMVN,
fair_like_norm=FairNormalize,
from espnet2.enh.nets.tasnet import TasNet
from espnet2.enh.nets.tf_mask_net import TFMaskingNet
from espnet2.tasks.abs_task import AbsTask
from espnet2.torch_utils.initialize import initialize
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
enh_choices = ClassChoices(
name="enh",
classes=dict(tf_masking=TFMaskingNet,
tasnet=TasNet,
wpe_beamformer=BeamformerNet),
type_check=AbsEnhancement,
default="tf_masking",
)
MAX_REFERENCE_NUM = 100
class EnhancementTask(AbsTask):
# If you need more than one optimizers, change this value
num_optimizers: int = 1
class_choices_list = [
# --enh and --enh_conf
enh_choices,
]
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.preprocessor import MutliTokenizerCommonPreprocessor
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import float_or_none
from espnet2.utils.types import int_or_none
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
frontend_choices = ClassChoices(
name="frontend",
classes=dict(
default=DefaultFrontend,
sliding_window=SlidingWindow,
s3prl=S3prlFrontend,
),
type_check=AbsFrontend,
default="default",
)
specaug_choices = ClassChoices(
name="specaug",
classes=dict(specaug=SpecAug),
type_check=AbsSpecAug,
default=None,
optional=True,
)
normalize_choices = ClassChoices(
"normalize",
classes=dict(
global_mvn=GlobalMVN,
from espnet2.asr.frontend.windowing import SlidingWindow
from espnet2.asr.maskctc_model import MaskCTCModel
from espnet2.asr.postencoder.abs_postencoder import AbsPostEncoder
from espnet2.layers.global_mvn import GlobalMVN
from espnet2.layers.utterance_mvn import UtteranceMVN
from espnet2.layers.abs_normalize import AbsNormalize
encoder_choices = ClassChoices(
"encoder",
classes=dict(
conformer=ConformerEncoder,
transformer=TransformerEncoder,
contextual_block_transformer=ContextualBlockTransformerEncoder,
vgg_rnn=VGGRNNEncoder,
rnn=RNNEncoder,
wav2vec2=FairSeqWav2Vec2Encoder,
hubert=FairseqHubertEncoder,
hubert_pretrain=FairseqHubertPretrainEncoder,
),
type_check=AbsEncoder,
default="rnn",
)
normalize_choices = ClassChoices(
"normalize",
classes=dict(
global_mvn=GlobalMVN,
utterance_mvn=UtteranceMVN,
),
type_check=AbsNormalize,
from espnet2.layers.utterance_mvn import UtteranceMVN
from espnet2.tasks.abs_task import AbsTask
from espnet2.torch_utils.initialize import initialize
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.preprocessor import CommonPreprocessor
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import int_or_none
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
frontend_choices = ClassChoices(
name="frontend",
classes=dict(default=DefaultFrontend),
type_check=AbsFrontend,
default="default",
)
specaug_choices = ClassChoices(
name="specaug",
classes=dict(specaug=SpecAug),
type_check=AbsSpecAug,
default=None,
optional=True,
)
normalize_choices = ClassChoices(
"normalize",
classes=dict(
global_mvn=GlobalMVN,
utterance_mvn=UtteranceMVN,
),
from espnet2.torch_utils.initialize import initialize
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.preprocessor import CommonPreprocessor
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
lm_choices = ClassChoices(
"lm",
classes=dict(
seq_rnn=SequentialRNNLM,
transformer=TransformerLM,
),
type_check=AbsLM,
default="seq_rnn",
)
class LMTask(AbsTask):
# If you need more than one optimizers, change this value
num_optimizers: int = 1
# Add variable objects configurations
class_choices_list = [lm_choices]
# If you need to modify train() or eval() procedures, change Trainer class here
trainer = Trainer
from espnet2.layers.utterance_mvn import UtteranceMVN
from espnet2.tasks.abs_task import AbsTask
from espnet2.torch_utils.initialize import initialize
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.preprocessor import CommonPreprocessor_multi
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import int_or_none
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
enh_choices = ClassChoices(
name="enh",
classes=dict(tf_masking=TFMaskingNet, tasnet=TasNet, wpe_beamformer=BeamformerNet),
type_check=AbsEnhancement,
default="tf_masking",
)
frontend_choices = ClassChoices(
name="frontend",
classes=dict(default=DefaultFrontend),
type_check=AbsFrontend,
default="default",
)
specaug_choices = ClassChoices(
name="specaug",
classes=dict(specaug=SpecAug),
type_check=AbsSpecAug,
default=None,
optional=True,
)
from espnet2.tts.abs_tts import AbsTTS
from espnet2.tts.espnet_model import ESPnetTTSModel
from espnet2.tts.feats_extract.abs_feats_extract import AbsFeatsExtract
from espnet2.tts.feats_extract.log_mel_fbank import LogMelFbank
from espnet2.tts.feats_extract.log_spectrogram import LogSpectrogram
from espnet2.tts.tacotron2 import Tacotron2
from espnet2.tts.transformer import Transformer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import int_or_none
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
feats_extractor_choices = ClassChoices(
"feats_extract",
classes=dict(fbank=LogMelFbank, spectrogram=LogSpectrogram),
type_check=AbsFeatsExtract,
default="fbank",
)
normalize_choices = ClassChoices(
"normalize",
classes=dict(global_mvn=GlobalMVN),
type_check=AbsNormalize,
default="global_mvn",
optional=True,
)
tts_choices = ClassChoices(
"tts",
classes=dict(tacotron2=Tacotron2, transformer=Transformer),
type_check=AbsTTS,
default="tacotron2",
)
from espnet2.lm.espnet_model import ESPnetLanguageModel
from espnet2.lm.seq_rnn import SequentialRNNLM
from espnet2.tasks.abs_task import AbsTask
from espnet2.torch_utils.initialize import initialize
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.preprocessor import CommonPreprocessor
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import str2bool
from espnet2.utils.types import str_or_none
lm_choices = ClassChoices(
"lm", classes=dict(seq_rnn=SequentialRNNLM), type_check=AbsLM, default="seq_rnn"
)
class LMTask(AbsTask):
# If you need more than one optimizers, change this value
num_optimizers: int = 1
# Add variable objects configurations
class_choices_list = [lm_choices]
# If you need to modify train() or eval() procedures, change Trainer class here
trainer = Trainer
@classmethod
def add_task_arguments(cls, parser: argparse.ArgumentParser):
from espnet2.train.class_choices import ClassChoices
from espnet2.train.collate_fn import CommonCollateFn
from espnet2.train.preprocessor import CommonPreprocessor
from espnet2.train.trainer import Trainer
from espnet2.utils.get_default_kwargs import get_default_kwargs
from espnet2.utils.nested_dict_action import NestedDictAction
from espnet2.utils.types import int_or_none
from espnet2.utils.types import str_or_none
from moneynet2.imgr.imgr_model import HynetImgrModel
normalize_choices = ClassChoices(
"normalize",
classes=dict(
global_mvn=GlobalMVN,
utterance_mvn=UtteranceMVN,
),
type_check=AbsNormalize,
default="utterance_mvn",
optional=True,
)
class ImgrTask(AbsTask):
# If you need more than one optimizers, change this value
num_optimizers: int = 1
# Add variable objects configurations
class_choices_list = [
# --normalize and --normalize_conf
normalize_choices,
]
