nnsvs
0.1.0
Demos
NNSVS demos
Guides
Installation guide
Getting started with recipes
How to choose model
Defining your custom model
Development guide
Tips
Update guide
Advanced guides
Hyperparameter optimization with Optuna
How to train neural vocoders with ParallelWaveGAN
How to train uSFGAN/SiFiGAN vocoders
How to convert ENUNU models to NNSVS’ ones
Notes
Overview of NNSVS’s SVS
Package reference
nnsvs.base
nnsvs.model
nnsvs.acoustic_models
nnsvs.postfilters
nnsvs.discriminators
nnsvs.pretrained
nnsvs.svs
nnsvs.dsp
nnsvs.gen
nnsvs.io
nnsvs.mdn
nnsvs.pitch
nnsvs.multistream
nnsvs.util
nnsvs.train_util
Resources
Useful links
Papers
Meta information
Change log
nnsvs
Index
Index
B
|
C
|
D
|
E
|
F
|
G
|
H
|
I
|
L
|
M
|
N
|
O
|
P
|
R
|
S
|
T
|
V
B
bandpass_filter() (in module nnsvs.dsp)
BaseModel (class in nnsvs.base)
BaseSVS (class in nnsvs.svs)
batch_by_size() (in module nnsvs.train_util)
BiLSTMMDNNonAttentiveDecoder (class in nnsvs.acoustic_models)
BiLSTMNonAttentiveDecoder (class in nnsvs.acoustic_models)
BiLSTMResF0NonAttentiveDecoder (class in nnsvs.acoustic_models)
C
cent_to_hz_based_c4() (in module nnsvs.pitch)
collate_fn_default() (in module nnsvs.train_util)
collate_fn_random_segments() (in module nnsvs.train_util)
compute_batch_pitch_regularization_weight() (in module nnsvs.train_util)
compute_distortions() (in module nnsvs.train_util)
compute_pitch_regularization_weight() (in module nnsvs.train_util)
Conv1dResnet (class in nnsvs.model)
Conv1dResnetMDN (class in nnsvs.model)
Conv1dResnetSAR (class in nnsvs.model)
Conv2dD (class in nnsvs.discriminators)
Conv2dPostFilter (class in nnsvs.postfilters)
correct_vuv_by_phone() (in module nnsvs.gen)
create_svs_engine() (in module nnsvs.pretrained)
D
DETERMINISTIC (nnsvs.base.PredictionType attribute)
DIFFUSION (nnsvs.base.PredictionType attribute)
dim_wise (nnsvs.mdn.MDNLayer attribute)
dynamic_import() (in module nnsvs.util)
E
ensure_divisible_by() (in module nnsvs.train_util)
example_xml_file() (in module nnsvs.util)
extract_vibrato_likelihood() (in module nnsvs.pitch)
extract_vibrato_parameters() (in module nnsvs.pitch)
F
FFConvLSTM (class in nnsvs.model)
FFN (class in nnsvs.model)
forward() (nnsvs.base.BaseModel method)
(nnsvs.mdn.MDNLayer method)
G
gen_sine_vibrato() (in module nnsvs.pitch)
gen_spsvs_static_features() (in module nnsvs.gen)
gen_world_params() (in module nnsvs.gen)
get_available_model_ids() (in module nnsvs.pretrained)
get_data_loaders() (in module nnsvs.train_util)
get_note_frame_indices() (in module nnsvs.io.hts)
get_note_indices() (in module nnsvs.io.hts)
get_num_phrases() (nnsvs.svs.NEUTRINO method)
get_phraselist() (nnsvs.svs.NEUTRINO method)
get_pitch_index() (in module nnsvs.io.hts)
get_pitch_indices() (in module nnsvs.io.hts)
get_static_features() (in module nnsvs.multistream)
get_static_stream_sizes() (in module nnsvs.multistream)
get_windows() (in module nnsvs.gen)
(in module nnsvs.multistream)
get_world_stream_info() (in module nnsvs.util)
H
has_residual_lf0_prediction() (nnsvs.base.BaseModel method)
hz_to_cent_based_c4() (in module nnsvs.pitch)
I
in_dim (nnsvs.mdn.MDNLayer attribute)
inference() (nnsvs.base.BaseModel method)
init_seed() (in module nnsvs.util)
init_weights() (in module nnsvs.util)
is_autoregressive() (nnsvs.base.BaseModel method)
L
load_utt_list() (in module nnsvs.util)
lowpass_filter() (in module nnsvs.dsp)
LSTMEncoder (class in nnsvs.model)
LSTMRNN (class in nnsvs.model)
LSTMRNNSAR (class in nnsvs.model)
M
make_non_pad_mask() (in module nnsvs.util)
make_pad_mask() (in module nnsvs.util)
MDN (class in nnsvs.model)
mdn_get_most_probable_sigma_and_mu() (in module nnsvs.mdn)
mdn_get_sample() (in module nnsvs.mdn)
mdn_loss() (in module nnsvs.mdn)
MDNLayer (class in nnsvs.mdn)
MDNMultistreamSeparateF0MelModel (class in nnsvs.acoustic_models)
MDNNonAttentiveDecoder (class in nnsvs.acoustic_models)
MDNResF0NonAttentiveDecoder (class in nnsvs.acoustic_models)
MDNv2 (class in nnsvs.model)
MinMaxScaler (class in nnsvs.util)
module
nnsvs.acoustic_models
nnsvs.base
nnsvs.discriminators
nnsvs.dsp
nnsvs.gen
nnsvs.io.hts
nnsvs.mdn
nnsvs.model
nnsvs.multistream
nnsvs.pitch
nnsvs.postfilters
nnsvs.pretrained
nnsvs.svs
nnsvs.train_util
nnsvs.util
multi_stream_mlpg() (in module nnsvs.multistream)
MULTISTREAM_HYBRID (nnsvs.base.PredictionType attribute)
MultistreamPostFilter (class in nnsvs.postfilters)
MultistreamSeparateF0MelModel (class in nnsvs.acoustic_models)
MultistreamSeparateF0ParametricModel (class in nnsvs.acoustic_models)
musicxml2label() (nnsvs.svs.NEUTRINO class method)
N
NEUTRINO (class in nnsvs.svs)
nnsvs.acoustic_models
module
nnsvs.base
module
nnsvs.discriminators
module
nnsvs.dsp
module
nnsvs.gen
module
nnsvs.io.hts
module
nnsvs.mdn
module
nnsvs.model
module
nnsvs.multistream
module
nnsvs.pitch
module
nnsvs.postfilters
module
nnsvs.pretrained
module
nnsvs.svs
module
nnsvs.train_util
module
nnsvs.util
module
NonAttentiveDecoder (class in nnsvs.acoustic_models)
nonzero_segments() (in module nnsvs.pitch)
note_segments() (in module nnsvs.train_util)
NPSSMDNMultistreamParametricModel (class in nnsvs.acoustic_models)
NPSSMultistreamParametricModel (class in nnsvs.acoustic_models)
num_gaussians (nnsvs.mdn.MDNLayer attribute)
num_trainable_params() (in module nnsvs.train_util)
O
out_dim (nnsvs.mdn.MDNLayer attribute)
P
pad_2d() (in module nnsvs.util)
plot_spsvs_params() (in module nnsvs.train_util)
postprocess_acoustic() (in module nnsvs.gen)
(nnsvs.svs.SPSVS method)
postprocess_duration() (in module nnsvs.gen)
(nnsvs.svs.SPSVS method)
postprocess_waveform() (in module nnsvs.gen)
(nnsvs.svs.SPSVS method)
predict_acoustic() (in module nnsvs.gen)
(nnsvs.svs.NEUTRINO method)
(nnsvs.svs.SPSVS method)
predict_duration() (in module nnsvs.gen)
(nnsvs.svs.SPSVS method)
predict_timelag() (in module nnsvs.gen)
(nnsvs.svs.SPSVS method)
predict_timing() (in module nnsvs.gen)
(nnsvs.svs.SPSVS method)
predict_waveform() (in module nnsvs.gen)
(nnsvs.svs.NEUTRINO method)
(nnsvs.svs.SPSVS method)
prediction_type() (nnsvs.base.BaseModel method)
PredictionType (class in nnsvs.base)
preprocess_target() (nnsvs.base.BaseModel method)
PROBABILISTIC (nnsvs.base.PredictionType attribute)
PyTorchStandardScaler (class in nnsvs.util)
R
ResF0Conv1dResnet (class in nnsvs.acoustic_models)
ResF0NonAttentiveDecoder (class in nnsvs.acoustic_models)
ResF0VariancePredictor (class in nnsvs.acoustic_models)
ResSkipF0FFConvLSTM (class in nnsvs.acoustic_models)
retrieve_pretrained_model() (in module nnsvs.pretrained)
RMDN (class in nnsvs.model)
S
save_checkpoint() (in module nnsvs.train_util)
select_streams() (in module nnsvs.multistream)
set_device() (nnsvs.svs.SPSVS method)
setup() (in module nnsvs.train_util)
split_streams() (in module nnsvs.multistream)
SPSVS (class in nnsvs.svs)
StandardScaler (class in nnsvs.util)
svs() (nnsvs.svs.BaseSVS method)
(nnsvs.svs.NEUTRINO method)
(nnsvs.svs.SPSVS method)
T
TransformerEncoder (class in nnsvs.model)
V
variance_scaling() (in module nnsvs.postfilters)
VariancePredictor (class in nnsvs.model)