lhotse
v0.4
Contents:
Getting started
Representing a corpus
Cuts
Feature extraction
Executing tasks in parallel
Augmentation
PyTorch Datasets
Kaldi Interoperability
Command-line interface
API Reference
lhotse
Docs
»
Index
Edit on GitHub
Index
_
|
A
|
C
|
D
|
E
|
F
|
G
|
H
|
I
|
L
|
M
|
N
|
O
|
P
|
R
|
S
|
T
|
U
|
V
|
W
_
__init__() (lhotse.audio.AudioMixer method)
(lhotse.audio.AudioSource method)
(lhotse.audio.Recording method)
(lhotse.audio.RecordingSet method)
(lhotse.cut.Cut method)
(lhotse.cut.CutSet method)
(lhotse.cut.MixedCut method)
(lhotse.cut.MixTrack method)
(lhotse.cut.PaddingCut method)
(lhotse.features.base.FeatureExtractor method)
(lhotse.features.base.Features method)
(lhotse.features.base.FeatureSet method)
(lhotse.features.base.FeatureSetBuilder method)
(lhotse.features.fbank.FbankConfig method)
(lhotse.features.io.LilcomFilesReader method)
(lhotse.features.io.LilcomFilesWriter method)
(lhotse.features.io.LilcomHdf5Reader method)
(lhotse.features.io.LilcomHdf5Writer method)
(lhotse.features.io.NumpyFilesReader method)
(lhotse.features.io.NumpyFilesWriter method)
(lhotse.features.io.NumpyHdf5Reader method)
(lhotse.features.io.NumpyHdf5Writer method)
(lhotse.features.mfcc.MfccConfig method)
(lhotse.features.mixer.FeatureMixer method)
(lhotse.features.spectrogram.SpectrogramConfig method)
(lhotse.supervision.SupervisionSegment method)
(lhotse.supervision.SupervisionSet method)
A
add_to_mix() (lhotse.audio.AudioMixer method)
(lhotse.features.mixer.FeatureMixer method)
append() (in module lhotse.cut)
(lhotse.cut.CutUtilsMixin method)
append_cuts() (in module lhotse.cut)
audio_energy() (in module lhotse.audio)
AudioMixer (class in lhotse.audio)
AudioSource (class in lhotse.audio)
available_storage_backends() (in module lhotse.features.io)
C
cepstral_lifter (lhotse.features.mfcc.MfccConfig attribute)
channel (lhotse.cut.Cut attribute)
(lhotse.supervision.SupervisionSegment attribute)
channel_ids() (lhotse.audio.Recording property)
channels (lhotse.audio.AudioSource attribute)
(lhotse.features.base.Features attribute)
close() (lhotse.features.io.LilcomHdf5Writer method)
(lhotse.features.io.NumpyHdf5Writer method)
close_cached_file_handles() (in module lhotse.features.io)
combine() (in module lhotse.manipulation)
compute_and_store_features() (in module lhotse.cut.CutSet)
(lhotse.cut.Cut method)
(lhotse.cut.CutSet method)
(lhotse.cut.MixedCut method)
(lhotse.cut.PaddingCut method)
compute_energy() (lhotse.features.base.FeatureExtractor static method)
(lhotse.features.fbank.Fbank static method)
(lhotse.features.spectrogram.Spectrogram static method)
compute_features() (lhotse.cut.CutUtilsMixin method)
compute_global_feature_stats() (lhotse.cut.CutSet method)
compute_global_stats() (in module lhotse.features.base)
(lhotse.features.base.FeatureSet method)
config_type (lhotse.features.base.FeatureExtractor attribute)
(lhotse.features.fbank.Fbank attribute)
(lhotse.features.mfcc.Mfcc attribute)
(lhotse.features.spectrogram.Spectrogram attribute)
create_default_feature_extractor() (in module lhotse.features.base)
custom (lhotse.supervision.SupervisionSegment attribute)
Cut (class in lhotse.cut)
cut (lhotse.cut.MixTrack attribute)
cut_into_windows() (lhotse.cut.CutSet method)
cuts (lhotse.cut.CutSet attribute)
CutSet (class in lhotse.cut)
CutUtilsMixin (class in lhotse.cut)
D
describe() (lhotse.cut.CutSet method)
dither (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
(lhotse.features.spectrogram.SpectrogramConfig attribute)
duration (lhotse.audio.Recording attribute)
(lhotse.cut.Cut attribute)
(lhotse.cut.PaddingCut attribute)
(lhotse.features.base.Features attribute)
(lhotse.supervision.SupervisionSegment attribute)
duration() (lhotse.audio.RecordingSet method)
(lhotse.cut.MixedCut property)
E
end() (lhotse.cut.Cut property)
(lhotse.cut.MixedCut property)
(lhotse.cut.PaddingCut property)
(lhotse.features.base.Features property)
(lhotse.supervision.SupervisionSegment property)
energy_floor (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
(lhotse.features.spectrogram.SpectrogramConfig attribute)
export_to_kaldi() (in module lhotse.kaldi)
extract() (lhotse.features.base.FeatureExtractor method)
(lhotse.features.base.TorchaudioFeatureExtractor method)
extract_from_recording_and_store() (lhotse.features.base.FeatureExtractor method)
extract_from_samples_and_store() (lhotse.features.base.FeatureExtractor method)
F
Fbank (class in lhotse.features.fbank)
FbankConfig (class in lhotse.features.fbank)
feature_dim() (lhotse.features.base.FeatureExtractor method)
(lhotse.features.fbank.Fbank method)
(lhotse.features.mfcc.Mfcc method)
(lhotse.features.spectrogram.Spectrogram method)
feature_fn (lhotse.features.base.TorchaudioFeatureExtractor attribute)
FeatureExtractor (class in lhotse.features.base)
FeatureMixer (class in lhotse.features.mixer)
Features (class in lhotse.features.base)
features (lhotse.cut.Cut attribute)
(lhotse.features.base.FeatureSet attribute)
features_type() (lhotse.cut.Cut property)
(lhotse.cut.MixedCut property)
FeatureSet (class in lhotse.features.base)
FeatureSetBuilder (class in lhotse.features.base)
FeaturesReader (class in lhotse.features.io)
FeaturesWriter (class in lhotse.features.io)
filter() (lhotse.audio.RecordingSet method)
(lhotse.cut.CutSet method)
(lhotse.supervision.SupervisionSet method)
filter_supervisions() (lhotse.cut.Cut method)
(lhotse.cut.CutSet method)
(lhotse.cut.MixedCut method)
(lhotse.cut.PaddingCut method)
find() (lhotse.features.base.FeatureSet method)
(lhotse.supervision.SupervisionSet method)
frame_length (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
(lhotse.features.spectrogram.SpectrogramConfig attribute)
frame_shift (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
(lhotse.features.spectrogram.SpectrogramConfig attribute)
frame_shift() (lhotse.cut.Cut property)
(lhotse.cut.MixedCut property)
(lhotse.cut.PaddingCut property)
(lhotse.features.base.FeatureExtractor property)
(lhotse.features.base.Features property)
(lhotse.features.base.TorchaudioFeatureExtractor property)
from_cuts() (lhotse.cut.CutSet static method)
from_dict() (lhotse.audio.AudioSource static method)
(lhotse.audio.Recording static method)
(lhotse.cut.Cut static method)
(lhotse.cut.MixedCut static method)
(lhotse.cut.MixTrack static method)
(lhotse.cut.PaddingCut static method)
(lhotse.features.base.FeatureExtractor class method)
(lhotse.features.base.Features static method)
(lhotse.supervision.SupervisionSegment static method)
from_dicts() (lhotse.audio.RecordingSet static method)
(lhotse.cut.CutSet static method)
(lhotse.features.base.FeatureSet static method)
(lhotse.supervision.SupervisionSet static method)
from_features() (lhotse.features.base.FeatureSet static method)
from_file() (lhotse.audio.Recording static method)
from_manifests() (lhotse.cut.CutSet static method)
from_recordings() (lhotse.audio.RecordingSet static method)
from_segments() (lhotse.supervision.SupervisionSet static method)
from_sphere() (lhotse.audio.Recording static method)
from_wav() (lhotse.audio.Recording static method)
from_yaml() (lhotse.features.base.FeatureExtractor class method)
G
gender (lhotse.supervision.SupervisionSegment attribute)
get_extractor_type() (in module lhotse.features.base)
get_reader() (in module lhotse.features.io)
get_writer() (in module lhotse.features.io)
H
has_features() (lhotse.cut.Cut property)
(lhotse.cut.MixedCut property)
(lhotse.cut.PaddingCut property)
has_recording() (lhotse.cut.Cut property)
(lhotse.cut.MixedCut property)
(lhotse.cut.PaddingCut property)
high_freq (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
I
id (lhotse.audio.Recording attribute)
(lhotse.cut.Cut attribute)
(lhotse.cut.MixedCut attribute)
(lhotse.cut.PaddingCut attribute)
(lhotse.supervision.SupervisionSegment attribute)
ids() (lhotse.cut.CutSet property)
index_supervisions() (lhotse.cut.CutSet method)
L
language (lhotse.supervision.SupervisionSegment attribute)
lhotse.audio
module
lhotse.augmentation
module
lhotse.cut
module
lhotse.features.base
module
lhotse.features.fbank
module
lhotse.features.io
module
lhotse.features.mfcc
module
lhotse.features.mixer
module
lhotse.features.spectrogram
module
lhotse.kaldi
module
lhotse.manipulation
module
lhotse.supervision
module
LilcomFilesReader (class in lhotse.features.io)
LilcomFilesWriter (class in lhotse.features.io)
LilcomHdf5Reader (class in lhotse.features.io)
LilcomHdf5Writer (class in lhotse.features.io)
load() (lhotse.features.base.Features method)
(lhotse.features.base.FeatureSet method)
load_audio() (lhotse.audio.AudioSource method)
(lhotse.audio.Recording method)
(lhotse.audio.RecordingSet method)
(lhotse.cut.Cut method)
(lhotse.cut.MixedCut method)
(lhotse.cut.PaddingCut method)
load_features() (lhotse.cut.Cut method)
(lhotse.cut.MixedCut method)
(lhotse.cut.PaddingCut method)
load_kaldi_data_dir() (in module lhotse.kaldi)
load_kaldi_text_mapping() (in module lhotse.kaldi)
load_manifest() (in module lhotse.manipulation)
lookup_cache_or_open() (in module lhotse.features.io)
low_freq (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
M
make_windowed_cuts_from_features() (in module lhotse.cut)
map() (lhotse.cut.CutSet method)
(lhotse.supervision.SupervisionSegment method)
(lhotse.supervision.SupervisionSet method)
map_supervisions() (lhotse.cut.Cut method)
(lhotse.cut.CutSet method)
(lhotse.cut.MixedCut method)
(lhotse.cut.PaddingCut method)
Mfcc (class in lhotse.features.mfcc)
MfccConfig (class in lhotse.features.mfcc)
min_duration (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
(lhotse.features.spectrogram.SpectrogramConfig attribute)
mix() (in module lhotse.cut)
(lhotse.cut.CutSet method)
(lhotse.cut.CutUtilsMixin method)
(lhotse.features.base.FeatureExtractor static method)
(lhotse.features.fbank.Fbank static method)
(lhotse.features.spectrogram.Spectrogram static method)
mix_cuts() (in module lhotse.cut)
mix_same_recording_channels() (lhotse.cut.CutSet method)
mixed_audio() (lhotse.audio.AudioMixer property)
mixed_cuts() (lhotse.cut.CutSet property)
mixed_feats() (lhotse.features.mixer.FeatureMixer property)
MixedCut (class in lhotse.cut)
MixTrack (class in lhotse.cut)
modify_ids() (lhotse.cut.CutSet method)
module
lhotse.audio
lhotse.augmentation
lhotse.cut
lhotse.features.base
lhotse.features.fbank
lhotse.features.io
lhotse.features.mfcc
lhotse.features.mixer
lhotse.features.spectrogram
lhotse.kaldi
lhotse.manipulation
lhotse.supervision
N
name (lhotse.features.base.FeatureExtractor attribute)
(lhotse.features.fbank.Fbank attribute)
(lhotse.features.io.LilcomFilesReader attribute)
(lhotse.features.io.LilcomFilesWriter attribute)
(lhotse.features.io.LilcomHdf5Reader attribute)
(lhotse.features.io.LilcomHdf5Writer attribute)
(lhotse.features.io.NumpyFilesReader attribute)
(lhotse.features.io.NumpyFilesWriter attribute)
(lhotse.features.io.NumpyHdf5Reader attribute)
(lhotse.features.io.NumpyHdf5Writer attribute)
(lhotse.features.mfcc.Mfcc attribute)
(lhotse.features.spectrogram.Spectrogram attribute)
name() (lhotse.features.io.FeaturesReader property)
(lhotse.features.io.FeaturesWriter property)
NonPositiveEnergyError
num_ceps (lhotse.features.mfcc.MfccConfig attribute)
num_channels() (lhotse.audio.Recording property)
(lhotse.audio.RecordingSet method)
num_features (lhotse.cut.PaddingCut attribute)
(lhotse.features.base.Features attribute)
num_features() (lhotse.cut.Cut property)
(lhotse.cut.MixedCut property)
(lhotse.features.mixer.FeatureMixer property)
num_frames (lhotse.cut.PaddingCut attribute)
(lhotse.features.base.Features attribute)
num_frames() (lhotse.cut.Cut property)
(lhotse.cut.MixedCut property)
num_mel_bins (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
num_samples (lhotse.audio.Recording attribute)
(lhotse.cut.PaddingCut attribute)
num_samples() (lhotse.audio.RecordingSet method)
(lhotse.cut.Cut property)
(lhotse.cut.MixedCut property)
NumpyFilesReader (class in lhotse.features.io)
NumpyFilesWriter (class in lhotse.features.io)
NumpyHdf5Reader (class in lhotse.features.io)
NumpyHdf5Writer (class in lhotse.features.io)
O
offset (lhotse.cut.MixTrack attribute)
P
pad() (lhotse.cut.Cut method)
(lhotse.cut.CutSet method)
(lhotse.cut.MixedCut method)
(lhotse.cut.PaddingCut method)
PaddingCut (class in lhotse.cut)
perturb_speed() (lhotse.audio.Recording method)
(lhotse.cut.Cut method)
(lhotse.cut.CutSet method)
(lhotse.cut.MixedCut method)
(lhotse.cut.PaddingCut method)
(lhotse.supervision.SupervisionSegment method)
play_audio() (lhotse.cut.CutUtilsMixin method)
plot_audio() (lhotse.cut.CutUtilsMixin method)
plot_features() (lhotse.cut.CutUtilsMixin method)
plot_tracks_audio() (lhotse.cut.MixedCut method)
plot_tracks_features() (lhotse.cut.MixedCut method)
preemphasis_coefficient (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
(lhotse.features.spectrogram.SpectrogramConfig attribute)
process_and_store_recordings() (lhotse.features.base.FeatureSetBuilder method)
R
raw_energy (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
(lhotse.features.spectrogram.SpectrogramConfig attribute)
read() (lhotse.features.io.FeaturesReader method)
(lhotse.features.io.LilcomFilesReader method)
(lhotse.features.io.LilcomHdf5Reader method)
(lhotse.features.io.NumpyFilesReader method)
(lhotse.features.io.NumpyHdf5Reader method)
read_audio() (in module lhotse.audio)
Recording (class in lhotse.audio)
recording (lhotse.cut.Cut attribute)
recording_id (lhotse.features.base.Features attribute)
(lhotse.supervision.SupervisionSegment attribute)
recording_id() (lhotse.cut.Cut property)
recordings (lhotse.audio.RecordingSet attribute)
RecordingSet (class in lhotse.audio)
register_extractor() (in module lhotse.features.base)
register_reader() (in module lhotse.features.io)
register_writer() (in module lhotse.features.io)
remove_dc_offset (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
(lhotse.features.spectrogram.SpectrogramConfig attribute)
round_to_power_of_two (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
(lhotse.features.spectrogram.SpectrogramConfig attribute)
S
sample() (lhotse.cut.CutSet method)
sampling_rate (lhotse.audio.Recording attribute)
(lhotse.cut.PaddingCut attribute)
(lhotse.features.base.Features attribute)
sampling_rate() (lhotse.audio.RecordingSet method)
(lhotse.cut.Cut property)
(lhotse.cut.MixedCut property)
save_kaldi_text_mapping() (in module lhotse.kaldi)
segments (lhotse.supervision.SupervisionSet attribute)
simple_cuts() (lhotse.cut.CutSet property)
snr (lhotse.cut.MixTrack attribute)
sort_by_duration() (lhotse.cut.CutSet method)
source (lhotse.audio.AudioSource attribute)
sources (lhotse.audio.Recording attribute)
speaker (lhotse.supervision.SupervisionSegment attribute)
speakers() (lhotse.cut.CutSet property)
speakers_audio_mask() (lhotse.cut.CutUtilsMixin method)
speakers_feature_mask() (lhotse.cut.CutUtilsMixin method)
Spectrogram (class in lhotse.features.spectrogram)
SpectrogramConfig (class in lhotse.features.spectrogram)
split() (lhotse.audio.RecordingSet method)
(lhotse.cut.CutSet method)
(lhotse.features.base.FeatureSet method)
(lhotse.supervision.SupervisionSet method)
start (lhotse.cut.Cut attribute)
(lhotse.features.base.Features attribute)
(lhotse.supervision.SupervisionSegment attribute)
start() (lhotse.cut.MixedCut property)
(lhotse.cut.PaddingCut property)
storage_key (lhotse.features.base.Features attribute)
storage_path (lhotse.features.base.Features attribute)
storage_path() (lhotse.features.io.FeaturesWriter property)
(lhotse.features.io.LilcomFilesWriter property)
(lhotse.features.io.LilcomHdf5Writer property)
(lhotse.features.io.NumpyFilesWriter property)
(lhotse.features.io.NumpyHdf5Writer property)
storage_type (lhotse.features.base.Features attribute)
store_feature_array() (in module lhotse.features.base)
subset() (lhotse.cut.CutSet method)
supervisions (lhotse.cut.Cut attribute)
supervisions() (lhotse.cut.MixedCut property)
(lhotse.cut.PaddingCut property)
supervisions_audio_mask() (lhotse.cut.CutUtilsMixin method)
supervisions_feature_mask() (lhotse.cut.CutUtilsMixin method)
SupervisionSegment (class in lhotse.supervision)
SupervisionSet (class in lhotse.supervision)
T
text (lhotse.supervision.SupervisionSegment attribute)
to_dicts() (lhotse.audio.RecordingSet method)
(lhotse.cut.CutSet method)
(lhotse.features.base.FeatureSet method)
(lhotse.supervision.SupervisionSet method)
to_manifest() (in module lhotse.manipulation)
to_yaml() (lhotse.features.base.FeatureExtractor method)
TorchaudioFeatureExtractor (class in lhotse.features.base)
tracks (lhotse.cut.MixedCut attribute)
transform_text() (lhotse.cut.CutSet method)
(lhotse.supervision.SupervisionSegment method)
(lhotse.supervision.SupervisionSet method)
transforms (lhotse.audio.Recording attribute)
trim() (lhotse.supervision.SupervisionSegment method)
trim_to_supervisions() (lhotse.cut.CutSet method)
trim_to_unsupervised_segments() (lhotse.cut.CutSet method)
trimmed_supervisions() (lhotse.cut.CutUtilsMixin property)
truncate() (lhotse.cut.Cut method)
(lhotse.cut.CutSet method)
(lhotse.cut.MixedCut method)
(lhotse.cut.PaddingCut method)
type (lhotse.audio.AudioSource attribute)
(lhotse.features.base.Features attribute)
U
unmixed_audio() (lhotse.audio.AudioMixer property)
unmixed_feats() (lhotse.features.mixer.FeatureMixer property)
use_energy (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
use_log_energy (lhotse.cut.PaddingCut attribute)
V
vtln_high (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
vtln_low (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
vtln_warp (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
W
window_type (lhotse.features.fbank.FbankConfig attribute)
(lhotse.features.mfcc.MfccConfig attribute)
(lhotse.features.spectrogram.SpectrogramConfig attribute)
with_features_path_prefix() (lhotse.cut.Cut method)
(lhotse.cut.CutSet method)
(lhotse.cut.MixedCut method)
(lhotse.cut.PaddingCut method)
with_id() (lhotse.cut.CutUtilsMixin method)
with_offset() (lhotse.supervision.SupervisionSegment method)
with_path_prefix() (lhotse.audio.AudioSource method)
(lhotse.audio.Recording method)
(lhotse.audio.RecordingSet method)
(lhotse.features.base.Features method)
(lhotse.features.base.FeatureSet method)
with_recording_path_prefix() (lhotse.cut.Cut method)
(lhotse.cut.CutSet method)
(lhotse.cut.MixedCut method)
(lhotse.cut.PaddingCut method)
write() (lhotse.features.io.FeaturesWriter method)
(lhotse.features.io.LilcomFilesWriter method)
(lhotse.features.io.LilcomHdf5Writer method)
(lhotse.features.io.NumpyFilesWriter method)
(lhotse.features.io.NumpyHdf5Writer method)
Read the Docs
v: v0.4
Versions
latest
stable
v1.1
v0.4_e
v0.4_g
v0.4_c
v0.3_ba
v0.3_y
v0.3_w
v0.3_u
v0.3_s
v0.3_q
v0.3_o
v0.3_k
v0.3_m
v0.3_c
v0.3_i
v0.3_g
v0.2_i
v0.2_e
v0.2_c
v0.2_s
v0.2_g
v0.2_o
v0.2_q
v0.2_m
v0.2_k
v0.1_l
v0.1
v0.1_j
v0.1_t
v0.1_v
v0.1_b
v0.1_d
v0.1_p
v0.1_f
v0.1_h
v0.1_n
v0.1_r
Downloads
On Read the Docs
Project Home
Builds
Free document hosting provided by
Read the Docs
.