Open kellkwang opened 1 month ago
MonoCut.load_features(args=(MonoCut(id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0-904459_sp1.1', start=0.0, duration=6.0533125, channel=0, supervisions=[SupervisionSegment(id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1', recording_id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1', start=0.0, duration=6.0533125, channel=0, text='由市政府分管领导担任负责人', language='Chinese', speaker='KeSpeech_KeSpeech_000000352', gender=None, custom={'origin': 'aidatatang_200zh'}, alignment=None)], features=Features(type='kaldi-fbank', num_frames=605, num_features=80, frame_shift=0.01, sampling_rate=16000, start=0.0, duration=6.0533125, storage_type='lilcom_chunky', storage_path='data/fbank/kespeech_feats_train/feats-55.lca', storage_key='2370543709,43556,8961', recording_id='None', channels=0), recording=Recording(id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1', sources=[AudioSource(type='file', channels=[0], source='KeSpeech/KeSpeech_000000352/1011480_9a450cb0.wav')], sampling_rate=16000, num_samples=96853, duration=6.0533125, channel_ids=[0], transforms=[{'name': 'Speed', 'kwargs': {'factor': 1.1}}]), custom={'dataloading_info': {'rank': 6, 'world_size': 8, 'worker_id': None}}),) kwargs={})
Does it work when you run this statement in a separate python script?
Note you need to import related python packages
MonoCut
MonoCut.load_features(args=(MonoCut(id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0-904459_sp1.1', start=0.0, duration=6.0533125, channel=0, supervisions=[SupervisionSegment(id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1', recording_id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1', start=0.0, duration=6.0533125, channel=0, text='由市政府分管领导担任负责人', language='Chinese', speaker='KeSpeech_KeSpeech_000000352', gender=None, custom={'origin': 'aidatatang_200zh'}, alignment=None)], features=Features(type='kaldi-fbank', num_frames=605, num_features=80, frame_shift=0.01, sampling_rate=16000, start=0.0, duration=6.0533125, storage_type='lilcom_chunky', storage_path='data/fbank/kespeech_feats_train/feats-55.lca', storage_key='2370543709,43556,8961', recording_id='None', channels=0), recording=Recording(id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1', sources=[AudioSource(type='file', channels=[0], source='KeSpeech/KeSpeech_000000352/1011480_9a450cb0.wav')], sampling_rate=16000, num_samples=96853, duration=6.0533125, channel_ids=[0], transforms=[{'name': 'Speed', 'kwargs': {'factor': 1.1}}]), custom={'dataloading_info': {'rank': 6, 'world_size': 8, 'worker_id': None}}),) kwargs={})
Does it work when you run this statement in a separate python script?
Note you need to import related python packages
Running this directly, I get a SyntaxError: invalid syntax error even though I import
from lhotse.cut import MonoCut
Could you post a screenshot about how you run it?
By the way, it is a python statement.
Could you post a screenshot about how you run it?
By the way, it is a python statement.
Could you use
MonoCut.load_features(
MonoCut(
id="KeSpeech_KeSpeech_000000352_1011480_9a450cb0-904459_sp1.1",
start=0.0,
duration=6.0533125,
channel=0,
supervisions=[
SupervisionSegment(
id="KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1",
recording_id="KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1",
start=0.0,
duration=6.0533125,
channel=0,
text="由市政府分管领导担任负责人",
language="Chinese",
speaker="KeSpeech_KeSpeech_000000352",
gender=None,
custom={"origin": "aidatatang_200zh"},
alignment=None,
)
],
features=Features(
type="kaldi-fbank",
num_frames=605,
num_features=80,
frame_shift=0.01,
sampling_rate=16000,
start=0.0,
duration=6.0533125,
storage_type="lilcom_chunky",
storage_path="data/fbank/kespeech_feats_train/feats-55.lca",
storage_key="2370543709,43556,8961",
recording_id="None",
channels=0,
),
recording=Recording(
id="KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1",
sources=[
AudioSource(
type="file",
channels=[0],
source="KeSpeech/KeSpeech_000000352/1011480_9a450cb0.wav",
)
],
sampling_rate=16000,
num_samples=96853,
duration=6.0533125,
channel_ids=[0],
transforms=[{"name": "Speed", "kwargs": {"factor": 1.1}}],
),
custom={"dataloading_info": {"rank": 6, "world_size": 8, "worker_id": None}},
),
kwargs={},
)
Could you use
MonoCut.load_features( MonoCut( id="KeSpeech_KeSpeech_000000352_1011480_9a450cb0-904459_sp1.1", start=0.0, duration=6.0533125, channel=0, supervisions=[ SupervisionSegment( id="KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1", recording_id="KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1", start=0.0, duration=6.0533125, channel=0, text="由市政府分管领导担任负责人", language="Chinese", speaker="KeSpeech_KeSpeech_000000352", gender=None, custom={"origin": "aidatatang_200zh"}, alignment=None, ) ], features=Features( type="kaldi-fbank", num_frames=605, num_features=80, frame_shift=0.01, sampling_rate=16000, start=0.0, duration=6.0533125, storage_type="lilcom_chunky", storage_path="data/fbank/kespeech_feats_train/feats-55.lca", storage_key="2370543709,43556,8961", recording_id="None", channels=0, ), recording=Recording( id="KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1", sources=[ AudioSource( type="file", channels=[0], source="KeSpeech/KeSpeech_000000352/1011480_9a450cb0.wav", ) ], sampling_rate=16000, num_samples=96853, duration=6.0533125, channel_ids=[0], transforms=[{"name": "Speed", "kwargs": {"factor": 1.1}}], ), custom={"dataloading_info": {"rank": 6, "world_size": 8, "worker_id": None}}, ), kwargs={}, )
I deleted a line,
kwargs={},
Because it caused an execution error. TypeError: load_features() got an unexpected keyword argument 'kwargs'
from lhotse.cut import MonoCut from lhotse.supervision import SupervisionSegment from lhotse.features.base import Features from lhotse.audio import Recording, AudioSource
MonoCut.load_features( MonoCut( id="KeSpeech_KeSpeech_000000352_1011480_9a450cb0-904459_sp1.1", start=0.0, duration=6.0533125, channel=0, supervisions=[ SupervisionSegment( id="KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1",
channel_ids=[0],
transforms=[{"name": "Speed", "kwargs": {"factor": 1.1}}],
),
custom={"dataloading_info": {"rank": 6, "world_size": 8, "worker_id": None}},
),
kwargs={},
)
The execution result is as follows:
could you use lilcom to read the file
data/fbank/kespeech_feats_train/feats-55.lca
please refer to the API of lilcom for how to read it.
ValueError lilcom: Length of string was too short [extra info] When calling: MonoCut.load_features(args=(MonoCut(id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0-904459_sp1.1', start=0.0, duration=6.0533125, channel=0, supervisions=[SupervisionSegment(id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1', recording_id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1', start=0.0, duration=6.0533125, channel=0, text='由市政府分管领导担任负责人', language='Chinese', speaker='KeSpeech_KeSpeech_000000352', gender=None, custom={'origin': 'aidatatang_200zh'}, alignment=None)], features=Features(type='kaldi-fbank', num_frames=605, num_features=80, frame_shift=0.01, sampling_rate=16000, start=0.0, duration=6.0533125, storage_type='lilcom_chunky', storage_path='data/fbank/kespeech_feats_train/feats-55.lca', storage_key='2370543709,43556,8961', recording_id='None', channels=0), recording=Recording(id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1', sources=[AudioSource(type='file', channels=[0], source='KeSpeech/KeSpeech_000000352/1011480_9a450cb0.wav')], sampling_rate=16000, num_samples=96853, duration=6.0533125, channel_ids=[0], transforms=[{'name': 'Speed', 'kwargs': {'factor': 1.1}}]), custom={'dataloading_info': {'rank': 6, 'world_size': 8, 'worker_id': None}}),) kwargs={}) [extra info] When calling: MixedCut.load_features(args=(MixedCut(id='44b5ea5b-1e26-427a-9ee7-4721603c8386', tracks=[MixTrack(cut=MonoCut(id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0-904459_sp1.1', start=0.0, duration=6.0533125, channel=0, supervisions=[SupervisionSegment(id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1', recording_id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1', start=0.0, duration=6.0533125, channel=0, text='由市政府分管领导担任负责人', language='Chinese', speaker='KeSpeech_KeSpeech_000000352', gender=None, custom={'origin': 'aidatatang_200zh'}, alignment=None)], features=Features(type='kaldi-fbank', num_frames=605, num_features=80, frame_shift=0.01, sampling_rate=16000, start=0.0, duration=6.0533125, storage_type='lilcom_chunky', storage_path='data/fbank/kespeech_feats_train/feats-55.lca', storage_key='2370543709,43556,8961', recording_id='None', channels=0), recording=Recording(id='KeSpeech_KeSpeech_000000352_1011480_9a450cb0_sp1.1', sources=[AudioSource(type='file', channels=[0], source='KeSpeech/KeSpeech_000000352/1011480_9a450cb0.wav')], sampling_rate=16000, num_samples=96853, duration=6.0533125, channel_ids=[0], transforms=[{'name': 'Speed', 'kwargs': {'factor': 1.1}}]), custom={'dataloading_info': {'rank': 6, 'world_size': 8, 'worker_id': None}}), type='MonoCut', offset=0.0, snr=None), MixTrack(cut=PaddingCut(id='846e29d3-a509-43d1-a114-4d22d52d4be7', duration=0.1866875, sampling_rate=16000, feat_value=-23.025850929940457, num_frames=19, num_features=80, frame_shift=0.01, num_samples=2987, video=None, custom=None), type='PaddingCut', offset=6.0533125, snr=None)], transforms=None),) kwargs={})
I checked the data and there is nothing wrong with it. How to solve this error?