lt-tensor 0.0.1a3__py3-none-any.whl → 0.0.1a4__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- lt_tensor/datasets/audio.py +7 -8
- {lt_tensor-0.0.1a3.dist-info → lt_tensor-0.0.1a4.dist-info}/METADATA +1 -1
- {lt_tensor-0.0.1a3.dist-info → lt_tensor-0.0.1a4.dist-info}/RECORD +6 -6
- {lt_tensor-0.0.1a3.dist-info → lt_tensor-0.0.1a4.dist-info}/WHEEL +0 -0
- {lt_tensor-0.0.1a3.dist-info → lt_tensor-0.0.1a4.dist-info}/licenses/LICENSE +0 -0
- {lt_tensor-0.0.1a3.dist-info → lt_tensor-0.0.1a4.dist-info}/top_level.txt +0 -0
lt_tensor/datasets/audio.py
CHANGED
@@ -1,8 +1,7 @@
|
|
1
1
|
__all__ = ["AudioProcessor"]
|
2
2
|
from ..torch_commons import *
|
3
3
|
import torchaudio
|
4
|
-
from
|
5
|
-
from lt_utils.common import PathLike
|
4
|
+
from lt_utils.common import *
|
6
5
|
import librosa
|
7
6
|
from lt_utils.type_utils import is_file
|
8
7
|
from torchaudio.functional import resample
|
@@ -15,18 +14,18 @@ class AudioProcessor:
|
|
15
14
|
self,
|
16
15
|
sample_rate: int = 24000,
|
17
16
|
n_mels: int = 80,
|
18
|
-
n_fft: int =
|
19
|
-
win_length: int =
|
17
|
+
n_fft: int = 1024,
|
18
|
+
win_length: int = 1024,
|
20
19
|
hop_length: int = 256,
|
21
20
|
f_min: float = 0,
|
22
21
|
f_max: float | None = None,
|
23
|
-
mean: int = -4,
|
24
|
-
std: int = 4,
|
25
22
|
n_iter: int = 32,
|
26
23
|
center: bool = True,
|
27
|
-
mel_scale:
|
24
|
+
mel_scale: Literal["htk", "slaney"] = "htk",
|
28
25
|
inv_n_fft: int = 16,
|
29
26
|
inv_hop: int = 4,
|
27
|
+
std: int = 4,
|
28
|
+
mean: int = -4,
|
30
29
|
):
|
31
30
|
self.mean = mean
|
32
31
|
self.std = std
|
@@ -51,7 +50,7 @@ class AudioProcessor:
|
|
51
50
|
)
|
52
51
|
self.mel_rscale = torchaudio.transforms.InverseMelScale(
|
53
52
|
n_stft=self.n_stft,
|
54
|
-
|
53
|
+
n_mels=n_mels,
|
55
54
|
sample_rate=sample_rate,
|
56
55
|
f_min=f_min,
|
57
56
|
f_max=f_max,
|
@@ -7,7 +7,7 @@ lt_tensor/monotonic_align.py,sha256=LhBd8p1xdBzg6jQrQX1j7b4PNeYGwIqM24zcU-pHOLE,
|
|
7
7
|
lt_tensor/torch_commons.py,sha256=fntsEU8lhBQo0ebonI1iXBkMbWMN3HpBsG13EWlP5s8,718
|
8
8
|
lt_tensor/transform.py,sha256=IVAaQlq12OvMVhX3lX4lgsTCJYJce5n5MtMy7IK_AU4,8892
|
9
9
|
lt_tensor/datasets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
10
|
-
lt_tensor/datasets/audio.py,sha256=
|
10
|
+
lt_tensor/datasets/audio.py,sha256=BZTceP9MlmyrVioHpWLkd_ZcyawYYZUAlVWKfKwyWAg,3318
|
11
11
|
lt_tensor/model_zoo/__init__.py,sha256=jipEk50_DTMQbGg8FnDDukxmh7Bcwvl_QVRS3rkb7aY,283
|
12
12
|
lt_tensor/model_zoo/bsc.py,sha256=muxIR7dU-Pvf-HFE-iy3zmRb1sTJlcs1vqdlnbU1Hss,6307
|
13
13
|
lt_tensor/model_zoo/disc.py,sha256=ND6JR_x6b2Y1VqxZejalv8Cz5_TO3H_Z-0x6UnACbBM,4740
|
@@ -17,8 +17,8 @@ lt_tensor/model_zoo/istft.py,sha256=RV7KVY7q4CYzzsWXH4NGJQwSqrYWwHh-16Q62lKoA2k,
|
|
17
17
|
lt_tensor/model_zoo/pos.py,sha256=N28v-rF8CELouYxQ9r45Jbd4ri5DNydwDgg7nzmQ4Ig,4471
|
18
18
|
lt_tensor/model_zoo/rsd.py,sha256=5bba50g1Hm5kMexuJ4SwOIJuyQ1qJd8Acrq-Ax6CqE8,6958
|
19
19
|
lt_tensor/model_zoo/tfrms.py,sha256=kauh-A13pk08SZ5OspEE5a-gPKD4rZr6tqMKWu3KGhk,4237
|
20
|
-
lt_tensor-0.0.
|
21
|
-
lt_tensor-0.0.
|
22
|
-
lt_tensor-0.0.
|
23
|
-
lt_tensor-0.0.
|
24
|
-
lt_tensor-0.0.
|
20
|
+
lt_tensor-0.0.1a4.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
|
21
|
+
lt_tensor-0.0.1a4.dist-info/METADATA,sha256=sbT9xduzE-huVvSjnak9iCo1Eyp45bsMUarc16oTD3o,968
|
22
|
+
lt_tensor-0.0.1a4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
23
|
+
lt_tensor-0.0.1a4.dist-info/top_level.txt,sha256=35FuhFeXnUyvHWdbVHGPh0hS8euofafnJ_GJAVSF4Kk,10
|
24
|
+
lt_tensor-0.0.1a4.dist-info/RECORD,,
|
File without changes
|
File without changes
|
File without changes
|