File size: 2,909 Bytes
0b32ad6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 |
from .base import SequentialDataPipe
from .common_pipes import (
EncodeCategory,
EncodeMultiLabel,
EncodeMultipleCategory,
LoadAudio,
SetOutputKeys,
)
class UtteranceClassificationPipe(SequentialDataPipe):
"""
each item in the input dataset should have:
wav_path: str
label: str
"""
def __init__(
self,
output_keys: dict = None,
audio_sample_rate: int = 16000,
audio_channel_reduction: str = "first",
sox_effects: list = None,
train_category_encoder: bool = False,
):
output_keys = output_keys or dict(
x="wav",
x_len="wav_len",
class_id="class_id",
label="label",
unique_name="id",
)
super().__init__(
LoadAudio(
audio_sample_rate=audio_sample_rate,
audio_channel_reduction=audio_channel_reduction,
sox_effects=sox_effects,
),
EncodeCategory(train_category_encoder=train_category_encoder),
SetOutputKeys(output_keys=output_keys),
)
class UtteranceMultipleCategoryClassificationPipe(SequentialDataPipe):
"""
each item in the input dataset should have:
wav_path: str
labels: List[str]
"""
def __init__(
self,
output_keys: dict = None,
audio_sample_rate: int = 16000,
audio_channel_reduction: str = "first",
sox_effects: list = None,
train_category_encoder: bool = False,
):
output_keys = output_keys or dict(
x="wav",
x_len="wav_len",
class_ids="class_ids",
labels="labels",
unique_name="id",
)
super().__init__(
LoadAudio(
audio_sample_rate=audio_sample_rate,
audio_channel_reduction=audio_channel_reduction,
sox_effects=sox_effects,
),
EncodeMultipleCategory(train_category_encoder=train_category_encoder),
SetOutputKeys(output_keys=output_keys),
)
class HearScenePipe(SequentialDataPipe):
"""
each item in the input dataset should have:
wav_path: str
labels: List[str]
"""
def __init__(
self,
output_keys: dict = None,
audio_sample_rate: int = 16000,
audio_channel_reduction: str = "first",
):
output_keys = output_keys or dict(
x="wav",
x_len="wav_len",
y="binary_labels",
labels="labels",
unique_name="id",
)
super().__init__(
LoadAudio(
audio_sample_rate=audio_sample_rate,
audio_channel_reduction=audio_channel_reduction,
),
EncodeMultiLabel(),
SetOutputKeys(output_keys=output_keys),
)
|