From 33d3d2084403fd34b79c835d2f2fe04f6cd8f738 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 13 九月 2023 09:33:54 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add
---
funasr/datasets/small_datasets/dataset.py | 36 +++++++++++++++++++++++++-----------
1 files changed, 25 insertions(+), 11 deletions(-)
diff --git a/funasr/datasets/small_datasets/dataset.py b/funasr/datasets/small_datasets/dataset.py
index 6ba8a02..bee9f50 100644
--- a/funasr/datasets/small_datasets/dataset.py
+++ b/funasr/datasets/small_datasets/dataset.py
@@ -9,15 +9,12 @@
from typing import Collection
from typing import Dict
from typing import Mapping
-from typing import Tuple
-from typing import Union
+from typing import Union, List, Tuple
import kaldiio
import numpy as np
import torch
from torch.utils.data.dataset import Dataset
-from typeguard import check_argument_types
-from typeguard import check_return_type
from funasr.fileio.npy_scp import NpyScpReader
from funasr.fileio.sound_scp import SoundScpReader
@@ -25,7 +22,6 @@
class AdapterForSoundScpReader(collections.abc.Mapping):
def __init__(self, loader, dtype=None):
- assert check_argument_types()
self.loader = loader
self.dtype = dtype
self.rate = None
@@ -110,8 +106,9 @@
float_dtype: str = "float32",
int_dtype: str = "long",
dest_sample_rate: int = 16000,
+ speed_perturb: Union[list, tuple] = None,
+ mode: str = "train",
):
- assert check_argument_types()
if len(path_name_type_list) == 0:
raise ValueError(
'1 or more elements are required for "path_name_type_list"'
@@ -123,6 +120,10 @@
self.float_dtype = float_dtype
self.int_dtype = int_dtype
self.dest_sample_rate = dest_sample_rate
+ self.speed_perturb = speed_perturb
+ self.mode = mode
+ if self.speed_perturb is not None:
+ logging.info("Using speed_perturb: {}".format(speed_perturb))
self.loader_dict = {}
self.debug_info = {}
@@ -138,7 +139,7 @@
def _build_loader(
self, path: str, loader_type: str
- ) -> Mapping[str, Union[np.ndarray, torch.Tensor, str, numbers.Number]]:
+ ) -> Mapping[str, Union[np.ndarray, torch.Tensor, str, List[int], numbers.Number]]:
"""Helper function to instantiate Loader.
Args:
@@ -146,13 +147,15 @@
loader_type: loader_type. sound, npy, text, etc
"""
if loader_type == "sound":
- loader = SoundScpReader(path, self.dest_sample_rate, normalize=True, always_2d=False)
+ speed_perturb = self.speed_perturb if self.mode == "train" else None
+ loader = SoundScpReader(path, self.dest_sample_rate, normalize=True, always_2d=False,
+ speed_perturb=speed_perturb)
return AdapterForSoundScpReader(loader, self.float_dtype)
elif loader_type == "kaldi_ark":
loader = kaldiio.load_scp(path)
return AdapterForSoundScpReader(loader, self.float_dtype)
elif loader_type == "npy":
- return NpyScpReader()
+ return NpyScpReader(path)
elif loader_type == "text":
text_loader = {}
with open(path, "r", encoding="utf-8") as f:
@@ -166,6 +169,19 @@
raise RuntimeError(f"{k} is duplicated ({path}:{linenum})")
text_loader[k] = v
return text_loader
+ elif loader_type == "text_int":
+ text_int_loader = {}
+ with open(path, "r", encoding="utf-8") as f:
+ for linenum, line in enumerate(f, 1):
+ sps = line.rstrip().split(maxsplit=1)
+ if len(sps) == 1:
+ k, v = sps[0], ""
+ else:
+ k, v = sps
+ if k in text_int_loader:
+ raise RuntimeError(f"{k} is duplicated ({path}:{linenum})")
+ text_int_loader[k] = [int(i) for i in v.split()]
+ return text_int_loader
else:
raise RuntimeError(f"Not supported: loader_type={loader_type}")
@@ -187,7 +203,6 @@
return _mes
def __getitem__(self, uid: Union[str, int]) -> Tuple[str, Dict[str, np.ndarray]]:
- assert check_argument_types()
# Change integer-id to string-id
if isinstance(uid, int):
@@ -245,5 +260,4 @@
data[name] = value
retval = uid, data
- assert check_return_type(retval)
return retval
--
Gitblit v1.9.1