From 3cd3473bf7a3b41484baa86d9092248d78e7af39 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 21 四月 2023 17:17:37 +0800
Subject: [PATCH] docs
---
funasr/datasets/iterable_dataset.py | 49 +++++++++++++++++++++++++++++--------------------
1 files changed, 29 insertions(+), 20 deletions(-)
diff --git a/funasr/datasets/iterable_dataset.py b/funasr/datasets/iterable_dataset.py
index 2001df9..4b2fb1a 100644
--- a/funasr/datasets/iterable_dataset.py
+++ b/funasr/datasets/iterable_dataset.py
@@ -8,6 +8,7 @@
from typing import Iterator
from typing import Tuple
from typing import Union
+from typing import List
import kaldiio
import numpy as np
@@ -66,7 +67,7 @@
return load_bytes(bytes)
DATA_TYPES = {
- "sound": lambda x: torchaudio.load(x)[0][0].numpy(),
+ "sound": lambda x: torchaudio.load(x)[0].numpy(),
"pcm": load_pcm,
"kaldi_ark": load_kaldi,
"bytes": load_bytes,
@@ -106,6 +107,7 @@
] = None,
float_dtype: str = "float32",
fs: dict = None,
+ mc: bool = False,
int_dtype: str = "long",
key_file: str = None,
):
@@ -122,12 +124,13 @@
self.int_dtype = int_dtype
self.key_file = key_file
self.fs = fs
+ self.mc = mc
self.debug_info = {}
non_iterable_list = []
self.path_name_type_list = []
- if not isinstance(path_name_type_list[0], Tuple):
+ if not isinstance(path_name_type_list[0], (Tuple, List)):
path = path_name_type_list[0]
name = path_name_type_list[1]
_type = path_name_type_list[2]
@@ -192,6 +195,7 @@
array = torchaudio.transforms.Resample(orig_freq=audio_fs,
new_freq=model_fs)(array)
array = array.squeeze(0).numpy()
+
data[name] = array
if self.preprocess is not None:
@@ -224,13 +228,9 @@
name = self.path_name_type_list[i][1]
_type = self.path_name_type_list[i][2]
if _type == "sound":
- audio_type = os.path.basename(value).split(".")[1].lower()
- if audio_type not in SUPPORT_AUDIO_TYPE_SETS:
- raise NotImplementedError(
- f'Not supported audio type: {audio_type}')
- if audio_type == "pcm":
- _type = "pcm"
-
+ audio_type = os.path.basename(value).lower()
+ if audio_type.rfind(".pcm") >= 0:
+ _type = "pcm"
func = DATA_TYPES[_type]
array = func(value)
if self.fs is not None and (name == "speech" or name == "ref_speech"):
@@ -238,11 +238,17 @@
model_fs = self.fs["model_fs"]
if audio_fs is not None and model_fs is not None:
array = torch.from_numpy(array)
- array = array.unsqueeze(0)
array = torchaudio.transforms.Resample(orig_freq=audio_fs,
new_freq=model_fs)(array)
- array = array.squeeze(0).numpy()
- data[name] = array
+ array = array.numpy()
+
+ if _type == "sound":
+ if self.mc:
+ data[name] = array.transpose((1, 0))
+ else:
+ data[name] = array[0]
+ else:
+ data[name] = array
if self.preprocess is not None:
data = self.preprocess(uid, data)
@@ -326,11 +332,8 @@
# 2.a. Load data streamingly
for value, (path, name, _type) in zip(values, self.path_name_type_list):
if _type == "sound":
- audio_type = os.path.basename(value).split(".")[1].lower()
- if audio_type not in SUPPORT_AUDIO_TYPE_SETS:
- raise NotImplementedError(
- f'Not supported audio type: {audio_type}')
- if audio_type == "pcm":
+ audio_type = os.path.basename(value).lower()
+ if audio_type.rfind(".pcm") >= 0:
_type = "pcm"
func = DATA_TYPES[_type]
# Load entry
@@ -340,11 +343,16 @@
model_fs = self.fs["model_fs"]
if audio_fs is not None and model_fs is not None:
array = torch.from_numpy(array)
- array = array.unsqueeze(0)
array = torchaudio.transforms.Resample(orig_freq=audio_fs,
new_freq=model_fs)(array)
- array = array.squeeze(0).numpy()
- data[name] = array
+ array = array.numpy()
+ if _type == "sound":
+ if self.mc:
+ data[name] = array.transpose((1, 0))
+ else:
+ data[name] = array[0]
+ else:
+ data[name] = array
if self.non_iterable_dataset is not None:
# 2.b. Load data from non-iterable dataset
_, from_non_iterable = self.non_iterable_dataset[uid]
@@ -377,3 +385,4 @@
if count == 0:
raise RuntimeError("No iteration")
+
--
Gitblit v1.9.1