From 3d9f094e9652d4b84894c6fd4eae39a4a753b0f0 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 16 五月 2023 23:48:00 +0800
Subject: [PATCH] train

---
 funasr/datasets/iterable_dataset.py |   33 ++++++++++++++++-----------------
 1 files changed, 16 insertions(+), 17 deletions(-)

diff --git a/funasr/datasets/iterable_dataset.py b/funasr/datasets/iterable_dataset.py
index 4436618..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
@@ -129,7 +130,7 @@
         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]
@@ -227,13 +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"):
@@ -244,10 +241,14 @@
                         array = torchaudio.transforms.Resample(orig_freq=audio_fs,
                                                                new_freq=model_fs)(array)
                         array = array.numpy()
-                if self.mc:
-                    data[name] = array.transpose(0, 1)
+                        
+                if _type == "sound":
+                    if self.mc:
+                        data[name] = array.transpose((1, 0))
+                    else:
+                        data[name] = array[0]
                 else:
-                    data[name] = array[0]
+                    data[name] = array
 
                 if self.preprocess is not None:
                     data = self.preprocess(uid, data)
@@ -331,11 +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
@@ -350,7 +348,7 @@
                             array = array.numpy()
                     if _type == "sound":
                         if self.mc:
-                            data[name] = array.transpose(0, 1)
+                            data[name] = array.transpose((1, 0))
                         else:
                             data[name] = array[0]
                     else:
@@ -387,3 +385,4 @@
 
         if count == 0:
             raise RuntimeError("No iteration")
+

--
Gitblit v1.9.1