From 0cf5dfec2c8313fc2ed2aab8d10bf3dc4b9c283f Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期四, 14 三月 2024 14:41:49 +0800
Subject: [PATCH] update cmakelist
---
funasr/utils/load_utils.py | 14 ++++----------
1 files changed, 4 insertions(+), 10 deletions(-)
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.py
index b7d0200..84c38f9 100644
--- a/funasr/utils/load_utils.py
+++ b/funasr/utils/load_utils.py
@@ -31,14 +31,13 @@
return [load_audio_text_image_video(audio, fs=fs, audio_fs=audio_fs, data_type=data_type, **kwargs) for audio in data_or_path_or_list]
if isinstance(data_or_path_or_list, str) and data_or_path_or_list.startswith('http'): # download url to local file
data_or_path_or_list = download_from_url(data_or_path_or_list)
- pdb.set_trace()
+
if isinstance(data_or_path_or_list, str) and os.path.exists(data_or_path_or_list): # local file
if data_type is None or data_type == "sound":
data_or_path_or_list, audio_fs = torchaudio.load(data_or_path_or_list)
if kwargs.get("reduce_channels", True):
data_or_path_or_list = data_or_path_or_list.mean(0)
elif data_type == "text" and tokenizer is not None:
- pdb.set_trace()
data_or_path_or_list = tokenizer.encode(data_or_path_or_list)
elif data_type == "image": # undo
pass
@@ -56,8 +55,7 @@
elif isinstance(data_or_path_or_list, str) and data_type == "kaldi_ark":
data_mat = kaldiio.load_mat(data_or_path_or_list)
if isinstance(data_mat, tuple):
- sampling_rate, mat = data_mat
- assert sampling_rate == audio_fs
+ audio_fs, mat = data_mat
else:
mat = data_mat
if mat.dtype == 'int16' or mat.dtype == 'int32':
@@ -69,7 +67,7 @@
else:
pass
# print(f"unsupport data type: {data_or_path_or_list}, return raw data")
- pdb.set_trace()
+
if audio_fs != fs and data_type != "text":
resampler = torchaudio.transforms.Resample(audio_fs, fs)
data_or_path_or_list = resampler(data_or_path_or_list[None, :])[0, :]
@@ -91,8 +89,6 @@
return array
def extract_fbank(data, data_len = None, data_type: str="sound", frontend=None, **kwargs):
- # import pdb;
- # pdb.set_trace()
if isinstance(data, np.ndarray):
data = torch.from_numpy(data)
if len(data.shape) < 2:
@@ -110,9 +106,7 @@
data_list.append(data_i)
data_len.append(data_i.shape[0])
data = pad_sequence(data_list, batch_first=True) # data: [batch, N]
- # import pdb;
- # pdb.set_trace()
- # if data_type == "sound":
+
data, data_len = frontend(data, data_len, **kwargs)
if isinstance(data_len, (list, tuple)):
--
Gitblit v1.9.1