From 6e69d784e4814c3dbe35e8f70c6cf4b920c8b20b Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 19 三月 2025 23:10:13 +0800
Subject: [PATCH] 1. bug fix:list(mean)和list(var)，由于mean和var是numpy，导致写入到文件的格式错误，参考上面的话，大概率是list(mean.tolist())，其实外层list没有必要 (#2437)
---
funasr/utils/load_utils.py | 27 +++++++++++++++++++++------
1 files changed, 21 insertions(+), 6 deletions(-)
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.py
index aabf5d9..072b578 100644
--- a/funasr/utils/load_utils.py
+++ b/funasr/utils/load_utils.py
@@ -10,7 +10,6 @@
import time
import logging
from torch.nn.utils.rnn import pad_sequence
-from pydub import AudioSegment
try:
from funasr.download.file import download_from_url
@@ -19,6 +18,11 @@
import pdb
import subprocess
from subprocess import CalledProcessError, run
+
+try:
+ from pydub import AudioSegment
+except:
+ pass
def is_ffmpeg_installed():
@@ -82,8 +86,10 @@
): # download url to local file
data_or_path_or_list = download_from_url(data_or_path_or_list)
- if isinstance(data_or_path_or_list, str) and os.path.exists(data_or_path_or_list): # local file
+ if (isinstance(data_or_path_or_list, str) and os.path.exists(data_or_path_or_list)) or hasattr(data_or_path_or_list, 'read'): # local file or bytes io
if data_type is None or data_type == "sound":
+ if hasattr(data_or_path_or_list, "read") and hasattr(data_or_path_or_list, "seek"):
+ data_or_path_or_list.seek(0)
# if use_ffmpeg:
# data_or_path_or_list = _load_audio_ffmpeg(data_or_path_or_list, sr=fs)
# data_or_path_or_list = torch.from_numpy(data_or_path_or_list).squeeze() # [n_samples,]
@@ -138,7 +144,10 @@
def load_bytes(input):
- input = validate_frame_rate(input)
+ try:
+ input = validate_frame_rate(input)
+ except:
+ pass
middle_data = np.frombuffer(input, dtype=np.int16)
middle_data = np.asarray(middle_data)
if middle_data.dtype.kind not in "iu":
@@ -153,16 +162,22 @@
array = np.frombuffer((middle_data.astype(dtype) - offset) / abs_max, dtype=np.float32)
return array
+
def validate_frame_rate(
input,
fs: int = 16000,
):
-
+
# 灏嗘枃浠惰鍙栦负瀛楄妭娴�
byte_data = BytesIO(input)
# 浣跨敤 pydub 鍔犺浇闊抽
- audio = AudioSegment.from_file(byte_data)
+ try:
+ audio = AudioSegment.from_file(byte_data)
+ except:
+ raise RuntimeError(
+ "You are decoding the pcm data, please install pydub first. via `pip install pydub`."
+ )
# 纭繚閲囨牱鐜囦负 16000 Hz
if audio.frame_rate != fs:
@@ -175,7 +190,7 @@
# 鑾峰彇閲嶆柊閲囨牱鍚庣殑瀛楄妭娴佹暟鎹�
input = output.read()
-
+
return input
--
Gitblit v1.9.1