From 37d6930561f4e798e76f81c37d912906c97b6bea Mon Sep 17 00:00:00 2001
From: pointerhacker <145901472+pointerhacker@users.noreply.github.com>
Date: 星期三, 20 十一月 2024 18:39:05 +0800
Subject: [PATCH] fix:添加音频码率验证以防止模型异常 (#2219)
---
funasr/utils/load_utils.py | 28 ++++++++++++++++++++++++++++
1 files changed, 28 insertions(+), 0 deletions(-)
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.py
index 37b3dbf..aabf5d9 100644
--- a/funasr/utils/load_utils.py
+++ b/funasr/utils/load_utils.py
@@ -1,6 +1,7 @@
import os
import torch
import json
+from io import BytesIO
import torch.distributed as dist
import numpy as np
import kaldiio
@@ -9,6 +10,7 @@
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
@@ -136,6 +138,7 @@
def load_bytes(input):
+ input = validate_frame_rate(input)
middle_data = np.frombuffer(input, dtype=np.int16)
middle_data = np.asarray(middle_data)
if middle_data.dtype.kind not in "iu":
@@ -150,6 +153,31 @@
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)
+
+ # 纭繚閲囨牱鐜囦负 16000 Hz
+ if audio.frame_rate != fs:
+ audio = audio.set_frame_rate(fs)
+
+ # 灏嗛噸鏂伴噰鏍峰悗鐨勯煶棰戝鍑轰负瀛楄妭娴�
+ output = BytesIO()
+ audio.export(output, format="wav")
+ output.seek(0)
+
+ # 鑾峰彇閲嶆柊閲囨牱鍚庣殑瀛楄妭娴佹暟鎹�
+ input = output.read()
+
+ return input
+
def extract_fbank(data, data_len=None, data_type: str = "sound", frontend=None, **kwargs):
if isinstance(data, np.ndarray):
--
Gitblit v1.9.1