From e67ed1d45d5a9d7fb7bb22d15fd2bfef17e9076f Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 17 一月 2024 10:57:14 +0800
Subject: [PATCH] Update load_pretrained_model.py
---
funasr/datasets/audio_datasets/datasets.py | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/funasr/datasets/audio_datasets/datasets.py b/funasr/datasets/audio_datasets/datasets.py
index edf127f..5af33fc 100644
--- a/funasr/datasets/audio_datasets/datasets.py
+++ b/funasr/datasets/audio_datasets/datasets.py
@@ -1,7 +1,7 @@
import torch
from funasr.register import tables
-from funasr.utils.load_utils import extract_fbank
+from funasr.utils.load_utils import extract_fbank, load_audio_text_image_video
@tables.register("dataset_classes", "AudioDataset")
@@ -55,7 +55,7 @@
# import pdb;
# pdb.set_trace()
source = item["source"]
- data_src = load_audio(source, fs=self.fs)
+ data_src = load_audio_text_image_video(source, fs=self.fs)
if self.preprocessor_speech:
data_src = self.preprocessor_speech(data_src)
speech, speech_lengths = extract_fbank(data_src, data_type=self.data_type, frontend=self.frontend) # speech: [b, T, d]
--
Gitblit v1.9.1