From ff4306346eae4021c711df3fe23979e82e06e751 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 19 二月 2024 21:26:25 +0800
Subject: [PATCH] aishell example
---
funasr/datasets/audio_datasets/datasets.py | 6 +++---
1 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/funasr/datasets/audio_datasets/datasets.py b/funasr/datasets/audio_datasets/datasets.py
index 62acb44..ab08fb0 100644
--- a/funasr/datasets/audio_datasets/datasets.py
+++ b/funasr/datasets/audio_datasets/datasets.py
@@ -22,12 +22,12 @@
self.index_ds = index_ds_class(path, **kwargs)
preprocessor_speech = kwargs.get("preprocessor_speech", None)
if preprocessor_speech:
- preprocessor_speech_class = tables.preprocessor_speech_classes.get(preprocessor_speech)
+ preprocessor_speech_class = tables.preprocessor_classes.get(preprocessor_speech)
preprocessor_speech = preprocessor_speech_class(**kwargs.get("preprocessor_speech_conf"))
self.preprocessor_speech = preprocessor_speech
preprocessor_text = kwargs.get("preprocessor_text", None)
if preprocessor_text:
- preprocessor_text_class = tables.preprocessor_text_classes.get(preprocessor_text)
+ preprocessor_text_class = tables.preprocessor_classes.get(preprocessor_text)
preprocessor_text = preprocessor_text_class(**kwargs.get("preprocessor_text_conf"))
self.preprocessor_text = preprocessor_text
@@ -57,7 +57,7 @@
source = item["source"]
data_src = load_audio_text_image_video(source, fs=self.fs)
if self.preprocessor_speech:
- data_src = self.preprocessor_speech(data_src)
+ data_src = self.preprocessor_speech(data_src, fs=self.fs)
speech, speech_lengths = extract_fbank(data_src, data_type=self.data_type, frontend=self.frontend, is_final=True) # speech: [b, T, d]
target = item["target"]
--
Gitblit v1.9.1