From 32905d8cdedd53dad26680b0bd41397aaf0e51ae Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 05 一月 2024 11:52:48 +0800
Subject: [PATCH] funasr1.0
---
funasr/models/paraformer/model.py | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/funasr/models/paraformer/model.py b/funasr/models/paraformer/model.py
index 4ce2c32..5492420 100644
--- a/funasr/models/paraformer/model.py
+++ b/funasr/models/paraformer/model.py
@@ -22,7 +22,7 @@
from torch.cuda.amp import autocast
-from funasr.datasets.audio_datasets.load_audio_extract_fbank import load_audio, extract_fbank
+from funasr.utils.load_utils import load_audio_and_text_image_video, extract_fbank, load_audio_and_text_image_video
from funasr.utils import postprocess_utils
from funasr.utils.datadir_writer import DatadirWriter
from funasr.register import tables
@@ -466,7 +466,7 @@
else:
# extract fbank feats
time1 = time.perf_counter()
- audio_sample_list = load_audio(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000))
+ audio_sample_list = load_audio_and_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000), data_type=kwargs.get("data_type", "sound"), tokenizer=tokenizer)
time2 = time.perf_counter()
meta_data["load_data"] = f"{time2 - time1:0.3f}"
speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"), frontend=frontend)
--
Gitblit v1.9.1