From ff78a5ea80f95192f8ccd682ee63dd793b8c4de1 Mon Sep 17 00:00:00 2001
From: 仁迷 <haoneng.lhn@alibaba-inc.com>
Date: 星期一, 13 二月 2023 16:26:15 +0800
Subject: [PATCH] update dataset audio load
---
funasr/bin/asr_inference_paraformer.py | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer.py b/funasr/bin/asr_inference_paraformer.py
index 5d7d6ea..3769b6c 100644
--- a/funasr/bin/asr_inference_paraformer.py
+++ b/funasr/bin/asr_inference_paraformer.py
@@ -181,7 +181,7 @@
self.nbest = nbest
self.frontend = frontend
self.encoder_downsampling_factor = 1
- if asr_train_args.encoder_conf["input_layer"] == "conv2d":
+ if asr_train_args.encoder == "data2vec_encoder" or asr_train_args.encoder_conf["input_layer"] == "conv2d":
self.encoder_downsampling_factor = 4
@torch.no_grad()
--
Gitblit v1.9.1