From 9f2e5f058ec9a080ed64f9c951f36bbe93f25ede Mon Sep 17 00:00:00 2001
From: zhuzizyf <42790740+zhuzizyf@users.noreply.github.com>
Date: 星期一, 15 五月 2023 10:56:15 +0800
Subject: [PATCH] Update e2e-vad.h
---
funasr/models/encoder/resnet34_encoder.py | 12 ++++++++++++
1 files changed, 12 insertions(+), 0 deletions(-)
diff --git a/funasr/models/encoder/resnet34_encoder.py b/funasr/models/encoder/resnet34_encoder.py
index 7d7179a..93695c8 100644
--- a/funasr/models/encoder/resnet34_encoder.py
+++ b/funasr/models/encoder/resnet34_encoder.py
@@ -406,6 +406,12 @@
tf2torch_tensor_name_prefix_torch="encoder",
tf2torch_tensor_name_prefix_tf="seq2seq/speech_encoder"
):
+ """
+ Author: Speech Lab, Alibaba Group, China
+ SOND: Speaker Overlap-aware Neural Diarization for Multi-party Meeting Analysis
+ https://arxiv.org/abs/2211.10243
+ """
+
super(ResNet34Diar, self).__init__(
input_size,
use_head_conv=use_head_conv,
@@ -633,6 +639,12 @@
tf2torch_tensor_name_prefix_torch="encoder",
tf2torch_tensor_name_prefix_tf="seq2seq/speech_encoder"
):
+ """
+ Author: Speech Lab, Alibaba Group, China
+ TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization
+ https://arxiv.org/abs/2303.05397
+ """
+
super(ResNet34SpL2RegDiar, self).__init__(
input_size,
use_head_conv=use_head_conv,
--
Gitblit v1.9.1