From b28f3c9da94ae72a3a0b7bb5982b587be7cf4cd6 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 18 一月 2024 22:00:58 +0800
Subject: [PATCH] fsmn-vad bugfix (#1270)
---
funasr/models/scama/decoder.py | 11 ++++++++---
1 files changed, 8 insertions(+), 3 deletions(-)
diff --git a/funasr/models/scama/sanm_decoder.py b/funasr/models/scama/decoder.py
similarity index 99%
rename from funasr/models/scama/sanm_decoder.py
rename to funasr/models/scama/decoder.py
index 4222e5f..9dcb9da 100644
--- a/funasr/models/scama/sanm_decoder.py
+++ b/funasr/models/scama/decoder.py
@@ -1,3 +1,8 @@
+#!/usr/bin/env python3
+# -*- encoding: utf-8 -*-
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+# MIT License (https://opensource.org/licenses/MIT)
+
from typing import List
from typing import Tuple
import logging
@@ -192,11 +197,11 @@
@tables.register("decoder_classes", "FsmnDecoderSCAMAOpt")
class FsmnDecoderSCAMAOpt(BaseTransformerDecoder):
"""
- Author: Speech Lab of DAMO Academy, Alibaba Group
+ Author: Shiliang Zhang, Zhifu Gao, Haoneng Luo, Ming Lei, Jie Gao, Zhijie Yan, Lei Xie
SCAMA: Streaming chunk-aware multihead attention for online end-to-end speech recognition
- https://arxiv.org/abs/2006.01713
-
+ https://arxiv.org/abs/2006.01712
"""
+
def __init__(
self,
vocab_size: int,
--
Gitblit v1.9.1