From 5589b4a6177a0ca6836c304a152befe87f0ddd96 Mon Sep 17 00:00:00 2001
From: haoneng.lhn <haoneng.lhn@alibaba-inc.com>
Date: 星期五, 14 四月 2023 11:47:28 +0800
Subject: [PATCH] support wav_file input
---
funasr/models/e2e_asr_mfcca.py | 6 +++++-
1 files changed, 5 insertions(+), 1 deletions(-)
diff --git a/funasr/models/e2e_asr_mfcca.py b/funasr/models/e2e_asr_mfcca.py
index 0336133..f22f12a 100644
--- a/funasr/models/e2e_asr_mfcca.py
+++ b/funasr/models/e2e_asr_mfcca.py
@@ -36,7 +36,11 @@
import random
import math
class MFCCA(AbsESPnetModel):
- """CTC-attention hybrid Encoder-Decoder model"""
+ """
+ Author: Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University
+ MFCCA:Multi-Frame Cross-Channel attention for multi-speaker ASR in Multi-party meeting scenario
+ https://arxiv.org/abs/2210.05265
+ """
def __init__(
self,
--
Gitblit v1.9.1