From 3c349ac0531b07239f37b81254f8568ab80e3f6a Mon Sep 17 00:00:00 2001
From: Han Zhang <45134013+holazzer@users.noreply.github.com>
Date: 星期二, 18 三月 2025 11:45:37 +0800
Subject: [PATCH] fix: use converted token_ids for alignment for sensevoice model with timestamp output (#2429)

---
 funasr/models/sense_voice/__init__.py |    0 
 1 files changed, 0 insertions(+), 0 deletions(-)

diff --git a/funasr/datasets/large_datasets/__init__.py b/funasr/models/sense_voice/__init__.py
similarity index 100%
copy from funasr/datasets/large_datasets/__init__.py
copy to funasr/models/sense_voice/__init__.py

--
Gitblit v1.9.1