From 2ac38adbe5f4e1374a079e032ed4b504351a207c Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 23 四月 2024 18:08:57 +0800
Subject: [PATCH] Dev gzf exp (#1647)

---
 funasr/datasets/audio_datasets/samplers.py |    7 +++++++
 1 files changed, 7 insertions(+), 0 deletions(-)

diff --git a/funasr/datasets/audio_datasets/samplers.py b/funasr/datasets/audio_datasets/samplers.py
index 108e68a..fdf630e 100644
--- a/funasr/datasets/audio_datasets/samplers.py
+++ b/funasr/datasets/audio_datasets/samplers.py
@@ -301,6 +301,7 @@
                  batch_type="token",
                  num_replicas=None,
                  rank=None,
+                 rank_split=False,
                  shuffle=True,
                  drop_last=False,
                  is_training: bool = True,
@@ -314,6 +315,12 @@
         except:
             rank = 0
             num_replicas = 1
+
+        if rank_split:
+            logging.info(f"Warning, rank_split: {rank_split}, batch and shuffle data in local rank")
+            rank = 0
+            num_replicas = 1
+            
         self.rank = rank
         self.num_replicas = num_replicas
         self.dataset = dataset

--
Gitblit v1.9.1