From 0a4a1d5257dace9561d95b38a9386539908dcd5e Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 23 四月 2024 12:48:52 +0800
Subject: [PATCH] Dev gzf exp (#1645)
---
funasr/datasets/audio_datasets/espnet_samplers.py | 11 ++++++++---
1 files changed, 8 insertions(+), 3 deletions(-)
diff --git a/funasr/datasets/audio_datasets/espnet_samplers.py b/funasr/datasets/audio_datasets/espnet_samplers.py
index bca0753..4bb34f3 100644
--- a/funasr/datasets/audio_datasets/espnet_samplers.py
+++ b/funasr/datasets/audio_datasets/espnet_samplers.py
@@ -32,8 +32,9 @@
def __init__(self, dataset,
batch_size,
batch_type="token",
- num_replicas=None,
rank=None,
+ num_replicas=None,
+ rank_split=False,
shuffle=True,
drop_last=False,
is_training: bool = True,
@@ -45,6 +46,10 @@
rank = dist.get_rank()
num_replicas = dist.get_world_size()
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
@@ -65,8 +70,8 @@
self.length_scale_source = kwargs.get("length_scale_source", 1.0)
- super().__init__(dataset, num_replicas=num_replicas, rank=rank,
- shuffle=shuffle, drop_last=drop_last)
+ # super().__init__(dataset, num_replicas=num_replicas, rank=rank,
+ # shuffle=shuffle, drop_last=drop_last)
def __iter__(self):
if self.shuffle:
g = torch.Generator()
--
Gitblit v1.9.1