From 4a99b828a834d1d3870abbe3ee477518470f3dd9 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 07 六月 2024 01:58:14 +0800
Subject: [PATCH] auto frontend
---
funasr/datasets/audio_datasets/samplers.py | 12 +++++++++---
1 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/funasr/datasets/audio_datasets/samplers.py b/funasr/datasets/audio_datasets/samplers.py
index 18f8f91..7195add 100644
--- a/funasr/datasets/audio_datasets/samplers.py
+++ b/funasr/datasets/audio_datasets/samplers.py
@@ -364,6 +364,8 @@
self.sort_size = sort_size * num_replicas
self.max_token_length = kwargs.get("max_token_length", 2048)
self.length_scale_source = kwargs.get("length_scale_source", 1.0)
+ self.start_step = kwargs.get("start_step", 2048)
+
super().__init__(
dataset, num_replicas=num_replicas, rank=rank, shuffle=shuffle, drop_last=drop_last
)
@@ -415,13 +417,17 @@
rank_batches[i % self.num_replicas].append(batch)
# Assign all batches for the current rank directly
- final_batches = rank_batches[self.rank]
+ final_batches = rank_batches[self.rank][self.start_step :]
+ self.batch_num = len(final_batches)
+ logging.info(
+ f"rank: {self.rank}, dataloader start from step: {self.start_step}, batch_num: {self.batch_num}"
+ )
return iter(final_batches)
def __len__(self):
-
- return 1
+ # Calculate the number of batches per epoch for the current rank
+ return self.batch_num
def set_epoch(self, epoch):
self.epoch = epoch
--
Gitblit v1.9.1