From 28ccfbfc51068a663a80764e14074df5edf2b5ba Mon Sep 17 00:00:00 2001
From: kongdeqiang <kongdeqiang960204@163.com>
Date: 星期五, 13 三月 2026 17:41:41 +0800
Subject: [PATCH] 提交
---
funasr/datasets/audio_datasets/samplers.py | 23 +++++++++++++++--------
1 files changed, 15 insertions(+), 8 deletions(-)
diff --git a/funasr/datasets/audio_datasets/samplers.py b/funasr/datasets/audio_datasets/samplers.py
index 27fbdac..f7057de 100644
--- a/funasr/datasets/audio_datasets/samplers.py
+++ b/funasr/datasets/audio_datasets/samplers.py
@@ -334,6 +334,7 @@
drop_last=False,
is_training: bool = True,
sort_size: int = 1024,
+ start_step: int = 0,
**kwargs,
):
@@ -364,11 +365,14 @@
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
- )
+ self.batch_size_sample_max = kwargs.get("batch_size_sample_max", 200)
+ self.start_step = start_step
+ self.batch_num = 1
+ if self.start_step > 0:
+ logging.info(f"Warning, start_step > 0, dataloader start from step: {self.start_step}")
+ # super().__init__(
+ # dataset, num_replicas=num_replicas, rank=rank, shuffle=shuffle, drop_last=drop_last
+ # )
def __iter__(self):
if self.shuffle:
@@ -388,19 +392,22 @@
)
batch = []
max_len_in_batch = 0
+ count = 1
for idx in buffer:
original_sample_length = self.dataset.get_source_len(idx)
if original_sample_length > self.max_token_length:
continue
sample_length = 1 if self.batch_type == "example" else original_sample_length
potential_batch_length = max(max_len_in_batch, sample_length) * (len(batch) + 1)
- if potential_batch_length <= self.batch_size:
+ if potential_batch_length <= self.batch_size and count < self.batch_size_sample_max:
batch.append(idx)
max_len_in_batch = max(max_len_in_batch, sample_length)
+ count += 1
else:
buffer_batches.append(batch)
batch = [idx]
max_len_in_batch = sample_length
+ count = 1
if batch:
buffer_batches.append(batch)
@@ -417,11 +424,11 @@
rank_batches[i % self.num_replicas].append(batch)
# Assign all batches for the current rank directly
- final_batches = rank_batches[self.rank] # [self.start_step :]
+ 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}"
+ f"rank: {self.rank}, dataloader start from step: {self.start_step}, batch_num: {len(rank_batches[self.rank])}, after: {self.batch_num}"
)
return iter(final_batches)
--
Gitblit v1.9.1