From d80ac2fd2df4e7fb8a28acfa512bb11472b5cc99 Mon Sep 17 00:00:00 2001
From: liugz18 <57401541+liugz18@users.noreply.github.com>
Date: 星期四, 18 七月 2024 21:34:55 +0800
Subject: [PATCH] Rename 'res' in line 514 to avoid with naming conflict with line 365
---
funasr/datasets/audio_datasets/espnet_samplers.py | 13 ++++++++-----
1 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/funasr/datasets/audio_datasets/espnet_samplers.py b/funasr/datasets/audio_datasets/espnet_samplers.py
index e155cd7..004201e 100644
--- a/funasr/datasets/audio_datasets/espnet_samplers.py
+++ b/funasr/datasets/audio_datasets/espnet_samplers.py
@@ -72,6 +72,7 @@
self.min_token_length = kwargs.get("min_token_length", 0)
self.length_scale_source = kwargs.get("length_scale_source", 1.0)
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,
@@ -146,16 +147,18 @@
start_idx = self.rank * batches_per_rank
end_idx = start_idx + batches_per_rank
rank_batches = buffer_batches[start_idx + self.start_step : end_idx]
- if self.start_step > 0:
- logging.info(
- f"Warning, rank: {self.rank}, dataloader start from step: {self.start_step}, batch_num_before: {end_idx-start_idx}, now: {len(rank_batches)}"
- )
+
+ self.batch_num = len(rank_batches)
+
+ logging.info(
+ f"rank: {self.rank}, dataloader start from step: {self.start_step}, batch_num: {end_idx-start_idx}, batch_num_after_step: {len(rank_batches)}"
+ )
# Return an iterator over the batches for the current rank
return iter(rank_batches)
def __len__(self):
# Calculate the number of batches per epoch for the current rank
- return 1
+ return self.batch_num
def set_epoch(self, epoch):
# Set the epoch for shuffling
--
Gitblit v1.9.1