From a09aba419f305abadc185ec41c336211549e894b Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 30 四月 2024 12:52:58 +0800
Subject: [PATCH] Dev gzf exp (#1682)
---
funasr/datasets/audio_datasets/espnet_samplers.py | 7 +++++--
1 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/funasr/datasets/audio_datasets/espnet_samplers.py b/funasr/datasets/audio_datasets/espnet_samplers.py
index cb30a28..e155cd7 100644
--- a/funasr/datasets/audio_datasets/espnet_samplers.py
+++ b/funasr/datasets/audio_datasets/espnet_samplers.py
@@ -71,7 +71,7 @@
self.max_token_length = kwargs.get("max_token_length", 2048)
self.min_token_length = kwargs.get("min_token_length", 0)
self.length_scale_source = kwargs.get("length_scale_source", 1.0)
- self.start_step = 0
+ self.start_step = start_step
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,
@@ -146,7 +146,10 @@
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)}"
+ )
# Return an iterator over the batches for the current rank
return iter(rank_batches)
--
Gitblit v1.9.1