From 561bdbdfc0f8fd6234c5130fdc8631bf8e294bd8 Mon Sep 17 00:00:00 2001
From: 王梦迪 <73778524+di-osc@users.noreply.github.com>
Date: 星期四, 22 五月 2025 11:27:01 +0800
Subject: [PATCH] 通过缓存seg_dict，加快seaco_paraformer推理 (#2520)
---
funasr/datasets/audio_datasets/samplers.py | 5 +----
1 files changed, 1 insertions(+), 4 deletions(-)
diff --git a/funasr/datasets/audio_datasets/samplers.py b/funasr/datasets/audio_datasets/samplers.py
index f8f744c..f7057de 100644
--- a/funasr/datasets/audio_datasets/samplers.py
+++ b/funasr/datasets/audio_datasets/samplers.py
@@ -399,10 +399,7 @@
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
- and count <= self.batch_size_sample_max
- ):
+ 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
--
Gitblit v1.9.1