From 528f92f7a2a26cade1c57ccf26b0ba6524e7cae5 Mon Sep 17 00:00:00 2001
From: TnR2 <115166373+TnR2@users.noreply.github.com>
Date: 星期三, 01 十月 2025 14:45:17 +0800
Subject: [PATCH] fix: handle empty strings after event removal in transcription processing (def rich_transcription_postprocess(s)) (#2681)
---
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