From eb1574b813e230b156fc09eaaf03227b1b0b4134 Mon Sep 17 00:00:00 2001
From: weilikai <jasper@talkus.fun>
Date: 星期六, 20 九月 2025 22:41:05 +0800
Subject: [PATCH] fix: support loading .pcm (16k 1c 16bit) audio files in load_utils.py (#2667) (#2668)
---
funasr/datasets/audio_datasets/samplers.py | 9 +++------
1 files changed, 3 insertions(+), 6 deletions(-)
diff --git a/funasr/datasets/audio_datasets/samplers.py b/funasr/datasets/audio_datasets/samplers.py
index bddf186..f7057de 100644
--- a/funasr/datasets/audio_datasets/samplers.py
+++ b/funasr/datasets/audio_datasets/samplers.py
@@ -392,17 +392,14 @@
)
batch = []
max_len_in_batch = 0
- count = 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
- 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
@@ -410,7 +407,7 @@
buffer_batches.append(batch)
batch = [idx]
max_len_in_batch = sample_length
- count = 0
+ count = 1
if batch:
buffer_batches.append(batch)
--
Gitblit v1.9.1