From fce4e1d1b48f23cd8332e60afce3df8d6209a6a7 Mon Sep 17 00:00:00 2001
From: gaochangfeng <54253717+gaochangfeng@users.noreply.github.com>
Date: 星期四, 11 四月 2024 14:59:22 +0800
Subject: [PATCH] SenseVoice对富文本解码的参数 (#1608)
---
funasr/datasets/audio_datasets/espnet_samplers.py | 8 ++++----
1 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/funasr/datasets/audio_datasets/espnet_samplers.py b/funasr/datasets/audio_datasets/espnet_samplers.py
index d38e2bf..c6ed919 100644
--- a/funasr/datasets/audio_datasets/espnet_samplers.py
+++ b/funasr/datasets/audio_datasets/espnet_samplers.py
@@ -57,7 +57,7 @@
self.drop_last = drop_last
self.total_size = len(self.dataset)
- # self.num_samples = int(math.ceil(self.total_size / self.num_replicas))
+ self.num_samples = int(math.ceil(self.total_size / self.num_replicas))
self.epoch = 0
self.sort_size = sort_size * num_replicas
self.max_token_length = kwargs.get("max_token_length", 2048)
@@ -71,10 +71,10 @@
g = torch.Generator()
g.manual_seed(self.epoch)
random.seed(self.epoch)
- indices = torch.randperm(self.total_size, generator=g).tolist()
+ indices = torch.randperm(len(self.dataset), generator=g).tolist()
else:
- indices = list(range(self.total_size))
-
+ indices = list(range(len(self.dataset)))
+
# Sort indices by sample length
sorted_indices = sorted(indices, key=lambda idx: self.dataset.get_source_len(idx))
--
Gitblit v1.9.1