From dee1354d0d984df21d16a2eba5bacec31bfb0b4b Mon Sep 17 00:00:00 2001
From: 维石 <shixian.shi@alibaba-inc.com>
Date: 星期五, 19 四月 2024 14:57:31 +0800
Subject: [PATCH] empty result bug fix
---
funasr/datasets/audio_datasets/espnet_samplers.py | 11 ++++++-----
1 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/funasr/datasets/audio_datasets/espnet_samplers.py b/funasr/datasets/audio_datasets/espnet_samplers.py
index d38e2bf..bca0753 100644
--- a/funasr/datasets/audio_datasets/espnet_samplers.py
+++ b/funasr/datasets/audio_datasets/espnet_samplers.py
@@ -57,10 +57,11 @@
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)
+ self.min_token_length = kwargs.get("min_token_length", 0)
self.length_scale_source = kwargs.get("length_scale_source", 1.0)
@@ -71,10 +72,10 @@
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))
@@ -85,7 +86,7 @@
for idx in sorted_indices:
original_sample_length = self.dataset.get_source_len(idx)
- if original_sample_length > self.max_token_length: # Skip samples that exceed the max length
+ if original_sample_length < self.min_token_length or original_sample_length > self.max_token_length: # Skip samples that exceed the max length
continue
# Set sample_length based on the batch type
sample_length = 1 if self.batch_type == "example" else original_sample_length
--
Gitblit v1.9.1