From 9fd3c47fd7ff191e1e07457b6bcffa1823e69b51 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期六, 08 六月 2024 21:08:54 +0800
Subject: [PATCH] fix bug
---
funasr/datasets/openai_datasets/datasets.py | 5 ++++-
1 files changed, 4 insertions(+), 1 deletions(-)
diff --git a/funasr/datasets/openai_datasets/datasets.py b/funasr/datasets/openai_datasets/datasets.py
index 46735ba..3bc6aa0 100644
--- a/funasr/datasets/openai_datasets/datasets.py
+++ b/funasr/datasets/openai_datasets/datasets.py
@@ -155,11 +155,14 @@
fbank_beg.append(fbank_beg_i)
if len(input_ids) > self.max_token_length:
+ logging.info(
+ f"input_ids > max_token_length: {len(input_ids)}>{self.max_token_length}, {item}"
+ )
badcase_flag = True
if badcase_flag:
continue
input_ids = torch.tensor(input_ids, dtype=torch.int64) # [: self.max_token_length]
- attention_mask = torch.tensor([len(input_ids)], dtype=torch.int32)
+ attention_mask = torch.tensor([1] * len(input_ids), dtype=torch.int32)
labels = torch.tensor(labels, dtype=torch.int64) # [: self.max_token_length]
fbank = speech[0, :, :]
--
Gitblit v1.9.1