From 28ccfbfc51068a663a80764e14074df5edf2b5ba Mon Sep 17 00:00:00 2001
From: kongdeqiang <kongdeqiang960204@163.com>
Date: 星期五, 13 三月 2026 17:41:41 +0800
Subject: [PATCH] 提交
---
funasr/datasets/openai_datasets/datasets.py | 29 +++++++++++++++++++----------
1 files changed, 19 insertions(+), 10 deletions(-)
diff --git a/funasr/datasets/openai_datasets/datasets.py b/funasr/datasets/openai_datasets/datasets.py
index ae9f289..d670708 100644
--- a/funasr/datasets/openai_datasets/datasets.py
+++ b/funasr/datasets/openai_datasets/datasets.py
@@ -283,10 +283,11 @@
self.pattern = re.compile(r"(<\|startofspeech\|>.*?<\|endofspeech\|>)")
# self.kwargs = kwargs
- self.max_token_length = kwargs.get("max_token_length", 1024)
+ self.max_token_length = kwargs.get("max_token_length", 1500)
self.batch_size_scale_ratio_max = kwargs.get("batch_size_scale_ratio_max", 1.5)
self.batch_size_token_max = kwargs.get("batch_size_token_max", 2500)
self.multiturn_num_max = kwargs.get("multiturn_num_max", 5)
+ self.max_source_length = kwargs.get("max_source_length", 3000)
def get_source_len(self, index):
item = self.index_ds[index]
@@ -300,9 +301,9 @@
return len(self.index_ds)
def __getitem__(self, index):
- import pdb
-
- pdb.set_trace()
+ # import pdb
+ #
+ # pdb.set_trace()
output = None
@@ -334,6 +335,12 @@
):
if i >= self.multiturn_num_max:
break
+ if len(input_ids) > self.max_token_length:
+ logging.info(
+ f"input_ids > max_token_length: {len(input_ids)}>{self.max_token_length}, {item}"
+ )
+ break
+
if i == 0:
source_input = f"<|im_start|>system\n{system_prompt}<|im_end|>\n<|im_start|>user\n{user_prompt}<|im_end|>\n<|im_start|>assistant\n"
else:
@@ -372,6 +379,11 @@
frontend=self.frontend,
is_final=True,
) # speech: [b, T, d]
+ if speech_lengths > self.max_source_length:
+ logging.info(
+ f"speech_lengths > max_source_length: {speech_lengths}>{self.max_source_length}, {item}"
+ )
+ badcase_flag = True
if self.permute:
speech = speech.permute(0, 2, 1)
# if speech_lengths > self.batch_size:
@@ -397,20 +409,17 @@
labels += source_mask + target_ids
fbank.append(speech[0, :, :])
fbank_mask += fbank_mask_i
+ fbank_lens.append(speech_lengths)
- 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([1] * len(input_ids), dtype=torch.int32)
labels = torch.tensor(labels, dtype=torch.int64) # [: self.max_token_length]
# fbank = speech[0, :, :]
- fbank_lens = speech_lengths
+ # fbank_lens = torch.tensor(fbank_lens, dtype=torch.int32)
fbank_mask = torch.tensor(fbank_mask, dtype=torch.float32)
fbank_beg = torch.tensor(fbank_beg, dtype=torch.int32)
fake_token_len = torch.tensor(fake_token_len, dtype=torch.int32)
--
Gitblit v1.9.1