From c350b6becb887d578126e363306e7398782ef675 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 07 六月 2024 04:32:26 +0800
Subject: [PATCH] auto frontend
---
funasr/datasets/openai_datasets/datasets.py | 8 ++++----
funasr/datasets/audio_datasets/samplers.py | 9 ++++++++-
2 files changed, 12 insertions(+), 5 deletions(-)
diff --git a/funasr/datasets/audio_datasets/samplers.py b/funasr/datasets/audio_datasets/samplers.py
index 27fbdac..2e271af 100644
--- a/funasr/datasets/audio_datasets/samplers.py
+++ b/funasr/datasets/audio_datasets/samplers.py
@@ -365,6 +365,7 @@
self.max_token_length = kwargs.get("max_token_length", 2048)
self.length_scale_source = kwargs.get("length_scale_source", 1.0)
self.start_step = kwargs.get("start_step", 2048)
+ self.batch_size_sample_max = kwargs.get("batch_size_sample_max", 200)
super().__init__(
dataset, num_replicas=num_replicas, rank=rank, shuffle=shuffle, drop_last=drop_last
@@ -388,19 +389,25 @@
)
batch = []
max_len_in_batch = 0
+ count = 0
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:
+ 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
else:
buffer_batches.append(batch)
batch = [idx]
max_len_in_batch = sample_length
+ count = 0
if batch:
buffer_batches.append(batch)
diff --git a/funasr/datasets/openai_datasets/datasets.py b/funasr/datasets/openai_datasets/datasets.py
index c51ace9..46735ba 100644
--- a/funasr/datasets/openai_datasets/datasets.py
+++ b/funasr/datasets/openai_datasets/datasets.py
@@ -154,13 +154,13 @@
fbank_mask += fbank_mask_i
fbank_beg.append(fbank_beg_i)
- # if len(input_ids) > self.max_token_length:
- # badcase_flag = True
+ if len(input_ids) > self.max_token_length:
+ badcase_flag = True
if badcase_flag:
continue
- input_ids = torch.tensor(input_ids, dtype=torch.int64)[: self.max_token_length]
+ input_ids = torch.tensor(input_ids, dtype=torch.int64) # [: self.max_token_length]
attention_mask = torch.tensor([len(input_ids)], dtype=torch.int32)
- labels = torch.tensor(labels, dtype=torch.int64)[: self.max_token_length]
+ labels = torch.tensor(labels, dtype=torch.int64) # [: self.max_token_length]
fbank = speech[0, :, :]
fbank_lens = speech_lengths
--
Gitblit v1.9.1