speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

batch

Browse Source
This commit is contained in:
游雁 2024-09-21 11:46:52 +08:00
parent 204fcd7900
commit d45230c6ba
1 changed files with 15 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
funasr/datasets/audio_datasets/index_ds.py
View File

@ -92,21 +92,21 @@ class IndexDSJsonlRankFull(torch.utils.data.Dataset):
target = data["target"]
source_len = data.get("source_len", 1)
target_len = data.get("target_len", 0)
if "aishell" in source:
target = target.replace(" ", "")
if (
source_len < self.min_source_length
or source_len > self.max_source_length
):
continue
if (
target_len < self.min_target_length
or target_len > self.max_target_length
):
continue
if (source_len + target_len) > self.max_token_length:
continue
# if "aishell" in source:
# target = target.replace(" ", "")
# if (
# source_len < self.min_source_length
# or source_len > self.max_source_length
# ):
# continue
# if (
# target_len < self.min_target_length
# or target_len > self.max_target_length
# ):
# continue
#
# if (source_len + target_len) > self.max_token_length:
# continue
contents_i = {
"source": source,