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

v3

Browse Source
This commit is contained in:
游雁 2024-09-26 13:47:00 +08:00
parent 0076212ac5
commit 4e57ba7b92
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
funasr/datasets/openai_datasets/index_ds.py
View File

@ -53,7 +53,7 @@ class OpenAIIndexDSJsonl(torch.utils.data.Dataset): # torch.utils.data.Dataset
data = data_dict["messages"]
speech_length = data_dict.get("speech_length", -1) // 8
text_length = data_dict.get("text_length", 0)
if speech_length * 2 > self.max_source_length:
if speech_length * 1.3 > self.max_source_length:
logging.info(
f"speech_length: {speech_length*8} > {self.max_source_length}, drop it: {data_dict}"
)