Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

按照脚本训练流程问题 #52

Open
KIP1024 opened this issue Oct 3, 2023 · 0 comments
Open

按照脚本训练流程问题 #52

KIP1024 opened this issue Oct 3, 2023 · 0 comments

Comments

@KIP1024
Copy link

KIP1024 commented Oct 3, 2023

1 我先是按照下载方式中通过魔塔社区下载的数据集,它是自动就给分好train、test等音频数据集,还有一个json文件与切分数据集的名称对应
2 stage 0这一步骤(wenetspeech_data_prep.sh),准备数据部分出现问题,我是把下载数据的json文件放在对应的路径下(但我总感觉不是这个json文件,这个只是对应划分训练集的),执行到下面 3 这个代码时候出现 4 的报错。求解!!没找到有写训练流程的教程。
3 # Files to be created:

wav.scp text segments utt2dur

python3 local/extract_meta.py
$wenetspeech_dir/WenetSpeech.json $corpus_dir || exit 1;

4
Traceback (most recent call last):
File "local/extract_meta.py", line 102, in
main()
File "local/extract_meta.py", line 98, in main
meta_analysis(args.input_json, args.output_dir)
File "local/extract_meta.py", line 47, in meta_analysis
if json_data['audio'] is not None:
KeyError: 'audio'

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant