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

error: unrecognized arguments: --resume_model以及--wav_path #178

Open
Sunbijuan opened this issue Dec 25, 2024 · 6 comments
Open

error: unrecognized arguments: --resume_model以及--wav_path #178

Sunbijuan opened this issue Dec 25, 2024 · 6 comments

Comments

@Sunbijuan
Copy link

是不是应该将对应的修改成--save_model_path以及--audio_path,
还有对长音频推理的时候报错 File "/usr/local/miniconda3/envs/STT/lib/python3.8/site-packages/yeaudio/utils/utils.py", line 26, in init
sess_opt = SessionOptions()
NameError: name 'SessionOptions' is not defined

@Sunbijuan
Copy link
Author

近几年不不大我用输给女儿压岁劝说亲旁不不不要给女儿压岁钱而改受压岁书,这种预测的结果中的重复字是因为没有集束搜索解码的原因吗,因为我没有执行这一步骤。

@yeyupiaoling
Copy link
Owner

yeyupiaoling commented Dec 25, 2024 via email

@Sunbijuan
Copy link
Author

不是的,应该是模型效果不够好,可以用更大的数据集训练,或者增大模型

那么请问上述的第一个问题怎么解决呢?

@Sunbijuan
Copy link
Author

分别在导出模型、预测音频、预测长音频时执行export_model.py以及infer_path.py时出的错

@yeyupiaoling
Copy link
Owner

yeyupiaoling commented Dec 25, 2024 via email

@Sunbijuan
Copy link
Author

Sunbijuan commented Dec 25, 2024

pip install onnxruntime -U
好的,这是由我的配置文件没有更新造成的结果,运行长音频预测文件之后报错/STT/utils/predict.py", line 96, in predict
audio_ndarray = audio_segment.samples[t['start']: t['end']]
TypeError: slice indices must be integers or None or have an index method,这里应该将索引改成int

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

2 participants