-
Notifications
You must be signed in to change notification settings - Fork 124
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
onnx 形式的预训练模型固定了帧长是有什么特别的考虑吗? #380
Comments
非常感谢对这个项目的关注! 导出onnx支持动态维度,如下: wespeaker/wespeaker/bin/export_onnx.py Lines 84 to 88 in e9bbf73
|
|
你好,预训练模型下载页面:https://github.com/wenet-e2e/wespeaker/blob/master/docs/pretrained.md ,里边提供了pytorch模型(包含config文件)和onnx模型,其中onnx模型是动态维度。 |
抱歉,这个onnx导出的有问题,变成了固定长度。 我们会重新导出并上传。 另外,你也可以利用pt模型,重新导出onnx。 https://wenet.org.cn/downloads?models=wespeaker&version=voxblink2_samresnet34.zip 导出命令如下: python wespeaker/bin/export_onnx.py --config voxblink2_samresnet34/config.yaml --checkpoint voxblink2_samresnet34/avg_model.pt --output_model voxblink2_samresnet34/final.onnx |
谢谢您的建议,按要求重新导出动态帧数维的模型后,想对这个模型做一些finetune,但是没有在预训练模型的配置文件中https://wenet.org.cn/downloads?models=wespeaker&version=voxblink2_samresnet34.zip 发现optimizer和学习率变化策略的配置,请问有更详细的配置文件有说明这两点吗? |
目前没有voxblink2的recipe,请关注这个issue #365 |
首先非常感谢如此优秀的项目!
请教一下,
The text was updated successfully, but these errors were encountered: