We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
#1058 adds updated zipformer.
However, we only have torch.jit.script() support for it at present.
torch.jit.script()
We need to export it to onnx so that it can be used in sherpa-onnx
Help from the community is highly appreciated.
We need to support both streaming and non-streaming versions. Specifically, for the streaming version, we need to add the following files:
Please also have a look at https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/zipformer/export.py
For the non-streaming version, we need to do similar things.
The non-streaming version is easier since it does not need to consider the intermediate states of the model.
The text was updated successfully, but these errors were encountered:
I wanna have a try :) Hope I could finish this task in half a month
Sorry, something went wrong.
I wanna have a try :)
Hope I could finish this task in half a month
Thanks!
@kakashidan Thanks for trying. I hope you can complete the task successfully and earlier. All the best.
No branches or pull requests
#1058 adds updated zipformer.
However, we only have
torch.jit.script()
support for it at present.We need to export it to onnx so that it can be used in sherpa-onnx
Help from the community is highly appreciated.
The task
We need to support both streaming and non-streaming versions.
Specifically, for the streaming version, we need to add the following files:
Please also have a look at https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/zipformer/export.py
For the non-streaming version, we need to do similar things.
The non-streaming version is easier since it does not need to consider the intermediate states of the model.
TODO
The text was updated successfully, but these errors were encountered: