Reduce model initialization time for online speech recognition #215
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thanks! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Implemented
model_typeparameter for online transducer models as suggested by @csukuangfj in this issue and based largely on this PR.Add a new argument
--model-typeso that it only needs to load the model once.Otherwise, it needs to load the model twice, where the first loading is to determine the model type.
I have tested csukuangfj/sherpa-onnx-streaming-zipformer-en-2023-06-26 via the Python API on Linux, by specifying
model_type="zipformer2"during initialization.The model loading time is reduced from ~6 seconds to ~3 seconds for the fp32 model; while for the int8 model the time is reduced from 4.4 seconds to 2.1 seconds.