-
Notifications
You must be signed in to change notification settings - Fork 1.1k
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
[runtime/gpu] Add GPU Hotwords #1860
Conversation
…e changes. Completed the casual and non-casual convolution model tests for the EfficientConformer, as well as JIT runtime tests. Modified yaml files for Aishell-1
…, and fix bug of V2 streaming decode
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice work. Would you mind merging the hotwords directory such that it would become a default settings?
- merge model_repo_hotwords with regular model repos.
- merge hotwords/readme.md into gpu/readme.md using a new section ### hotwords
- hotwords.yaml could be under model_repo_x/scoring/, however, default hotwords_path is None like lm_path. In readme.md, set it to ./model_repo_x/scoring/hotwords.yaml to enable hotwords. e.g. sed -i /hotwords_path/xxx/ config_template.pbtxt
- In this way, we may don't need convert_start_x.sh
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Also, it would be nice if you could upload the script to comput f1 to scripts/.
No problem, we are going to merge the hotwords directory and upload the f1 code. |
…del_repo_x; add hotwords evaluation script; update readme.
In the latest commit, we
Please help us review this pr when you are free. Thanks♪(・ω・)ノ |
Many thanks. |
Support hotword boosting for offline or streaming WeNet ASR models on GPUs.
For more information regarding the
ctc_decoder
, please refer to:Slyne/ctc_decoder#11Here are our test results:
Tested ENV
Hotwords file: https://huggingface.co/58AILab/wenet_u2pp_aishell1_with_hotwords/tree/main/models
AISHELL-1 Test dataset
AISHELL-1 hostwords sub-testsets
Decoding result
佟健
Refer to more results: https://huggingface.co/58AILab/wenet_u2pp_aishell1_with_hotwords/tree/main/results
Mainly developed by @FieldsMedal