-
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
Efficient Conformer implementation #1636
Conversation
|
@xingchensong 感谢建议,cache shape问题我再具体看下。 |
…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
THX! |
@zwglory 請問有預訓練模型能夠下載測試嗎? 謝謝。 |
@KakayaLin 可以的,后面我们上传后在这里同步。 |
@zwglory 不好意思, 請問上傳有更新進度嗎? 謝謝。 |
@KakayaLin AISHELL-1 的模型链接如下,后续会更新在相关README中 |
謝謝!! |
Can we incorporate LM in efficient conformer? |
@dipeshhoncho07 yes, efficient conformer support LM in runtime. |
Hi, @zwglory, do you have an update on onnx cpu export? Thanks. |
You can refer to this description to try it out, and we will follow up on this part of the feature when we have time. |
This PR is about our implementation of Efficient Conformer for WeNet encoder structure and runtime.
In 58.Com Inc, using Efficient Conformer can reduce CER by 6% relative to Conformer and a 10% increase in inference speed (CPU JIT runtime). Combined with int8 quantization, the inference speed can be improved by 50~70%. More detail of our work: https://mp.weixin.qq.com/s/7T1gnNrVmKIDvQ03etltGQ
Added features
StrideConformerEncoderLayer
for "Progressive Downsampling to the Conformer encoder"GroupedRelPositionMultiHeadedAttention
for "Grouped Attention"Conv2dSubsampling2
for 1/2 Convolution Downsamplingforward_chunk
andforward_chunk_by_chunk
inwenet/efficient_conformer/encoder.py
TorchAsrModelEfficient
inruntime/core/decoder
for Progressive Downsamplingtrain_u2++_efficonformer_v1.yaml
for our online deploymenttrain_u2++_efficonformer_v2.yaml
for Original paperDevelopers
TODO