Rajeev

> We do not have so many requests, actually. We also have some internal discussions, but there are a lot of alternatives for the faster (lightweight) encoder and Squeezeformer does...

@sw005320 Any plans for adding Squeezeformer to ESPNet?

> And please note that enabling KV cache never affects your model outputs. @WoosukKwon I'm getting different output almost 10-15% of the time when the KV cache is enabled with...

> For me, it happens after several epochs. 16 to be exact. > > However, this I am seeing in training PARSeq on an Indian language (Manipuri, another subtype of...

> Hi @rajeevbaalwan I would like to confirm some points: > > * Would you tell me which encoder you use in your model? > * Did you observe any...

@Masao-Someki I have tried with conformer encoder based ASR model also but getting same error. ``` 2023-10-08 23:12:29.048358681 [E:onnxruntime:, sequential_executor.cc:339 Execute] Non-zero status code returned while running Add node. Name:'/encoders/encoders.0/self_attn/Add_5'...

@Masao-Someki Thanks it worked for me. But the exported ONNX models do not work with batch input, right ? It only works for a single audio clip.

@Masao-Someki Thanks for the reply. I have already made the changes in the dynamic axes but this only won't solve the problem as the forward function only takes feats and...

@Masao-Someki You are absolutely right ONNX exported do not give huge speed up for large batch sizes but for small batch size like 4, 8, etc it is better than...

@Masao-Someki is ESPnetLanguageModel is support in ONNX?