macsim

## ❓ Questions and Help #### What is your question? Hi i'm trying finetuning wav2vec2 and using wav2vec_seq2seq transformer decoder but because one line of code section , train is...

sdpa about

3

I'm curious about performance of flash attention. And I saw the 5dfc9dcbd4f6fa050baa297b9d0fe2e38a4aaa0b (commit id), We can use a sdpa for conformer now. Is it only available cpu-mode? If it works...

Whisper finetune

1

Hi I'm trying to train whisper fine-tune with multi-gpu and I don't know what `RANK` to set I just set `WORLD_SIZE` is numer of gpu and `MASTER_ADDR` is localhost, `MASTER_PORT`...

WhisperPositionalEmbedding

1

Hi there I'm trying to fintune whisper model but there is a problem that decoder positional embedding size(small model case is [448,768]) should not bigger than 448(first dim) I have...

converting to triton model

1

Hi, Thanks to this repository, I made the onnx model what I trained and I curious about the model is on cpu or gpu Now I'm trying to convert espnet...

Hi, I'm execute onnx model usefully thanks to export_onnx_cpu or gpu python file. But Sometime I face this situation that model output differently between CPU onnx model and GPU onnx...