icefall
icefall copied to clipboard
k2-fsa
make it's ok when using lm rescoring with transformer lm
I am getting nan outputs from the encoder of pruned transducer streaming model. tensor([[[nan, nan, nan, ..., nan, nan, nan], [nan, nan, nan, ..., nan, nan, nan], [nan, nan, nan,...
Hello guys, I am working with my inhouse data, which contains 5000 hours of noisy audio. I found that applying of Chat GPT as error correction post processing in some...
Can you explain why you do not normalize transducer loss. And if I increase batch size, it will make gradients to be larger, can model converges.
How to fine-tune the zipformer-s model on aishell dataset, is there a pretrained model of zipformer-s on wenetspeech data?
Add code for streaming version of ReazonSpeech. We are currently still evaluating the accuracy of these models so the results section is blank in RESULTS.md file, but we will add...
This PR adds a recipe of training Zipformer with Adam optimizer. The goal is to help people integrate Zipformer encoder into their own models trained with Adam optimizer. To make...
Hi, just have a question regarding the training speed using different GPUs. We have tested the training speed with A100 and H100 (single GPU for test) using the same training...
Hi We're looking to finetune a zipformer streaming model on our custom dataset of around 100 hours that we are about to get manually annotated. The speech in that dataset...
