Marlowe

请问如何在pipeline中使用外挂的transformer-lm做shallow fusion

1

RT 请问如何在pipeline中使用外挂的transformer-lm做shallow fusion

Now I'm using code as follow,  Server side log is  How to pass request_id when using post

Does the vad perform better with a linear donoiser than only using Silero ?

may ask if a sketch of hyperparameters can be shown.

i've done some experiments on the best-rq model, including ssl pretraining and supervised finetuning both on wenetspeech dataset. luckily, the pretraining is stable and with # of codebook equals to...