leo-speech

> It's hard to say what may be going wrong just based on WER. Did you change any hyperparameters? Did you look at the intermediate results (e.g. from GMM decoding)...

> I think so, yeah. The WER without RNNLM rescoring should be closer to 46%. See this at the top of the run_cnn_tdnn_1b.sh: %WER 46.07 [ 27124 / 58881, 2905...

> You can try tuning some of the hyperparameters (esp. learning rate) since you changed the number of training jobs (GPUs). But I think at this point you're close enough...

> We have update the training with a bugfix of OOM. Please update funasr and try it again. Thanks for the updata,the paraformer_streaming is already for normal training; For this...

> Please update torch Thanks again!