firdota

With use_batch=false, it generates characters one by one while sampling. It seems that only cpu is used and gpu is idle, so the speed of sampling is quite slow. Is...

hello, every one. can i use this model to detect voice in audio with music and noice?

i can run inference.py successfully, but it's a bit slow when predicting one block by one on long audio. How can i predict on batch input? thanks.

unexpected result when loading baidu_en8k

2

my code is as follows: ```python import paddle from paddlespeech.s2t.models.ds2 import DeepSpeech2Model config = './conf/deepspeech2.yaml' model = DeepSpeech2Model.from_config(config) model_param_path = './baidu_en8k/params.pdparams' model_dict = paddle.load(model_param_path) print(model_dict) model.set_state_dict(model_dict) ``` The error when...