Sangchun Ha
Sangchun Ha
Hello, @OleguerCanal Currently we are not providing it. Also I know that E2E timestamps (including CTC decoder) perform relatively poorly, How was your experience using CTCBeamDecoder?
Could you show me training scripts?
Thanks. I'll check it out as soon as possible.
@YuXI-Chn I think I missed it. Thanks for letting me know. I'll fix it as soon as possible.
안녕하세요 @sonofbit ! 현재 구현되어있는 inference 과정은 없고, 빠른 시일내에 추가하도록 하겠습니다. 감사합니다.
Hello @yunigma ! I think there is an error using the `cross_entropy` criterion for the transducer model. Would you like to use the criterion as `transducer`?
Well, Would you like to experiment by modifying the gradient accumulation parameter? [[link]](https://github.com/openspeech-team/openspeech/blob/main/openspeech/dataclass/configurations.py#L184-L186) I think your batch size is 16, so it might be a good idea to set `accumulate_grad_batches`...
@yunigma I'll have to do some more testing. I'm so sorry... 😭
Prediction is not supported yet. We will add more later.
@wuxiuzhi738 I'm so sorry for late reply. This is not a language model, it is a script that trains the conformer encoder and lstm decoder together.