KinamSalad

## Title - Inference code for RNN-T ## Description 안녕하세요. 먼저 음성인식에 관심이 많아 둘러보던 중 좋은오픈소스를 제공해주셔서 감사합니다. ./bin/inference.py 코드를 보면 지원하는모델이 SpeechTransformer, Jasper, DeepSpeech2, ListenAttendSpell, Conformer, 이렇게 5개...

Thank you for your contribution! I have referenced your M2Voc implementation to implement Voice cloning task using adain-vc and speaker embedding options. I was thinking of a scenario where voice...

[Question] Do I need to install nvidia-docker to train a new bilm?

1

In README.md, there is about installing nvidia-docker. However, only 'sudo nvidia-docker run -t allennlp/bilm-tf:training-gpu', it doesn't work. Is there any problem training bilm even if I do not install it?...

question about inference

1

As far as I read the paper, we need a total of 3 data for the inference. I understood that we need three types: voice data for prompt, text data...

I have a simple question for generating samples...

1

I am getting a lot of help from this project. Thank you! I have one question. Is the method for generating samples(ex images) with models trained using the FM framework...