ngocpham97

Cannot apply data augmentation

4

**Describe the bug** Hello, I want to agmentation data training and follow the instructions in [training_a_model.ipynb](https://github.com/pyannote/pyannote-audio/blob/develop/tutorials/training_a_model.ipynb) but doesn't work. **To Reproduce** **** ```bash import os os.environ["PYANNOTE_DATABASE_CONFIG"] = '/home/ngocpt/Desktop/AMI-diarization-setup/pyannote/database.yml' os.environ["CUDA_VISIBLE_DEVICES"] =...

Generate encoder.json for other languages

2

Hi all, Please tell me the way to generate encoder.json for other languages French, Spanish... I tried to create a encoder.json but it's not exactly the same example of GPT...

Batch size in training GPT_2

1

I have a question about batch size in [train.py](https://github.com/nshepperd/gpt-2/blob/finetuning/train.py). I wonder batch_size =1 meaning 1 token will pass to model or 1024 token. Anyone explain help me ? Thank a...