doheeeeeee

omegaconf.errors.ConfigAttributeError: Key 'autoregressive' not in 'HubertCtcConfig'

2

## 🐛 Bug Hi, When I tried to load a hubert model, I got this error: ```bash Traceback (most recent call last): File "", line 1, in File "/home/work/workspace/fairseq_origin/fairseq/checkpoint_utils.py", line...

Calculate batch norm statistic loss on parallel training

3

Hello, I have one question about batch norm statistic loss. Consider parallel training. I have 8 GPUs. and 1 gpu can bear 128 batch size. But you know, batch norm...

After 100 epochs training, the model can synthesize natural speech on LibriTTS

68

I trained vall-e on LibriTTS about 100 epochs (took almost 4 days on 8 A100 GPUs) and I obtained plausible synthesized audio. Here is a demo. [1] prompt : [prompt_link](https://drive.google.com/file/d/149pHqb6TZzVwhF1vRN50H8A4AEYShpfp/view?usp=share_link)...

Description: I am experiencing a discrepancy in training loss when using different GPU configurations for training the Zipformer model. Specifically, I observe different training loss patterns when training on a...