Sagnik Majumder

**Is your feature request related to a problem? Please describe.** A. `mfa align` does not retain the original case of the words in the source TextGrid file. **Describe the solution...

Differentiability of proxy T_60 error

3

Hi Nikhil, Thanks for open-sourcing the code! I have a question regarding the differentiability of the [proxy T_60 error](https://github.com/nikhilsinghmus/image2reverb/blob/f855f49d50e7e0d7830e114cc46d54a711e4d5f2/image2reverb/model.py#L71). Firstly, in the in `compare_t60` in [image2reverb.util](https://github.com/nikhilsinghmus/image2reverb/blob/main/image2reverb/util.py), `detach` is being called...

Hi, do you think the following could be bugs in the lr scheduler? 1. https://github.com/DAMO-NLP-SG/Video-LLaMA/blob/ae12557b8510a7cc94baa3d3aea58ea07f6de76a/video_llama/common/optims.py#L83 should be `step=total_cur_step,`? 2. https://github.com/DAMO-NLP-SG/Video-LLaMA/blob/ae12557b8510a7cc94baa3d3aea58ea07f6de76a/video_llama/common/optims.py#L91 should be `epoch=total_cur_step - self.warmup_steps,`? 3. https://github.com/DAMO-NLP-SG/Video-LLaMA/blob/ae12557b8510a7cc94baa3d3aea58ea07f6de76a/video_llama/common/optims.py#L93 should be `max_epoch=self.max_epoch...

Best SPELL checkpoint for AVA

1

Hi, WIll it be possible to share the best SPELL checkpoint for AVA? Thanks!