Skip to content

Issues: X-LANCE/SLAM-LLM

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

16 Open 27 Closed
16 Open 27 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

How to reproduce asr_librispeech?
#157 opened Oct 17, 2024 by IQ17
Killed when using long list of training data, How to solve it ?
#154 opened Oct 15, 2024 by housebaby
1 of 2 tasks
Resume training from checkpoint with same hyperparameter
#146 opened Oct 11, 2024 by Amg9794
loss value and acc seems wrong when after setting gradient_accumulate_step>1 in Deepspeed training
#144 opened Oct 10, 2024 by Vindicator645
1 of 2 tasks
1
The answer is given to SLAM as input during training, wouldn't that make the model cheat?
#132 opened Sep 19, 2024 by Yahya-Saleh
1 of 2 tasks
1
Data Form of the MaLa-ASR
#130 opened Aug 28, 2024 by zsLin177
1 of 2 tasks
@yanghaha0908
2
repetition 问题记录
#128 opened Aug 6, 2024 by fclearner
question about q-former
#127 opened Aug 2, 2024 by peggyxpxu
@cwx-worst-one
4
data filter mechanism
#126 opened Aug 1, 2024 by fclearner
2
Currently we use a single GPU for decoding. We have the plan to support Multi-GPU decoding and the script is on the way.
#119 opened Jul 20, 2024 by Learneducn
5
Suggestion on Add mutliple encoder
#116 opened Jul 18, 2024 by YGHacker
3
Training suggestion...? For reducing LLM to produce like "I am sorry, I'm an AI language model and I don't have abilty to transcribe speech to text"
#113 opened Jul 11, 2024 by billweasley
1 of 2 tasks
7
NCCL error when saving with DDP
#109 opened Jul 1, 2024 by Vindicator645
1 of 2 tasks
2
About FSDP，deepspeech.
#101 opened Jun 6, 2024 by Alex-Songs
4
Valid model.pt for ckpt_path -- Is it a open-source model
#100 opened Jun 6, 2024 by uni-manjunath-ke
1 of 2 tasks
21
Do you have any plan about Speech to Text or Speech to Speech End2End models?
#78 opened May 21, 2024 by Irvingao
6
ProTip! Follow long discussions with comments:>50.