issues
search
X-LANCE
/
SLAM-LLM
Speech, Language, Audio, Music Processing with Large Language Model
MIT License
576
stars
52
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
BAT: Learning to Reason about Spatial Sounds Pretrained checkpoints
#121
Utkarsh4430
closed
1 month ago
2
repeated codes
#120
fclearner
closed
3 months ago
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
Learneducn
opened
3 months ago
5
Update QR code
#118
ddlBoJack
closed
4 months ago
0
wechat group is late.
#117
wntg
closed
4 months ago
1
Suggestion on Add mutliple encoder
#116
YGHacker
opened
4 months ago
3
what's the model's input
#115
xiayu-cell
closed
3 months ago
9
Peft LoRA checkpoint will not be saved if DDP enabled and PEFT is enabled
#114
billweasley
closed
4 months ago
1
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
billweasley
closed
1 week ago
7
Update README
#112
ddlBoJack
closed
4 months ago
0
sync
#111
ddlBoJack
closed
4 months ago
0
Mala_ASR projector checkpoint下载权限
#110
FengrunZhang
closed
4 months ago
1
NCCL error when saving with DDP
#109
Vindicator645
opened
4 months ago
2
Request for additional checkpoints of SALM-ASR
#108
jeeyung
closed
2 months ago
1
fix batch_size bug
#107
yanghaha0908
closed
5 months ago
0
Update MaLa-ASR
#106
ddlBoJack
closed
5 months ago
0
sync
#105
ddlBoJack
closed
5 months ago
0
The batch decoding results are inconsistent with the non-batch decoding results
#104
lzl-mt
closed
5 months ago
3
LoRA weights and config are not generated when finetuning the model for AAC task with peft
#103
alifarrokh
closed
5 months ago
4
Ygr pr1
#102
yanghaha0908
closed
5 months ago
0
About FSDP，deepspeech.
#101
Alex-Songs
closed
1 week ago
5
Valid model.pt for ckpt_path -- Is it a open-source model
#100
uni-manjunath-ke
opened
5 months ago
21
Update README
#99
ddlBoJack
closed
5 months ago
0
sync
#98
ddlBoJack
closed
5 months ago
0
Mismatch Issue in the EAT Checkpoint Dictionary for the AAC Inference Task
#97
RookieJunChen
closed
5 months ago
9
fix for issue #93 and a memory hack
#96
zzasdf
closed
5 months ago
0
Query on Metrics Reported in VSR Sub-Project Test Phase
#95
RookieJunChen
closed
5 months ago
2
checkpoint文件下载权限
#94
heihei1204
closed
5 months ago
2
Deepspeed training dataset does not have sampler
#93
lzl-mt
closed
5 months ago
2
FSDP training raise "KeyError: 'ShardingStrategy.NO_SHARD'"
#92
lzl-mt
closed
1 month ago
4
add ckpt_path to config
#91
yanghaha0908
closed
5 months ago
0
Avoid putting a bos token before answer ？
#90
Alex-Songs
closed
5 months ago
6
Update slack and WeChat group
#89
ddlBoJack
closed
5 months ago
0
Is it possible to handle speech front-end signal processing tasks?
#88
zuowanbushiwo
closed
2 months ago
3
Fix a bug on modality mask
#87
ddlBoJack
closed
5 months ago
0
License
#86
fakerybakery
closed
5 months ago
2
Fix modality padding mask bug (Question #82)
#85
zszheng147
closed
5 months ago
0
Update README.md in aac_audiocaps
#84
cwx-worst-one
closed
5 months ago
0
What dataset was used to train/eval the AAC model?
#83
jasonppy
closed
2 months ago
1
[Question] Does it support the combination of hubert-large + linear-projector + tinyllama
#82
VictorChen2012
closed
5 months ago
3
fix git clone '.git' bug
#81
lingfengchencn
closed
5 months ago
2
What data was used to train the pretrained vallex?
#80
EsOff
closed
5 months ago
3
Add MusicFM Support & Fix Bug in mc_musiccaps
#79
juhayna-zh
closed
5 months ago
0
Do you have any plan about Speech to Text or Speech to Speech End2End models?
#78
Irvingao
opened
5 months ago
7
Add Dockerfile & fix README bug
#77
ZhikangNiu
closed
5 months ago
0
Update README
#76
ddlBoJack
closed
6 months ago
0
sync
#75
ddlBoJack
closed
6 months ago
0
Bat
#74
zszheng147
closed
6 months ago
0
Dev mzy
#73
ddlBoJack
closed
6 months ago
0
sync
#72
ddlBoJack
closed
6 months ago
0
Previous
Next