ictnlp/LLaMA-Omni

Issues

• 模型训练loss变化是什么样的？

  #50 opened 22 days ago by shihuai
  13

• 建了一个语音AI微信群复现这个论文，有兴趣的一起讨论。 Chat Group to discuss the implementation of this paper

  #46 opened a month ago by tianke0711
  5

• Error of Gradio Demo

  #42 opened a month ago by zchoi
  2

• Error while inference

  #49 opened a month ago by ZhengRachel
  1

• 请问，会开源训练和微调的方法吗

  #41 opened a month ago by SevenMpp
  2

• Automatically exit while Launch a model worker.

  #31 opened 2 months ago by JV-X
  2

• Use Gradio WebRTC component for better conversational demo

  #48 opened a month ago by freddyaboulton
  0

• 中文支持

  #34 opened 2 months ago by JunweiLiang
  2

• about Gradio Demo

  #47 opened a month ago by mysxs
  0

• 能否支持ollama

  #45 opened a month ago by chaoqunxie
  0

• 内存占用

  #44 opened a month ago by mmlingyu
  0

• support to replace audio encoder(whisper) in llama omni

  #43 opened a month ago by satheeshkola-532
  0

• sample dataset of InstructS2S-200K dataset

  #39 opened a month ago by tianke0711
  2

• about train code

  #1 opened 2 months ago by ali762111
  10

• '_flash_supports_window_size' is not defined

  #32 opened 2 months ago by boji123
  4

• 报错求助：找不到config.json文件

  #40 opened a month ago by Enermy
  2

• [Question] About offset in datasets/preprocess.py

  #38 opened a month ago by world1tree
  0

• About your gradio issue

  #37 opened a month ago by thiswillbeyourgithub
  0

• [FYI] I made a demo request at livekits's agents to showcase Llama-Omni

  #36 opened 2 months ago by thiswillbeyourgithub
  0

• Visit [http://localhost:8000/]

  #35 opened 2 months ago by yywhsgnd
  0

• point 1 download from hugginface is not clear

  #33 opened 2 months ago by mirecta
  1

• Are there any multilingual unit-based HiFi-GAN vocoders?

  #30 opened 2 months ago by pilkyu95
  0

• RuntimeError: FlashAttention only supports Ampere GPUs or newer.

  #29 opened 2 months ago by haoyz
  0

• Where do the models go?

  #18 opened 2 months ago by SoftologyPro
  7

• Can you release the codes for getting discrete units?

  #28 opened 2 months ago by isruihu
  0

• No microphone found

  #27 opened 2 months ago by AlgoJay1991
  1

• Streaming input ws demo

  #26 opened 2 months ago by pulpoff
  0

• About gradio_web_server | Models: []

  #25 opened 2 months ago by ZxnSnowy
  1

• Evaluation scripts?

  #24 opened 2 months ago by Btlmd
  0

• Open-source test dataset(InstructS2S-Eval)?

  #23 opened 2 months ago by sphmel
  0

• InstructS2S-200K

  #21 opened 2 months ago by zhentingqi
  0

• Fail to open gradio_web_server with unexpetced urllib3 error

  #20 opened 2 months ago by irrikrlla
  0

• macOS Apple Silicon (M1) support?

  #19 opened 2 months ago by yukiarimo
  0

• What languages are supported?

  #16 opened 2 months ago by lostmsu
  0

• require for training code

  #14 opened 2 months ago by CrazyBoyM
  2

• Modelling of the prosody

  #13 opened 2 months ago by Ming-er
  1

• How is the recognition effect on Chinese?

  #8 opened 2 months ago by Smashhhhhhhhhh
  1

• How would we use the pretrained model in our own python code?

  #7 opened 2 months ago by PhilipAmadasun
  1

• What need to be change if generation added a new modal

  #5 opened 2 months ago by MonolithFoundation
  1

• do you support audio input of more than 30s

  #4 opened 2 months ago by choyakawa
  1

• question about code

  #3 opened 2 months ago by UestcJay
  3

• Getting this model error, when launching a model worker

  #10 opened 2 months ago by hp2413
  5

• Can we convert this into .GGUF format without breaking?

  #9 opened 2 months ago by Kingbadger3d
  1

• Error when starting model_work

  #11 opened 2 months ago by Jun-Howie
  2

• 请问下hubert具体用的哪个模型

  #6 opened 2 months ago by yuguochencuc
  0

• Error loading llama3 tokenizer

  #2 opened 2 months ago by hexastrayer
  1