bytedance/SALMONN

Issues

• a Few questions...

  #46 opened a month ago by SoshyHayami
  2

• About distributed training

  #44 opened a month ago by ucasyouzhao1987
  3

• 不支持tts任务吗，以后有没有计划推出

  #45 opened a month ago by ZaymeShaw
  0

• beats下载链接失效

  #43 opened a month ago by Daisyqk
  1

• Request for Task Level 3 Training Data

  #42 opened 2 months ago by EnisBerk
  0

• 第一阶段speech Qformer的训练和模型

  #40 opened 2 months ago by ASolitaryMan
  1

• inference cuda OOM on smaller GPU

  #41 opened 2 months ago by rrscholarship
  0

• SALMONN 7B 使用的Vicuna版本？

  #39 opened 3 months ago by CleyLyChen
  1

• Cannot download Fine-tuned BEATs_iter3+ (AS2M) (cpt2).

  #38 opened 3 months ago by KuofengGao
  2

• Some questions about this project hoping for your further answers.

  #35 opened 3 months ago by StupidDebugger
  2

• 请问需要下载哪个版本的 whisper-large-v2?

  #34 opened 3 months ago by yt605155624
  1

• config 里面应该再加个 bert config path

  #36 opened 3 months ago by yt605155624
  1

• 使用 7B 模型，有的时候无法生成 audio caption

  #37 opened 3 months ago by yt605155624
  0

• 请问是否在 AAC 任务上和 Qwne-Audio 比较过

  #33 opened 3 months ago by yt605155624
  0

• when can we get the codes for trainning?

  #9 opened 3 months ago by David19970306
  4

• when can we finetune the model with vicuna7B?

  #31 opened 3 months ago by David19970306
  1

• the instruction tuning stage

  #32 opened 6 months ago by yttas
  2

• How to adopt a speaker verification task?

  #30 opened 6 months ago by jodiesue
  1

• 中文能力如何？

  #29 opened 7 months ago by xxm1668
  2

• 什么时候可以得到vicuna7B的模型呢？

  #27 opened 8 months ago by David19970306
  1

• Typo error in README.md

  #23 opened 8 months ago by manavb2214
  0

• Adding Contributors section to the readme.md !

  #17 opened 8 months ago by mohitd404
  2

• Adding Code of conduct to repo !

  #16 opened 8 months ago by mohitd404
  1

• Is the paper published?

  #4 opened 8 months ago by PanQiWei
  2

• The role of prompt_pattern parameter

  #8 opened 9 months ago by 980202006
  2

• Where is the source code, only a bunch of raw audio files?

  #5 opened 9 months ago by ridingmower
  3

• 对中文电话录音识别的支持好像不太行？

  #1 opened 9 months ago by magicleo
  2

• SALMONN模型支持多大的语音文件呢？

  #2 opened 9 months ago by Dinxin
  1

• Any more information about audio text aligner

  #6 opened 9 months ago by YimengZhu
  3

• 模型会考虑开源吗？

  #3 opened 9 months ago by Dinxin
  4

• Great work! Can I know when the implementation and code will be available? Thanks

  #7 opened 9 months ago by WilTay1
  1