QwenLM/Qwen-Audio

Issues

• qwen-audio和lauragpt的相关问题讨论

  #62 opened 12 days ago by wwfcnu
  0

• qwen-audio处理长音频（五分钟左右）结果只输出前面20秒的文本是什么原因？

  #34 opened 5 months ago by Wolverhampton0
  7

• 关于训练数据中不同语言分布情况

  #61 opened 16 days ago by shihuai
  0

• 本地部署需要多少算力‘’

  #60 opened 18 days ago by Gpwner
  0

• 有量化后的版本吗

  #57 opened 2 months ago by whk6688
  1

• 微信群满了

  #59 opened a month ago by adeamoy
  0

• chat模型，相同文本问题，不同音频，每次ASR返回结果都一样

  #58 opened a month ago by LiXuanming
  0

• 有onnx格式的模型吗

  #56 opened 2 months ago by whk6688
  1

• use of whisper audio encoder

  #33 opened 5 months ago by x75
  4

• 如何一个音频中分辨多人对话

  #16 opened 6 months ago by qixing-ai
  4

• how can i chat in demo

  #55 opened 2 months ago by lzl-mt
  0

• 是不支持中文提示词吗

  #53 opened 2 months ago by GioGioBond
  0

• 复现实验结果有差距

  #26 opened 5 months ago by roydcai
  2

• 请问是否支持 VLLM 等api部署

  #52 opened 2 months ago by su-zelong
  1

• 训练超参数相关问题

  #51 opened 2 months ago by jwang1993
  0

• 微信群满了

  #49 opened 3 months ago by zhangfan-algo
  0

• allow_pickle=False

  #48 opened 3 months ago by Leejl0011
  2

• wechat full

  #36 opened 4 months ago by lixf071213
  4

• 支持本地api调用吗？

  #47 opened 3 months ago by dfengpo
  0

• 请问Qwen-audio的训练速度，阿里官方达到多少？

  #46 opened 3 months ago by luboxu
  0

• Mac M1 runs painfully slow

  #8 opened 6 months ago by zfarrell13
  3

• 关于粤语支持

  #45 opened 3 months ago by lq0104
  0

• qwen-audio 微调

  #38 opened 4 months ago by wjfwjfwjf
  2

• Few-shot Examples

  #44 opened 3 months ago by aqibsaeed
  0

• 请问prompt要怎么写才能获得单个task的信息或者想要的task的信息？

  #32 opened 3 months ago by wjyfelicity
  2

• 确定给的本地模型没问题吗

  #41 opened 4 months ago by wukongbuku
  0

• Infer eval_audio目录下的multi-task eval脚本，发现模型针对batch 解码性能衰减很快，请问是训练时候attention mask 或者tokenizer padding部分处理有问题吗？

  #43 opened 4 months ago by yangjiabupt
  0

• 报错，requests.exceptions.HTTPError: Response details: 404 page not found, Request id: ab8a478639c847c6bbb41438e4d8606e

  #42 opened 4 months ago by wukongbuku
  0

• 可以问一下微调代码的公开的计划嘛？预计什么时候能开源呢？非常感谢！！！

  #40 opened 4 months ago by icemoon-creative
  0

• End of sentence id

  #35 opened 4 months ago by marcoyang1998
  0

• 关于Output Instruction的问题

  #31 opened 5 months ago by jwang1993
  1

• 哪里可以进行指令微调呢？什么时候开放有具体排期吗？

  #21 opened 6 months ago by David19970306
  1

• 是否考虑加入whisper.cpp的支持？

  #30 opened 5 months ago by dyt06
  0

• 关于训练数据问题

  #29 opened 5 months ago by qy-NJU
  0

• 问题请教，关于gradio的问题，我在本地部署好了，想在手机上使用，显示找不到麦克风

  #28 opened 5 months ago by cl886699
  0

• Tokenizer vocab size mismatch model vocab size

  #27 opened 5 months ago by yangjiabupt
  0

• SFT use lora? or finetune all parameters?

  #24 opened 5 months ago by yangjiabupt
  2

• The number of people in the WeChat group is full. Can you update the WeChat group QR code?

  #25 opened 5 months ago by rookie0607
  1

• Qwen-Audio给的示例Demo输入本地音频文件没有跑出转写的文本结果？ 能提供相应的例子吗

  #23 opened 6 months ago by apple2333cream
  3

• How to predict the task tag in finetuning stage?

  #17 opened 5 months ago by jodiesue
  0

• Performance degradation on known langauges of whisper

  #13 opened 6 months ago by akashicMarga
  1

• 可以给一些训练数据示例吗？

  #18 opened 6 months ago by Wyswyss
  1

• ground

  #22 opened 6 months ago by wntg
  0

• 关于Clotho AQA数据集？

  #19 opened 6 months ago by liziming5353
  0

• 12月7号有什么更新了吗？

  #12 opened 6 months ago by ahban
  1

• What is EvaluationTokenizer?

  #11 opened 6 months ago by EmbraceAir
  3

• 怎样可以让asr的输出带标点呢

  #6 opened 6 months ago by liuxq
  1

• 长音频如何处理？长音频调用只输出一半对应的文本

  #10 opened 6 months ago by xxm1668
  2

• 训练问题

  #7 opened 6 months ago by Mddct
  1

• low gender classification accuracy

  #9 opened 6 months ago by yl4579
  0