QwenLM/Qwen-Audio
The official repo of Qwen-Audio (通义千问-Audio) chat & pretrained large audio language model proposed by Alibaba Cloud.
PythonNOASSERTION
Issues
- 0
qwen-audio和lauragpt的相关问题讨论
#62 opened by wwfcnu - 7
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 by Wolverhampton0 - 0
关于训练数据中不同语言分布情况
#61 opened by shihuai - 0
本地部署需要多少算力‘’
#60 opened by Gpwner - 1
- 0
- 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 by LiXuanming - 1
有onnx格式的模型吗
#56 opened by whk6688 - 4
use of whisper audio encoder
#33 opened by x75 - 4
如何一个音频中分辨多人对话
#16 opened by qixing-ai - 0
how can i chat in demo
#55 opened by lzl-mt - 0
是不支持中文提示词吗
#53 opened by GioGioBond - 2
- 1
请问是否支持 VLLM 等api部署
#52 opened by su-zelong - 0
- 0
微信群满了
#49 opened by zhangfan-algo - 2
allow_pickle=False
#48 opened by Leejl0011 - 4
wechat full
#36 opened by lixf071213 - 0
支持本地api调用吗?
#47 opened by dfengpo - 0
请问Qwen-audio的训练速度,阿里官方达到多少?
#46 opened by luboxu - 3
Mac M1 runs painfully slow
#8 opened by zfarrell13 - 0
- 2
qwen-audio 微调
#38 opened by wjfwjfwjf - 0
Few-shot Examples
#44 opened by aqibsaeed - 2
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 by wjyfelicity - 0
确定给的本地模型没问题吗
#41 opened 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 by yangjiabupt - 0
报错,requests.exceptions.HTTPError: Response details: 404 page not found, Request id: ab8a478639c847c6bbb41438e4d8606e
#42 opened 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 by icemoon-creative - 0
End of sentence id
#35 opened by marcoyang1998 - 1
关于Output Instruction的问题
#31 opened 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 by David19970306 - 0
是否考虑加入whisper.cpp的支持?
#30 opened by dyt06 - 0
- 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 by cl886699 - 0
- 2
SFT use lora? or finetune all parameters?
#24 opened by yangjiabupt - 1
The number of people in the WeChat group is full. Can you update the WeChat group QR code?
#25 opened by rookie0607 - 3
- 0
How to predict the task tag in finetuning stage?
#17 opened by jodiesue - 1
- 1
可以给一些训练数据示例吗?
#18 opened by Wyswyss - 0
- 0
关于Clotho AQA数据集?
#19 opened by liziming5353 - 1
12月7号有什么更新了吗?
#12 opened by ahban - 3
What is EvaluationTokenizer?
#11 opened by EmbraceAir - 1
怎样可以让asr的输出带标点呢
#6 opened by liuxq - 2
长音频如何处理?长音频调用只输出一半对应的文本
#10 opened by xxm1668 - 1
- 0
low gender classification accuracy
#9 opened by yl4579