Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / QwenLM/Qwen-Audio issues and pull requests

#76 - Compute Requirements and Execution Time

Issue - State: open - Opened by Sedherthe 2 months ago - 1 comment

#74 - 请问有计划接入TTS模块吗

Issue - State: open - Opened by CD678 3 months ago

#72 - 在rustc 1.80.1编译tokenizers v0.13.3报错

Issue - State: open - Opened by martinzh717 3 months ago

#71 - Get token in predict ?

Issue - State: closed - Opened by CungNguyenHuy 4 months ago

#70 - cuda版本错误

Issue - State: open - Opened by ZHUHF123 4 months ago

#69 - 微信群满了

Issue - State: open - Opened by qgzang 5 months ago - 6 comments

#68 - Problems for speech translation tasks

Issue - State: open - Opened by ShoutaoGuo 5 months ago

#67 - Update TUTORIAL.md

Pull Request - State: open - Opened by pranit-gandhi 5 months ago

#66 - Input multiple audio file to audio encoder

Issue - State: open - Opened by DevKiHyun 5 months ago

#65 - Clarification | Datasets used for training.

Issue - State: open - Opened by Iosifts 5 months ago - 2 comments

#64 - Evaluation script for VSC task seems not correct

Issue - State: open - Opened by mlxu995 5 months ago

#63 - 能否获得hidden表示？

Issue - State: open - Opened by Kristopher-Chen 5 months ago - 1 comment

#62 - qwen-audio和lauragpt的相关问题讨论

Issue - State: open - Opened by wwfcnu 6 months ago

#61 - 关于训练数据中不同语言分布情况

Issue - State: open - Opened by shihuai 6 months ago

#60 - 本地部署需要多少算力‘’

Issue - State: open - Opened by Gpwner 6 months ago

#59 - 微信群满了

Issue - State: open - Opened by adeamoy 7 months ago - 1 comment

#57 - 有量化后的版本吗

Issue - State: open - Opened by whk6688 7 months ago - 1 comment

#56 - 有onnx格式的模型吗

Issue - State: open - Opened by whk6688 7 months ago - 2 comments

#55 - how can i chat in demo

Issue - State: open - Opened by lzl-mt 7 months ago

#54 - fix: fixed a typo in README.md

Pull Request - State: open - Opened by m2moiz 7 months ago

#53 - 是不支持中文提示词吗

Issue - State: open - Opened by GioGioBond 7 months ago - 1 comment

#52 - 请问是否支持 VLLM 等api部署

Issue - State: open - Opened by su-zelong 8 months ago - 1 comment

#51 - 训练超参数相关问题

Issue - State: open - Opened by jwang1993 8 months ago - 1 comment

#49 - 微信群满了

Issue - State: open - Opened by zhangfan-algo 8 months ago

#48 - allow_pickle=False

Issue - State: open - Opened by Leejl0011 8 months ago - 2 comments

#47 - 支持本地api调用吗？

Issue - State: open - Opened by dfengpo 9 months ago

#46 - 请问Qwen-audio的训练速度，阿里官方达到多少？

Issue - State: open - Opened by luboxu 9 months ago - 1 comment

#45 - 关于粤语支持

Issue - State: open - Opened by lq0104 9 months ago - 1 comment

#44 - Few-shot Examples

Issue - State: closed - Opened by aqibsaeed 9 months ago

#41 - 确定给的本地模型没问题吗

Issue - State: closed - Opened by wukongbuku 9 months ago

#39 - Fix README.md typo

Pull Request - State: open - Opened by tianyu-z 10 months ago

#38 - qwen-audio 微调

Issue - State: closed - Opened by wjfwjfwjf 10 months ago - 2 comments

#37 - Update README.md

Pull Request - State: open - Opened by huangxu1991 10 months ago

#36 - wechat full

Issue - State: open - Opened by lixf071213 10 months ago - 4 comments

#35 - End of sentence id

Issue - State: open - Opened by marcoyang1998 10 months ago

#33 - use of whisper audio encoder

Issue - State: open - Opened by x75 11 months ago - 4 comments

#31 - 关于Output Instruction的问题

Issue - State: open - Opened by jwang1993 11 months ago - 1 comment

#30 - 是否考虑加入whisper.cpp的支持？

Issue - State: open - Opened by dyt06 11 months ago

#29 - 关于训练数据问题

Issue - State: open - Opened by qy-NJU 11 months ago

#27 - Tokenizer vocab size mismatch model vocab size

Issue - State: open - Opened by yangjiabupt 11 months ago

#26 - 复现实验结果有差距

Issue - State: open - Opened by roydcai 11 months ago - 2 comments

#24 - SFT use lora? or finetune all parameters?

Issue - State: open - Opened by yangjiabupt 11 months ago - 2 comments

#22 - ground

Issue - State: open - Opened by wntg 11 months ago

#19 - 关于Clotho AQA数据集？

Issue - State: open - Opened by liziming5353 12 months ago

#18 - 可以给一些训练数据示例吗？

Issue - State: open - Opened by Wyswyss 12 months ago - 1 comment

#17 - How to predict the task tag in finetuning stage?

Issue - State: closed - Opened by jodiesue 12 months ago

#16 - 如何一个音频中分辨多人对话

Issue - State: open - Opened by qixing-ai 12 months ago - 6 comments

#15 - feat: add pr template for other contributors

Pull Request - State: open - Opened by ve-varun-sharma 12 months ago

#13 - Performance degradation on known langauges of whisper

Issue - State: open - Opened by akashicMarga 12 months ago - 1 comment

#12 - 12月7号有什么更新了吗？

Issue - State: closed - Opened by ahban 12 months ago - 1 comment

#11 - What is EvaluationTokenizer?

Issue - State: closed - Opened by EmbraceAir 12 months ago - 3 comments

#10 - 长音频如何处理？长音频调用只输出一半对应的文本

Issue - State: closed - Opened by xxm1668 12 months ago - 3 comments

#9 - low gender classification accuracy

Issue - State: open - Opened by yl4579 12 months ago

#9 - low gender classification accuracy

Issue - State: open - Opened by yl4579 12 months ago

#8 - Mac M1 runs painfully slow

Issue - State: open - Opened by zfarrell13 12 months ago - 3 comments

#7 - 训练问题

Issue - State: closed - Opened by Mddct 12 months ago - 2 comments

#6 - 怎样可以让asr的输出带标点呢

Issue - State: closed - Opened by liuxq 12 months ago - 1 comment

#6 - 怎样可以让asr的输出带标点呢

Issue - State: closed - Opened by liuxq 12 months ago - 1 comment

#5 - 微调代码可以开源一下不

Issue - State: open - Opened by zhangfan-algo 12 months ago - 14 comments

#4 - is that possible to do tts and speaker diarizatoin?

Issue - State: closed - Opened by lucasjinreal almost 1 year ago - 1 comment

#3 - It's just an advertise. No code No model

Issue - State: closed - Opened by yangboyd about 1 year ago - 2 comments

#2 - 开源时间提问

Issue - State: closed - Opened by Mddct about 1 year ago - 16 comments

#1 - Add README_JA.md

Pull Request - State: open - Opened by eltociear about 1 year ago - 1 comment