Ecosyste.ms: Issues

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

GitHub / thudm/glm-4-voice issues and pull requests

#110 - token数目不对齐

Issue - State: open - Opened by fanpengustc 6 days ago - 1 comment

#107 - 请问 会开源base 非chat的模型吗

Issue - State: open - Opened by Mddct 7 days ago - 2 comments

#107 - 请问 会开源base 非chat的模型吗

Issue - State: open - Opened by Mddct 7 days ago - 2 comments

#105 - 控制情绪的测试效果不如开源的demo

Issue - State: open - Opened by yygg678 8 days ago - 1 comment

#105 - 控制情绪的测试效果不如开源的demo

Issue - State: open - Opened by yygg678 8 days ago - 1 comment

#104 - 语音loss下降情况

Issue - State: open - Opened by tianzhangwu 8 days ago - 2 comments

#104 - 语音loss下降情况

Issue - State: open - Opened by tianzhangwu 8 days ago - 2 comments

#102 - glm4-voice是否支持rag方式

Issue - State: open - Opened by AlexYoung757 8 days ago - 1 comment

#102 - glm4-voice是否支持rag方式

Issue - State: open - Opened by AlexYoung757 8 days ago - 1 comment

#100 - mac m系列可以用吗

Issue - State: open - Opened by chatyeei 12 days ago - 7 comments

#100 - mac m系列可以用吗

Issue - State: open - Opened by chatyeei 12 days ago - 7 comments

#99 - 能不能添加systemprompt给模型增加人设呢？

Issue - State: open - Opened by chatyeei 12 days ago - 2 comments

#99 - 能不能添加systemprompt给模型增加人设呢？

Issue - State: open - Opened by chatyeei 12 days ago - 2 comments

#98 - 流式测试

Issue - State: closed - Opened by panhu 12 days ago

#98 - 流式测试

Issue - State: closed - Opened by panhu 12 days ago

#97 - 如何修改模型交替输出token数量

Issue - State: open - Opened by SteinsHead 12 days ago - 1 comment

#97 - 如何修改模型交替输出token数量

Issue - State: open - Opened by SteinsHead 12 days ago - 1 comment

#96 - 怎么给cosyVoice提速的，这个生成的速度不快啊

Issue - State: open - Opened by hjj-lmx 12 days ago - 2 comments

#96 - 怎么给cosyVoice提速的，这个生成的速度不快啊

Issue - State: open - Opened by hjj-lmx 12 days ago - 2 comments

#95 - 请问会开源训练部分吗？？？

Issue - State: open - Opened by SevenMpp 12 days ago - 2 comments

#95 - 请问会开源训练部分吗？？？

Issue - State: open - Opened by SevenMpp 12 days ago - 2 comments

#94 - 支持麦克风输入吗

Issue - State: closed - Opened by Lzzzii10 12 days ago

#94 - 支持麦克风输入吗

Issue - State: closed - Opened by Lzzzii10 12 days ago

#93 - 使用zhipuai/glm-4-voice:0.1 docker 无法运行

Issue - State: open - Opened by soloHeroo 13 days ago - 2 comments

#92 - 可以只输出文本而不输出音频吗

Issue - State: open - Opened by air158 13 days ago - 1 comment

#92 - 可以只输出文本而不输出音频吗

Issue - State: open - Opened by air158 13 days ago - 1 comment

#91 - 请问文字的终止条件是如何判断的

Issue - State: open - Opened by QinghanLai 13 days ago - 5 comments

#91 - 请问文字的终止条件是如何判断的

Issue - State: open - Opened by QinghanLai 13 days ago - 5 comments

#90 - 支持纯cpu推理吗

Issue - State: open - Opened by sgwzy22 14 days ago - 2 comments

#89 - 安装后启动demo，执行submit后自动退出服务。

Issue - State: open - Opened by fengchaobaby 14 days ago - 12 comments

#88 - 我在A800上流式推理为什么每输出一个token要2秒钟

Issue - State: open - Opened by anliyuan 15 days ago - 4 comments

#87 - Whether the training dataset will be made public

Issue - State: closed - Opened by SteinsHead 15 days ago - 2 comments

#86 - fix: tts_mel in streaming inference

Pull Request - State: open - Opened by NanYANG2015 15 days ago

#82 - feat: add ngrok proxy to run server

Pull Request - State: open - Opened by weedge 18 days ago

#80 - fixed cuda bug

Pull Request - State: closed - Opened by sixsixcoder 19 days ago

#79 - dev分支的vllm_model_server.py指定GPU貌似无效

Issue - State: open - Opened by Jimmy-L99 19 days ago - 1 comment

#78 - 能把图片和视频模态加上吗，来个omni大一统

Issue - State: closed - Opened by QinghanLai 20 days ago - 2 comments

#76 - 所有的推理出的音频内容无法在gradio的audio控件播放

Issue - State: closed - Opened by codersun123 21 days ago - 5 comments

#75 - 能够输出音频对应的时间戳文本吗

Issue - State: open - Opened by cat-knight 21 days ago - 2 comments

#73 - 输入tokens转文本

Issue - State: open - Opened by panhu 21 days ago - 4 comments

#72 - Do you have expected timeline to release the technical report?

Issue - State: open - Opened by hbwu-ntu 21 days ago - 1 comment

#71 - semantic token如何保留语速、情感等副语言信息？

Issue - State: open - Opened by tianzhangwu 21 days ago - 3 comments

#71 - semantic token如何保留语速、情感等副语言信息？

Issue - State: open - Opened by tianzhangwu 21 days ago - 3 comments

#70 - 音频重建后男声变女声

Issue - State: open - Opened by tianzhangwu 21 days ago - 1 comment

#69 - 请问目前支持TTS语音合成接口调用嘛

Issue - State: open - Opened by njzfw1024 22 days ago - 1 comment

#68 - 关于 glm-4-voice-decoder 有两个疑惑，需要解答

Issue - State: closed - Opened by choyakawa 22 days ago - 9 comments

#67 - 为什么推理不输出音频

Issue - State: open - Opened by zhanghanweii 23 days ago - 1 comment

#66 - improve Gradio streaming audio playback

Pull Request - State: closed - Opened by Mereithhh 23 days ago - 5 comments

#65 - 是否可以指定音色？

Issue - State: open - Opened by xajdlg 23 days ago - 2 comments

#63 - strange flash attention error

Issue - State: open - Opened by silvacarl2 25 days ago - 1 comment

#61 - 方言支持列表

Issue - State: open - Opened by lq0104 26 days ago - 3 comments

#60 - 这个模型可以固定某个声线吗？

Issue - State: open - Opened by SkyblueMr 26 days ago - 2 comments

#60 - 这个模型可以固定某个声线吗？

Issue - State: open - Opened by SkyblueMr 26 days ago - 2 comments

#59 - 请教

Issue - State: closed - Opened by zcdliuwei 26 days ago - 7 comments

#58 - ubuntu 系统下 GLM-4-Voice 部署经验分享，扫坑之旅。

Issue - State: open - Opened by peilongchencc 27 days ago - 7 comments

#57 - Support loading and launching web programs from vllm=0.6.3

Pull Request - State: closed - Opened by sixsixcoder 27 days ago

#56 - web demo录入语音报错

Issue - State: open - Opened by kssmmm 27 days ago - 1 comment

#55 - 如何使用API调用

Issue - State: open - Opened by qiujingfei1 28 days ago - 1 comment

#54 - merge

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR 28 days ago

#53 - 执行python web_demo.py 报错

Issue - State: closed - Opened by njzfw1024 28 days ago - 2 comments

#52 - glm-4-voice语音生成声音有毛刺和卡顿

Issue - State: open - Opened by Jimmy-L99 28 days ago - 1 comment

#51 - 在线API调用

Issue - State: open - Opened by tai960519073 28 days ago - 1 comment

#50 - 请问技术报告公布的确切时间

Issue - State: open - Opened by hbwu-ntu 28 days ago

#48 - Multi-GPU Support: Originally limited to single-GPU setups, this code…

Pull Request - State: open - Opened by StevenChen16 29 days ago - 2 comments

#47 - 可以提供一个Docker镜像吗？

Issue - State: closed - Opened by log4gin 29 days ago - 2 comments

#46 - update with int4 inference

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR 29 days ago

#45 - Main

Pull Request - State: closed - Opened by Yopoto 29 days ago

#44 - 导入tokenizer报错

Issue - State: closed - Opened by zhongJY1998 30 days ago

#43 - 这个能结合RAG吗

Issue - State: open - Opened by Alan-zhong 30 days ago

#40 - f-word

Issue - State: closed - Opened by AMAG-AB 30 days ago

#39 - error: with prompt: 介绍下大熊猫

Issue - State: closed - Opened by wonderisland 30 days ago - 1 comment

#38 - can not control voice character

Issue - State: open - Opened by ggsonic 30 days ago - 4 comments

#35 - Create python-package-conda.yes

Pull Request - State: open - Opened by Ninjaneer32 30 days ago

#34 - JSONDecodeError，这怎么解决

Issue - State: closed - Opened by LilLeapo 30 days ago - 1 comment

#33 - Fix public model name in README

Pull Request - State: closed - Opened by ggdupont about 1 month ago - 1 comment

#32 - load a 4-bit or 8-bit quantized version

Pull Request - State: closed - Opened by glide-the about 1 month ago

#31 - _pickle.UnpicklingError: invalid load key, 'v'.

Issue - State: closed - Opened by sunnyyangyangyang about 1 month ago - 2 comments

#30 - 无法正常启动，看不到页面

Issue - State: closed - Opened by Lawrenceeeeeeee about 1 month ago - 2 comments