-
Notifications
You must be signed in to change notification settings - Fork 986
Insights: FunAudioLLM/CosyVoice
Overview
There hasn’t been any commit activity on FunAudioLLM/CosyVoice in the last week.
Want to help out?
1 Pull request merged by 1 person
-
feat(docker): update CUDA base image to 12.4.1 for TensorRT support
#936 merged
Feb 6, 2025
1 Pull request opened by 1 person
-
Add a inference_instruct2 route to support and defaultly supports cosyvoice2 in fastapi server
#940 opened
Feb 3, 2025
3 Issues closed by 3 people
-
Update Docker base image to CUDA 12.4.1 for TensorRT compatibility
#935 closed
Feb 6, 2025 -
模型支持商用么
#692 closed
Feb 5, 2025 -
Error encountered while using TensorRT for inference
#901 closed
Jan 31, 2025
6 Issues opened by 6 people
-
docker创建镜像实在是太大了
#946 opened
Feb 6, 2025 -
cosyvoice2 llm training support?
#945 opened
Feb 6, 2025 -
CosyVoice2-0.5B中llm.pt和CosyVoice-BlankEN文件下的模型权重是一致的吗?
#944 opened
Feb 6, 2025 -
关于单说话人微调SFT
#943 opened
Feb 6, 2025 -
No module named 'matcha.models'; 'matcha' is not a package
#942 opened
Feb 5, 2025 -
谁帮我看看这个? 十分头疼
#941 opened
Feb 4, 2025
20 Unresolved conversations
Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.
-
CosyVoice2,Prompt的不同会对 Zero shot 结果的正确性带来影响
#816 commented on
Jan 31, 2025 • 0 new comments -
调用函数流式输出,与官方webui流式输出,终端提示显示不一致
#815 commented on
Jan 31, 2025 • 0 new comments -
ValueError: The provided filename pretrained_models/CosyVoice2-0.5B/flow.encoder.fp16.zip does not exist
#825 commented on
Feb 2, 2025 • 0 new comments -
English is under trained
#820 commented on
Feb 2, 2025 • 0 new comments -
生成的音频与文本对不上
#829 commented on
Feb 3, 2025 • 0 new comments -
Problems with finetuned flow used in CosyVoice2 while in SFT scenario
#826 commented on
Feb 3, 2025 • 0 new comments -
运行后出现这个问题!
#824 commented on
Feb 3, 2025 • 0 new comments -
如何在cosyvoice1的基础上升级为cosyvoice2
#804 commented on
Feb 3, 2025 • 0 new comments -
Conv node status error
#833 commented on
Feb 4, 2025 • 0 new comments -
Finetune CosyVoice2 Flow Module
#784 commented on
Feb 5, 2025 • 0 new comments -
从头训模型总是loss突然变成nan
#652 commented on
Feb 5, 2025 • 0 new comments -
在相同数据上进行微调,25hz模型和50hz差距很大
#489 commented on
Feb 5, 2025 • 0 new comments -
【音质问题】合成音频时,音频的开始总会有滴的一声
#480 commented on
Feb 5, 2025 • 0 new comments -
AttributeError: 'NoneType' object has no attribute 'create_execution_context'
#720 commented on
Feb 5, 2025 • 0 new comments -
偶尔触发CUDA error: device-side assert triggered,频率还挺高
#684 commented on
Feb 5, 2025 • 0 new comments -
调了两个通宵,测了5种语言,不管怎么改都会吞字,弃坑
#917 commented on
Feb 6, 2025 • 0 new comments -
读错了声调如何修正?2读成两怎么修正?我想自定义某些词组的发声需要如何实现呢?
#938 commented on
Feb 6, 2025 • 0 new comments -
生成长中文音频时,只返回了一段音频,没有返回完整的音频
#828 commented on
Feb 6, 2025 • 0 new comments -
same loss when running two experiments simultaneously under examples/libritts/cosyvoice
#662 commented on
Feb 6, 2025 • 0 new comments