-
In the generation process of Cosy Voice a flow matching module is employed to convert Speech Tokens to Mel Spectrum
![image](https://github.com/user-attachments/assets/b18f3312-a348-4bc6-94ca-94d5d5c…
-
**Describe the bug**
比如:` 这样的训练过程使得我能够回答各种问题、创作文字,以及进行多轮对话等任务。` 这段文字,使用 CosyVoice-300M-SFT 模型推理生成的语音, `、` 之后的文字没有生成语音。
**To Reproduce**
```
from cosyvoice.cli.cosyvoice import CosyVoice
from c…
-
**Describe the bug**
语音生成的效率太低了,同样的句子。openvoice 下只需要5秒,语音克隆也只要1分钟,而CosyVoice sft需要2分钟,zero-short更是需要5分钟以上
> 这是一段使用open voice 和 melo-tts生成的语音。 支持中文+英文的Cross-Lingual 句子。这个project真的挺challenging的,我们得赶…
-
### Describe the bug
Hello everyone, thank you very much for open sourcing coqui ai, such a great TTS that performs much better than similar products in terms of performance and effectiveness. I enco…
-
以下是错误讯息
`2024-08-31 15:33:09,546 - modelscope - INFO - PyTorch version 2.0.1+cu118 Found.
2024-08-31 15:33:09,547 - modelscope - INFO - Loading ast index from C:\Users\USER\.cache\modelscope\ast_ind…
-
I am using the latest version of Windows 10. My computer's power plan is set to have my display sleep after 25 minutes of inactivity. The Aerial 6.1 screen saver is set to become active after 5 minute…
-
Untitled Document
Chapter I
IN WHICH PHILEAS FOGG AND PASSEPARTOUT ACCEPT EACH OTHER, THE ONE AS MASTER, THE OTHER AS MAN
Two driven jocks help fax my big quiz. Do wafting zephyrs…
-
**Describe the bug**
Follow the instructions in README.md step by step, deploy on a personal server, execute
`python3 webui.py --port 50000 --model_dir speech_tts/CosyVoice-300M`
Unable to start, e…
-
Phd track: 21 Nov 2021 - 21 Nov 2025
First step in 4 year phd track: get paper from master thesis work.
Venues: https://github.com/Tribler/tribler/wiki/Scientific-publication-venues-for-ledger-scien…
-
我在本地部署了我们的Cosy Voice,体验下来非常棒,我已经有一些使用它的小创意了。再次感谢项目组的辛苦付出。
我的环境:
我使用的一个我的一个旧电脑,CPU i7 8核心,一个AMD显卡 2G显存,内存16G,操作系统为Centos7。
1、关于CPU资源使用:我发现在使用的过程中,并没有把我的CPU资源给占满,而且我也没有发现配置进程数量的地方(可能是我没找到),是否可以默认…