Ruoyi comments

Results 71 comments of


                                            Ruoyi

WSL2 Ubuntu安装的，怎么启动项目呀？

ubuntu建议你直接执行命令行tools/webui.py

[Feature] hello,could it generate the audio phoneme delayedtime sequence such azure?

Sorry, but we didn't put any audio phoneme delayedtime sequence into training.

ERROR: Error loading ASGI app. Could not import module "tools.api".

please use ```bash python -m tools.api --llama-checkpoint-path checkpoints/fish-agent-v0.1-3b/ --mode agent ``` to run the api

[Feature] some idea for support chinese dialect

欢迎pr，也欢迎自行实践得出结论

Why is the streaming parameter of the TTS interface set to True, which actually returns all fragments instead of streaming

Obviously the stream function returns trunk-like data, the LLM backbone supports streaming but vocoder currently not, as it isn't an autoregressive model.

Is there a doc for the API?

Which api? The one for the playground or the one in the repo? Here's the api doc for the playground : https://docs.fish.audio/ For the api in the repo, I'm sorry...

微调llama模型后，没有生成微调后的 checkpoints文件夹

根据文档进行操作，同时请检查各个文件目录下的内容

ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory

Need a sound card to stream out audio. Same problem may occur when audio played on device instead of play with audio processing applications.

[FINETUNE]

30mins' data is so little for finetune, we recommend you to finetune with data more than 10 hours.

[Feature] existing streaming latency is still takes time,

Please compile the model, or try the quantized version.