lemondy

Results 6 comments of lemondy

> 关于克隆特定人声音的问题 > > 1、是用主页提供的模型接着训练,还是自己从零训练好些? > > 2、自己准备数据集,大概需要多丰富的数据效果才能好? +1 同样的疑问,另外还有个问题,是否每个人需要单独训练个合成器了(synthesizer)?

> 我想问下自己训练出来的final.pt怎么用才能够实现语音转文字呢(小白不是很会) 可以看下 examples 目录下run.sh 脚本中如下调用 recognize.py 音频转文本的示例,里面 --checkpoint 后面用你训练的模型 pt 文件即可 https://github.com/wenet-e2e/wenet/blob/3eb9a8579d65a32b606aa04c89bdfcaca10d220b/examples/aishell/s0/run.sh#L180

> > aishell-1 should give poorer result than wenetspeech since the model is trained on much less data(200 vs 10,000). > > You can combine the two hours data with...

In windows, change rdagent/utils/env.py ` normalize_volumns` function like below, it works: ``` def normalize_volumes(vols: dict[str, str | dict[str, str]], working_dir: str) -> dict: abs_vols: dict[str, str | dict[str, str]] =...