Yaodada12 comments

Results 28 comments of


                                            Yaodada12

我想让生成的语音带有情感和正常人说话的节奏，有什么改进方案吗

> 中文没有办法了吗他的意思应该是让你说英文？

我想让生成的语音带有情感和正常人说话的节奏，有什么改进方案吗

> 我想问下实际操作下来可以克隆自己的声音来读文章是行得通吗可以的，自己玩一下没什么问题。

A better plan for Chinese polyphonic characters

可以的，大佬

[Feature request] CLI or importable script for generating dataset & fine-tuning XTTS

> **🚀 Feature Description** > > Right now (and correct me if I'm wrong) it seems that the [collab](https://colab.research.google.com/drive/1GiI4_X724M8q2W-zZ-jXo7cWTV7RfaH-?usp=sharing#scrollTo=zd2xo_7a8wyj) is the only way to fine-tune XTTS from zero (i.e. no...

[Feature request] CLI or importable script for generating dataset & fine-tuning XTTS

> @Yaodada12 > > Check out these repos https://github.com/daswer123/xtts-finetune-webui https://github.com/Haurrus/xtts-trainer-no-ui-auto Thank you so much！

xtts demo not saving checkpoints, thus can't run inference[Bug]

> ### Describe the bug > Hi, I ran the demo yesterday with no isses on colab. Today I try again with the same conditions but this time the best...

[Bug] TypeError: 'NoneType' object is not subscriptable

> It might be related to this one: [36143fe](https://github.com/coqui-ai/TTS/commit/36143fee2625aac6c6b3f7c7d0e0b7d75800167a) > > If the speaker_file_path is None, it will try to load os.path.join(checkpoint_dir, "speakers_xtts.pth") If checkoint_dir is also None, because it's...