diff --git a/README.md b/README.md index 891dc3e..4ceb75f 100644 --- a/README.md +++ b/README.md @@ -50,6 +50,8 @@ Your-zip-file.zip └───zzz.wav ``` Note that the format & name of the audio files does not matter as long as they are audio files. +Audio quality requirements: >=2s, <=20s per audio, background noise should be as less as possible. +Audio quantity requirements: at least 10 per character, better if 20+ per character. You can either choose to perform step 2, 3, or both, depending on your needs. 4. Fine-tune (30 min) After everything is done, download the fine-tuned model & model config diff --git a/README_EN.md b/README_EN.md index 891dc3e..4ceb75f 100644 --- a/README_EN.md +++ b/README_EN.md @@ -50,6 +50,8 @@ Your-zip-file.zip └───zzz.wav ``` Note that the format & name of the audio files does not matter as long as they are audio files. +Audio quality requirements: >=2s, <=20s per audio, background noise should be as less as possible. +Audio quantity requirements: at least 10 per character, better if 20+ per character. You can either choose to perform step 2, 3, or both, depending on your needs. 4. Fine-tune (30 min) After everything is done, download the fine-tuned model & model config diff --git a/README_ZH.md b/README_ZH.md index 4b4c57b..0d80a8b 100644 --- a/README_ZH.md +++ b/README_ZH.md @@ -8,13 +8,13 @@ English Documentation Please Click [here](https://github.com/SongtingLiu/VITS_vo ### 目前支持的任务: - [x] 转换用户声线到 [这些角色](https://github.com/SongtingLiu/VITS_voice_conversion/blob/main/configs/finetune_speaker.json) -- [ ] 自定义角色的中日英三语TTS(待完成) +- [x] 自定义角色的中日英三语TTS! ### 目前支持声线转换和中日英三语TTS的角色 -- [x] 赛马娘 (仅已实装角色) -- [x] 魔女的夜宴(柚子社) (5人) -- [x] 原神 (仅已实装角色) -- [ ] 任意角色(待完成) +- [x] 赛马娘 (仅已实装角色)(预训练时使用的角色) +- [x] 魔女的夜宴(柚子社) (5人)(预训练时使用的角色) +- [x] 原神 (仅已实装角色)(预训练时使用的角色) +- [x] 任意角色(只要你有角色的声音样本) @@ -47,7 +47,9 @@ Your-zip-file.zip ├───yyy.mp3 └───zzz.wav ``` -注意音频的格式和名称都不重要,只要它们是音频文件。 +注意音频的格式和名称都不重要,只要它们是音频文件。 +质量要求:2秒以上,20秒以内,尽量不要有背景噪音。 +数量要求:一个角色至少10条,最好每个角色20条以上。 你可以选择进行步骤2或3,或二者一起,取决于你的需求。 3. 进行微调 (30 min)