upload files

This commit is contained in:
Plachta
2023-02-16 19:46:23 +08:00
parent 6e8d3255a1
commit 018a0aa0d8
3 changed files with 12 additions and 6 deletions
+2
View File
@@ -50,6 +50,8 @@ Your-zip-file.zip
└───zzz.wav └───zzz.wav
``` ```
Note that the format & name of the audio files does not matter as long as they are audio files. 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. You can either choose to perform step 2, 3, or both, depending on your needs.
4. Fine-tune (30 min) 4. Fine-tune (30 min)
After everything is done, download the fine-tuned model & model config After everything is done, download the fine-tuned model & model config
+2
View File
@@ -50,6 +50,8 @@ Your-zip-file.zip
└───zzz.wav └───zzz.wav
``` ```
Note that the format & name of the audio files does not matter as long as they are audio files. 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. You can either choose to perform step 2, 3, or both, depending on your needs.
4. Fine-tune (30 min) 4. Fine-tune (30 min)
After everything is done, download the fine-tuned model & model config After everything is done, download the fine-tuned model & model config
+8 -6
View File
@@ -8,13 +8,13 @@ English Documentation Please Click [here](https://github.com/SongtingLiu/VITS_vo
### 目前支持的任务: ### 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) - [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 ### 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] 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) - [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) - [x] 原神 (仅已实装角色)(预训练时使用的角色)
- [ ] 任意角色(待完成 - [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 ├───yyy.mp3
└───zzz.wav └───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。 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) 3. 进行微调 (30 min)