blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2025-10-05 22:20:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Replace the outdated link and pin dependencies

Browse Source
This commit is contained in:
XXXXRT666 2025-04-18 04:13:29 +01:00 committed by GitHub
parent c0b46314ca
commit 67a1e01ef6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
6 changed files with 17 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -146,13 +146,13 @@ docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-Docker
## Pretrained Models
**If `install.sh` runs successfully, you may skip No.1.**
**If `install.sh` runs successfully, you may skip No.1 & No.2**
**Users in China can [download all these models here](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e/dkxgpiy9zb96hob4#nVNhX).**
1. Download pretrained models from [GPT-SoVITS Models](https://huggingface.co/lj1995/GPT-SoVITS) and place them in `GPT_SoVITS/pretrained_models`.
2. Download G2PW models from [G2PWModel_1.1.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip), unzip and rename to `G2PWModel`, and then place them in `GPT_SoVITS/text`.(Chinese TTS Only)
2. Download G2PW models from [G2PWModel_1.1.zip](https://www.modelscope.cn/models/kamiorinn/g2pw/resolve/master/G2PWModel_1.1.zip), unzip and rename to `G2PWModel`, and then place them in `GPT_SoVITS/text`.(Chinese TTS Only)
3. For UVR5 (Vocals/Accompaniment Separation & Reverberation Removal, additionally), download models from [UVR5 Weights](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/uvr5_weights) and place them in `tools/uvr5/uvr5_weights`.
@ -262,7 +262,7 @@ Use v2 from v1 environment:
3. Download v2 pretrained models from [huggingface](https://huggingface.co/lj1995/GPT-SoVITS/tree/main/gsv-v2final-pretrained) and put them into `GPT_SoVITS\pretrained_models\gsv-v2final-pretrained`.
Chinese v2 additional: [G2PWModel_1.1.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip)(Download G2PW models, unzip and rename to `G2PWModel`, and then place them in `GPT_SoVITS/text`.)
Chinese v2 additional: [G2PWModel_1.1.zip](https://www.modelscope.cn/models/kamiorinn/g2pw/resolve/master/G2PWModel_1.1.zip)(Download G2PW models, unzip and rename to `G2PWModel`, and then place them in `GPT_SoVITS/text`.)
## V3 Release Notes

6
docs/cn/README.md
View File

@ -148,13 +148,13 @@ docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-Docker
## 预训练模型
**若成功运行`install.sh`可跳过 No.1**
**若成功运行`install.sh`可跳过 No.1 & No.2**
**中国地区的用户可以[在此处下载这些模型](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e/dkxgpiy9zb96hob4#nVNhX).**
1. 从 [GPT-SoVITS Models](https://huggingface.co/lj1995/GPT-SoVITS) 下载预训练模型, 并将其放置在 `GPT_SoVITS/pretrained_models` 目录中.
2. 从 [G2PWModel_1.1.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip) 下载模型, 解压并重命名为 `G2PWModel`, 然后将其放置在 `GPT_SoVITS/text` 目录中. (仅限中文 TTS)
2. 从 [G2PWModel_1.1.zip](https://www.modelscope.cn/models/kamiorinn/g2pw/resolve/master/G2PWModel_1.1.zip) 下载模型, 解压并重命名为 `G2PWModel`, 然后将其放置在 `GPT_SoVITS/text` 目录中. (仅限中文 TTS)
3. 对于 UVR5 (人声/伴奏分离和混响移除, 额外功能), 从 [UVR5 Weights](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/uvr5_weights) 下载模型, 并将其放置在 `tools/uvr5/uvr5_weights` 目录中.
@ -264,7 +264,7 @@ python webui.py
3. 需要从[huggingface](https://huggingface.co/lj1995/GPT-SoVITS/tree/main/gsv-v2final-pretrained) 下载预训练模型文件放到 GPT_SoVITS\pretrained_models\gsv-v2final-pretrained 下
中文额外需要下载[G2PWModel_1.1.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip) (下载 G2PW 模型,解压并重命名为`G2PWModel`,将其放到`GPT_SoVITS/text`目录下)
中文额外需要下载[G2PWModel_1.1.zip](https://www.modelscope.cn/models/kamiorinn/g2pw/resolve/master/G2PWModel_1.1.zip) (下载 G2PW 模型,解压并重命名为`G2PWModel`,将其放到`GPT_SoVITS/text`目录下)
## V3 更新说明

6
docs/ja/README.md
View File

@ -140,11 +140,11 @@ docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-Docker
## 事前訓練済みモデル
**`install.sh`が正常に実行された場合、No.1はスキップしてかまいません.**
**`install.sh`が正常に実行された場合、No.1 & No.2 はスキップしてかまいません.**
1. [GPT-SoVITS Models](https://huggingface.co/lj1995/GPT-SoVITS) から事前訓練済みモデルをダウンロードし、`GPT_SoVITS/pretrained_models` ディレクトリに配置してください.
2. [G2PWModel_1.1.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip) からモデルをダウンロードし、解凍して `G2PWModel` にリネームし、`GPT_SoVITS/text` ディレクトリに配置してください. (中国語 TTS のみ)
2. [G2PWModel_1.1.zip](https://www.modelscope.cn/models/kamiorinn/g2pw/resolve/master/G2PWModel_1.1.zip) からモデルをダウンロードし、解凍して `G2PWModel` にリネームし、`GPT_SoVITS/text` ディレクトリに配置してください. (中国語 TTS のみ)
3. UVR5 (ボーカル/伴奏 (BGM 等) 分離 & リバーブ除去の追加機能) の場合は、[UVR5 Weights](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/uvr5_weights) からモデルをダウンロードし、`tools/uvr5/uvr5_weights` ディレクトリに配置してください.
@ -252,7 +252,7 @@ V1 環境から V2 を使用するには:
3. [huggingface](https://huggingface.co/lj1995/GPT-SoVITS/tree/main/gsv-v2final-pretrained)から V2 の事前学習モデルをダウンロードし、それらを`GPT_SoVITS\pretrained_models\gsv-v2final-pretrained`に配置
中国語 V2 追加: [G2PWModel_1.1.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip) (G2PW モデルをダウンロードし、解凍して`G2PWModel`にリネームし、`GPT_SoVITS/text`に配置します)
中国語 V2 追加: [G2PWModel_1.1.zip](https://www.modelscope.cn/models/kamiorinn/g2pw/resolve/master/G2PWModel_1.1.zip) (G2PW モデルをダウンロードし、解凍して`G2PWModel`にリネームし、`GPT_SoVITS/text`に配置します)
## V3 リリースノート

6
docs/ko/README.md
View File

@ -145,11 +145,11 @@ docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-Docker
## 사전 학습된 모델
**`install.sh`가 성공적으로 실행되면 No.1은 건너뛰어도 됩니다.**
**`install.sh`가 성공적으로 실행되면 No.1 & No.2 은 건너뛰어도 됩니다.**
1. [GPT-SoVITS Models](https://huggingface.co/lj1995/GPT-SoVITS) 에서 사전 학습된 모델을 다운로드하고, `GPT_SoVITS/pretrained_models` 디렉토리에 배치하세요.
2. [G2PWModel_1.1.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip) 에서 모델을 다운로드하고 압축을 풀어 `G2PWModel`로 이름을 변경한 후, `GPT_SoVITS/text` 디렉토리에 배치하세요. (중국어 TTS 전용)
2. [G2PWModel_1.1.zip](https://www.modelscope.cn/models/kamiorinn/g2pw/resolve/master/G2PWModel_1.1.zip) 에서 모델을 다운로드하고 압축을 풀어 `G2PWModel`로 이름을 변경한 후, `GPT_SoVITS/text` 디렉토리에 배치하세요. (중국어 TTS 전용)
3. UVR5 (보컬/반주 분리 & 잔향 제거 추가 기능)의 경우, [UVR5 Weights](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/uvr5_weights) 에서 모델을 다운로드하고 `tools/uvr5/uvr5_weights` 디렉토리에 배치하세요.
@ -257,7 +257,7 @@ V1 환경에서 V2를 사용하려면:
3. [huggingface](https://huggingface.co/lj1995/GPT-SoVITS/tree/main/gsv-v2final-pretrained)에서 V2 사전 학습 모델을 다운로드하여 `GPT_SoVITS\pretrained_models\gsv-v2final-pretrained`에 넣으십시오.
중국어 V2 추가: [G2PWModel_1.1.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip) (G2PW 모델을 다운로드하여 압축을 풀고 `G2PWModel`로 이름을 변경한 다음 `GPT_SoVITS/text`에 배치합니다.)
중국어 V2 추가: [G2PWModel_1.1.zip](https://www.modelscope.cn/models/kamiorinn/g2pw/resolve/master/G2PWModel_1.1.zip) (G2PW 모델을 다운로드하여 압축을 풀고 `G2PWModel`로 이름을 변경한 다음 `GPT_SoVITS/text`에 배치합니다.)
## V3 릴리스 노트

6
docs/tr/README.md
View File

@ -140,11 +140,11 @@ docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-Docker
## Önceden Eğitilmiş Modeller
**Eğer `install.sh` başarıyla çalıştırılırsa, No.1 adımını atlayabilirsiniz.**
**Eğer `install.sh` başarıyla çalıştırılırsa, No.1 & No.2 adımını atlayabilirsiniz.**
1. [GPT-SoVITS Models](https://huggingface.co/lj1995/GPT-SoVITS) üzerinden önceden eğitilmiş modelleri indirip `GPT_SoVITS/pretrained_models` dizinine yerleştirin.
2. [G2PWModel_1.1.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip) üzerinden modeli indirip sıkıştırmayı açın ve `G2PWModel` olarak yeniden adlandırın, ardından `GPT_SoVITS/text` dizinine yerleştirin. (Sadece Çince TTS için)
2. [G2PWModel_1.1.zip](https://www.modelscope.cn/models/kamiorinn/g2pw/resolve/master/G2PWModel_1.1.zip) üzerinden modeli indirip sıkıştırmayı açın ve `G2PWModel` olarak yeniden adlandırın, ardından `GPT_SoVITS/text` dizinine yerleştirin. (Sadece Çince TTS için)
3. UVR5 (Vokal/Enstrümantal Ayrımı & Yankı Giderme) için, [UVR5 Weights](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/uvr5_weights) üzerinden modelleri indirip `tools/uvr5/uvr5_weights` dizinine yerleştirin.
@ -254,7 +254,7 @@ V1 ortamından V2'yi kullanmak için:
3. [huggingface](https://huggingface.co/lj1995/GPT-SoVITS/tree/main/gsv-v2final-pretrained) adresinden v2 önceden eğitilmiş modelleri indirin ve bunları `GPT_SoVITS\pretrained_models\gsv-v2final-pretrained` dizinine yerleştirin.
Ek olarak Çince V2: [G2PWModel_1.1.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip) (G2PW modellerini indirip, zipten çıkarıp, `G2PWModel` olarak yeniden adlandırıp `GPT_SoVITS/text` dizinine yerleştirin.)
Ek olarak Çince V2: [G2PWModel_1.1.zip](https://www.modelscope.cn/models/kamiorinn/g2pw/resolve/master/G2PWModel_1.1.zip) (G2PW modellerini indirip, zipten çıkarıp, `G2PWModel` olarak yeniden adlandırıp `GPT_SoVITS/text` dizinine yerleştirin.)
## V3 Sürüm Notları

4
requirements.txt
View File

@ -4,7 +4,7 @@ tensorboard
librosa==0.9.2
numba
pytorch-lightning>=2.4
gradio<5
gradio>=4.41,<5
ffmpeg-python
onnxruntime; sys_platform == 'darwin'
onnxruntime-gpu; sys_platform != 'darwin'
@ -34,7 +34,7 @@ ko_pron
opencc; sys_platform != 'linux'
opencc==1.1.1; sys_platform == 'linux'
python_mecab_ko; sys_platform != 'win32'
fastapi>=0.115.1
fastapi[standard]>=0.115.1
x_transformers
torchmetrics<=1.5
pydantic<=2.10.6