diff --git a/README.md b/README.md
index d03514f0..2afaf1ce 100644
--- a/README.md
+++ b/README.md
@@ -9,7 +9,7 @@ A Powerful Few-shot Voice Conversion and Text-to-Speech WebUI.
-[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/colab_webui.ipynb)
+[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/Colab-WebUI.ipynb)
[](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/LICENSE)
[](https://huggingface.co/spaces/lj1995/GPT-SoVITS-v2)
[](https://discord.gg/dnrgs5GHfG)
@@ -333,7 +333,7 @@ Use v4 from v1/v2/v3 environment:
New Features:
1. Slightly higher VRAM usage than v2, surpassing v4's performance, with v2's hardware cost and speed.
- [more details](https://github.com/RVC-Boss/GPT-SoVITS/wiki/GPT%E2%80%90SoVITS%E2%80%90features-(%E5%90%84%E7%89%88%E6%9C%AC%E7%89%B9%E6%80%A7))
+ [more details]()
2.v1/v2 and the v2Pro series share the same characteristics, while v3/v4 have similar features. For training sets with average audio quality, v1/v2/v2Pro can deliver decent results, but v3/v4 cannot. Additionally, the synthesized tone and timebre of v3/v4 lean more toward the reference audio rather than the overall training set.
diff --git a/docker-compose.yaml b/docker-compose.yaml
index 9703d0c7..f0fc2b43 100644
--- a/docker-compose.yaml
+++ b/docker-compose.yaml
@@ -12,10 +12,6 @@ services:
- "9880:9880"
volumes:
- .:/workspace/GPT-SoVITS
- - /dev/null:/workspace/GPT-SoVITS/GPT_SoVITS/pretrained_models
- - /dev/null:/workspace/GPT-SoVITS/GPT_SoVITS/text/G2PWModel
- - /dev/null:/workspace/GPT-SoVITS/tools/asr/models
- - /dev/null:/workspace/GPT-SoVITS/tools/uvr5/uvr5_weights
environment:
- is_half=true
tty: true
@@ -34,10 +30,6 @@ services:
- "9880:9880"
volumes:
- .:/workspace/GPT-SoVITS
- - /dev/null:/workspace/GPT-SoVITS/GPT_SoVITS/pretrained_models
- - /dev/null:/workspace/GPT-SoVITS/GPT_SoVITS/text/G2PWModel
- - /dev/null:/workspace/GPT-SoVITS/tools/asr/models
- - /dev/null:/workspace/GPT-SoVITS/tools/uvr5/uvr5_weights
- tools/asr/models:/workspace/models/asr_models
- tools/uvr5/uvr5_weights:/workspace/models/uvr5_weights
environment:
@@ -58,10 +50,6 @@ services:
- "9880:9880"
volumes:
- .:/workspace/GPT-SoVITS
- - /dev/null:/workspace/GPT-SoVITS/GPT_SoVITS/pretrained_models
- - /dev/null:/workspace/GPT-SoVITS/GPT_SoVITS/text/G2PWModel
- - /dev/null:/workspace/GPT-SoVITS/tools/asr/models
- - /dev/null:/workspace/GPT-SoVITS/tools/uvr5/uvr5_weights
environment:
- is_half=true
tty: true
@@ -80,10 +68,6 @@ services:
- "9880:9880"
volumes:
- .:/workspace/GPT-SoVITS
- - /dev/null:/workspace/GPT-SoVITS/GPT_SoVITS/pretrained_models
- - /dev/null:/workspace/GPT-SoVITS/GPT_SoVITS/text/G2PWModel
- - /dev/null:/workspace/GPT-SoVITS/tools/asr/models
- - /dev/null:/workspace/GPT-SoVITS/tools/uvr5/uvr5_weights
- tools/asr/models:/workspace/models/asr_models
- tools/uvr5/uvr5_weights:/workspace/models/uvr5_weights
environment:
diff --git a/docs/cn/README.md b/docs/cn/README.md
index e674d9cf..2f4be4ae 100644
--- a/docs/cn/README.md
+++ b/docs/cn/README.md
@@ -9,7 +9,7 @@
-[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/colab_webui.ipynb)
+[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/Colab-WebUI.ipynb)
[](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/LICENSE)
[](https://huggingface.co/spaces/lj1995/GPT-SoVITS-v2)
[](https://discord.gg/dnrgs5GHfG)
@@ -329,7 +329,7 @@ python webui.py
新特性：
1. **相比 V2 占用稍高显存, 性能超过 V4, 在保留 V2 硬件成本和推理速度优势的同时实现更高音质.**
- [更多详情](https://github.com/RVC-Boss/GPT-SoVITS/wiki/GPT%E2%80%90SoVITS%E2%80%90features-(%E5%90%84%E7%89%88%E6%9C%AC%E7%89%B9%E6%80%A7))
+ [更多详情]()
2. V1/V2 与 V2Pro 系列具有相同特性, V3/V4 则具备相近功能. 对于平均音频质量较低的训练集, V1/V2/V2Pro 可以取得较好的效果, 但 V3/V4 无法做到. 此外, V3/V4 合成的声音更偏向参考音频, 而不是整体训练集的风格.
diff --git a/docs/ja/README.md b/docs/ja/README.md
index d4d3081e..4e965efb 100644
--- a/docs/ja/README.md
+++ b/docs/ja/README.md
@@ -7,7 +7,7 @@
-[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/colab_webui.ipynb)
+[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/Colab-WebUI.ipynb)
[](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/LICENSE)
[](https://huggingface.co/spaces/lj1995/GPT-SoVITS-v2)
[](https://discord.gg/dnrgs5GHfG)
@@ -304,7 +304,7 @@ v2 環境から v3 を使用する方法:
新機能:
1. **V4 は、V3 で発生していた非整数倍アップサンプリングによる金属音の問題を修正し、音声がこもる問題を防ぐためにネイティブに 48kHz 音声を出力します（V3 はネイティブに 24kHz 音声のみ出力）**. 作者は V4 を V3 の直接的な置き換えとして推奨していますが、さらなるテストが必要です.
- [詳細はこちら](https://github.com/RVC-Boss/GPT-SoVITS/wiki/GPT%E2%80%90SoVITS%E2%80%90v3v4%E2%80%90features-(%E6%96%B0%E7%89%B9%E6%80%A7))
+ [詳細はこちら]()
V1/V2/V3 環境から V4 への移行方法:
@@ -319,7 +319,7 @@ V1/V2/V3 環境から V4 への移行方法:
新機能:
1. **V2 と比較してやや高いメモリ使用量ですが、ハードウェアコストと推論速度は維持しつつ、V4 よりも高い性能と音質を実現します. **
- [詳細はこちら](https://github.com/RVC-Boss/GPT-SoVITS/wiki/GPT%E2%80%90SoVITS%E2%80%90features-(%E5%90%84%E7%89%88%E6%9C%AC%E7%89%B9%E6%80%A7))
+ [詳細はこちら]()
2. V1/V2 と V2Pro シリーズは類似した特徴を持ち、V3/V4 も同様の機能を持っています. 平均音質が低いトレーニングセットの場合、V1/V2/V2Pro は良好な結果を出すことができますが、V3/V4 では対応できません. また、V3/V4 の合成音声はトレーニング全体ではなく、より参考音声に寄った音質になります.
diff --git a/docs/ko/README.md b/docs/ko/README.md
index c4c7c794..88c36814 100644
--- a/docs/ko/README.md
+++ b/docs/ko/README.md
@@ -7,7 +7,7 @@
-[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/colab_webui.ipynb)
+[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/Colab-WebUI.ipynb)
[](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/LICENSE)
[](https://huggingface.co/spaces/lj1995/GPT-SoVITS-v2)
[](https://discord.gg/dnrgs5GHfG)
@@ -319,7 +319,7 @@ V1/V2/V3 환경에서 V4로 전환 방법:
신규 기능:
1. **V2보다 약간 높은 VRAM 사용량이지만 성능은 V4보다 우수하며, V2 수준의 하드웨어 비용과 속도를 유지합니다**.
- [자세히 보기](https://github.com/RVC-Boss/GPT-SoVITS/wiki/GPT%E2%80%90SoVITS%E2%80%90features-(%E5%90%84%E7%89%88%E6%9C%AC%E7%89%B9%E6%80%A7))
+ [자세히 보기]()
2. V1/V2와 V2Pro 시리즈는 유사한 특징을 가지며, V3/V4도 비슷한 기능을 가지고 있습니다. 평균 음질이 낮은 학습 데이터셋에서는 V1/V2/V2Pro가 좋은 결과를 내지만 V3/V4는 그렇지 못합니다. 또한 V3/V4의 합성 음색은 전체 학습 데이터셋보다는 참고 음성에 더 가깝습니다.
diff --git a/docs/tr/README.md b/docs/tr/README.md
index cc32691f..fb0b31a7 100644
--- a/docs/tr/README.md
+++ b/docs/tr/README.md
@@ -9,7 +9,7 @@ Güçlü Birkaç Örnekli Ses Dönüştürme ve Metinden Konuşmaya Web Arayüz
-[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/colab_webui.ipynb)
+[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/Colab-WebUI.ipynb)
[](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/LICENSE)
[](https://huggingface.co/spaces/lj1995/GPT-SoVITS-v2)
[](https://discord.gg/dnrgs5GHfG)
@@ -323,7 +323,7 @@ V1/V2/V3 ortamından V4'e geçiş:
Yeni Özellikler:
1. **V2 ile karşılaştırıldığında biraz daha yüksek VRAM kullanımı sağlar ancak V4'ten daha iyi performans gösterir; aynı donanım maliyeti ve hız avantajını korur**.
- [Daha fazla bilgi](https://github.com/RVC-Boss/GPT-SoVITS/wiki/GPT%E2%80%90SoVITS%E2%80%90features-(%E5%90%84%E7%89%88%E6%9C%AC%E7%89%B9%E6%80%A7))
+ [Daha fazla bilgi]()
2. V1/V2 ve V2Pro serisi benzer özelliklere sahipken, V3/V4 de yakın işlevleri paylaşır. Ortalama kalite düşük olan eğitim setleriyle V1/V2/V2Pro iyi sonuçlar verebilir ama V3/V4 veremez. Ayrıca, V3/V4’ün ürettiği ses tonu genel eğitim setine değil, referans ses örneğine daha çok benzemektedir.