Skip to content

SOTA Open Source TTS

docs: adjust the chapter structure to better organize the model downl… (#839)

chesha108f3205afd52
diff --git a/docs/en/inference.md b/docs/en/inference.md
index 769d7fd..5238292 100644
--- a/docs/en/inference.md
+++ b/docs/en/inference.md
@@ -10,14 +10,14 @@ Inference support command line, HTTP API and web UI.
3. Given a new piece of text, let the model generate the corresponding semantic tokens.
4. Input the generated semantic tokens into VITS / VQGAN to decode and generate the corresponding voice.
-## Command Line Inference
-
+## Download Models
Download the required `vqgan` and `llama` models from our Hugging Face repository.
```bash
huggingface-cli download fishaudio/fish-speech-1.5 --local-dir checkpoints/fish-speech-1.5
```
+## Command Line Inference
### 1. Generate prompt from voice:
!!! note
diff --git a/docs/ja/inference.md b/docs/ja/inference.md
index e6ce2af..7a53489 100644
--- a/docs/ja/inference.md
+++ b/docs/ja/inference.md
@@ -10,14 +10,14 @@
3. 新しいテキストが与えられた場合、モデルに対応するセマンティックトークンを生成させます。
4. 生成されたセマンティックトークンをVITS / VQGANに入力してデコードし、対応する音声を生成します。
-## コマンドライン推論
-
+## モデルをダウンロード
必要な`vqgan`および`llama`モデルを Hugging Face リポジトリからダウンロードします。
```bash
huggingface-cli download fishaudio/fish-speech-1.5 --local-dir checkpoints/fish-speech-1.5
```
+## コマンドライン推論
### 1. 音声からプロンプトを生成する:
!!! note
diff --git a/docs/ko/inference.md b/docs/ko/inference.md
index 3d1730d..9e1b003 100644
--- a/docs/ko/inference.md
+++ b/docs/ko/inference.md
@@ -10,14 +10,14 @@
3. 새로운 텍스트를 입력하면, 모델이 해당하는 시맨틱 토큰을 생성합니다.
4. 생성된 시맨틱 토큰을 VITS / VQGAN에 입력하여 음성을 디코딩하고 생성합니다.
-## 명령줄 추론
-
+## 모델 다운로드
필요한 `vqgan` 및 `llama` 모델을 Hugging Face 리포지토리에서 다운로드하세요.
```bash
huggingface-cli download fishaudio/fish-speech-1.5 --local-dir checkpoints/fish-speech-1.5
```
+## 명령줄 추론
### 1. 음성에서 프롬프트 생성:
!!! note
diff --git a/docs/pt/inference.md b/docs/pt/inference.md
index b4c87ac..1b96b6e 100644
--- a/docs/pt/inference.md
+++ b/docs/pt/inference.md
@@ -10,14 +10,14 @@ Suporte para inferência por linha de comando, API HTTP e interface web (WebUI).
3. Dado um novo trecho de texto, fazer com que o modelo gere os tokens semânticos correspondentes.
4. Inserir os tokens semânticos gerados no VITS / VQGAN para decodificar e gerar a voz correspondente.
-## Inferência por Linha de Comando
-
+## Baixar modelos
Baixe os modelos `vqgan` e `llama` necessários do nosso repositório Hugging Face.
```bash
huggingface-cli download fishaudio/fish-speech-1.5 --local-dir checkpoints/fish-speech-1.5
```
+## Inferência por Linha de Comando
### 1. Gerar prompt a partir da voz:
!!! note
diff --git a/docs/zh/inference.md b/docs/zh/inference.md
index 5a593cf..e076d49 100644
--- a/docs/zh/inference.md
+++ b/docs/zh/inference.md
@@ -10,8 +10,7 @@
3. 给定一段新文本, 让模型生成对应的语义 token.
4. 将生成的语义 token 输入 VQGAN 解码, 生成对应的语音.
-## 命令行推理
-
+## 下载模型
从我们的 huggingface 仓库下载所需的 `vqgan` 和 `llama` 模型。
```bash
@@ -24,6 +23,7 @@ huggingface-cli download fishaudio/fish-speech-1.5 --local-dir checkpoints/fish-
HF_ENDPOINT=https://hf-mirror.com huggingface-cli download fishaudio/fish-speech-1.5 --local-dir checkpoints/fish-speech-1.5
```
+## 命令行推理
### 1. 从语音生成 prompt:
!!! note