Skip to content

Commit 08f3205

Browse files
authored
docs: adjust the chapter structure to better organize the model downl… (#839)
* docs: adjust the chapter structure to better organize the model download sections * docs: ko, ja, pt
1 parent e0cd697 commit 08f3205

File tree

5 files changed

+10
-10
lines changed

5 files changed

+10
-10
lines changed

docs/en/inference.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -10,14 +10,14 @@ Inference support command line, HTTP API and web UI.
1010
3. Given a new piece of text, let the model generate the corresponding semantic tokens.
1111
4. Input the generated semantic tokens into VITS / VQGAN to decode and generate the corresponding voice.
1212

13-
## Command Line Inference
14-
13+
## Download Models
1514
Download the required `vqgan` and `llama` models from our Hugging Face repository.
1615

1716
```bash
1817
huggingface-cli download fishaudio/fish-speech-1.5 --local-dir checkpoints/fish-speech-1.5
1918
```
2019

20+
## Command Line Inference
2121
### 1. Generate prompt from voice:
2222

2323
!!! note

docs/ja/inference.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -10,14 +10,14 @@
1010
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。
1111
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。
1212

13-
## コマンドライン推論
14-
13+
## モデルをダウンロード
1514
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。
1615

1716
```bash
1817
huggingface-cli download fishaudio/fish-speech-1.5 --local-dir checkpoints/fish-speech-1.5
1918
```
2019

20+
## コマンドライン推論
2121
### 1. 音声からプロンプトを生成する:
2222

2323
!!! note

docs/ko/inference.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -10,14 +10,14 @@
1010
3. 새로운 텍스트를 입력하면, 모델이 해당하는 시맨틱 토큰을 생성합니다.
1111
4. 생성된 시맨틱 토큰을 VITS / VQGAN에 입력하여 음성을 디코딩하고 생성합니다.
1212

13-
## 명령줄 추론
14-
13+
## 모델 다운로드
1514
필요한 `vqgan``llama` 모델을 Hugging Face 리포지토리에서 다운로드하세요.
1615

1716
```bash
1817
huggingface-cli download fishaudio/fish-speech-1.5 --local-dir checkpoints/fish-speech-1.5
1918
```
2019

20+
## 명령줄 추론
2121
### 1. 음성에서 프롬프트 생성:
2222

2323
!!! note

docs/pt/inference.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -10,14 +10,14 @@ Suporte para inferência por linha de comando, API HTTP e interface web (WebUI).
1010
3. Dado um novo trecho de texto, fazer com que o modelo gere os tokens semânticos correspondentes.
1111
4. Inserir os tokens semânticos gerados no VITS / VQGAN para decodificar e gerar a voz correspondente.
1212

13-
## Inferência por Linha de Comando
14-
13+
## Baixar modelos
1514
Baixe os modelos `vqgan` e `llama` necessários do nosso repositório Hugging Face.
1615

1716
```bash
1817
huggingface-cli download fishaudio/fish-speech-1.5 --local-dir checkpoints/fish-speech-1.5
1918
```
2019

20+
## Inferência por Linha de Comando
2121
### 1. Gerar prompt a partir da voz:
2222

2323
!!! note

docs/zh/inference.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -10,8 +10,7 @@
1010
3. 给定一段新文本, 让模型生成对应的语义 token.
1111
4. 将生成的语义 token 输入 VQGAN 解码, 生成对应的语音.
1212

13-
## 命令行推理
14-
13+
## 下载模型
1514
从我们的 huggingface 仓库下载所需的 `vqgan``llama` 模型。
1615

1716
```bash
@@ -24,6 +23,7 @@ huggingface-cli download fishaudio/fish-speech-1.5 --local-dir checkpoints/fish-
2423
HF_ENDPOINT=https://hf-mirror.com huggingface-cli download fishaudio/fish-speech-1.5 --local-dir checkpoints/fish-speech-1.5
2524
```
2625

26+
## 命令行推理
2727
### 1. 从语音生成 prompt:
2828

2929
!!! note

0 commit comments

Comments
 (0)