Skip to content

SOTA-Class TTS at Compact Scale

Python

Document Hugging Face model download

root746b6201cac7
diff --git a/README.md b/README.md
index 6dc196f..6227049 100644
--- a/README.md
+++ b/README.md
@@ -60,8 +60,11 @@ source .venv/bin/activate
pip install -r requirements.txt
```
-The local checkpoint is stored in `model/audio8_tts_0_6B_preview`. All commands
-also accept a Hugging Face model ID through `--model`.
+Download the checkpoint from
+[Hugging Face](https://huggingface.co/AutoArk-AI/Audio8-TTS-Preview-0.6b) and
+place it in the repository's `model/` directory. The expected local checkpoint
+path is `model/audio8_tts_0_6B_preview/`. All commands also accept a Hugging
+Face model ID through `--model`.
## Inference
diff --git a/README_zh.md b/README_zh.md
index d6f0b07..a7e83a4 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -54,8 +54,9 @@ source .venv/bin/activate
pip install -r requirements.txt
```
-本地模型位于 `model/audio8_tts_0_6B_preview`。所有命令也可以通过 `--model` 接收 Hugging Face
-模型 ID。
+请从 [Hugging Face](https://huggingface.co/AutoArk-AI/Audio8-TTS-Preview-0.6b)
+下载模型,并将其放入仓库的 `model/` 文件夹中。默认本地模型路径为
+`model/audio8_tts_0_6B_preview/`。所有命令也可以通过 `--model` 接收 Hugging Face 模型 ID。
## 推理