tingshu

Tingshu (聽舒)

讓作者的聲音直達聽眾| Bringing the author's voice directly to you

項目預覽| Preview

點擊進入項目主頁｜Home

快速開始| Quick Start

點擊這裡觀看視頻

1. 安裝環境| Install Environment

./scripts/install.sh

2. 下載模型權重| Download Model Weights

./scripts/download_weights.sh

3. 啟動Web UI | Run Web Interface

./scripts/run_gradio.sh

4. 生成前端音頻數據| Generate Audio Data

./scripts/generate_web_data.sh

項目優化｜ TODO

• 1. 使用新方案替代tts方式生成的錄音缺乏情感，頓挫，聽感不好問題。
  Replace the TTS-generated recordings to address issues of lacking emotion, intonation, and poor listening experience.

• 2. 更新web ui, 替換靜態加載模式
  Update web ui and switch from static loading mode.

• 3. 增加英文版自傳數據內容
  Add autobiographical content in the English version.

• 4. 適當增加背景音樂內容、音效
  Appropriately enhance background music and sound effects.

免責聲明| Disclaimer

本項目僅供學習和研究使用。使用者須遵守當地的法律法規，包括但不限於DMCA 相關法律。我們不對任何非法使用承擔責任。

This project is for research and learning purposes only. Users must comply with local laws and regulations, including but not limited to DMCA-related laws. We do not take any responsibility for illegal usage.

技術鳴謝| Credits

本項目基於以下開源項目構建：

• VITS2
• Bert-VITS2
• GPT VITS
• GPT-SoVITS
• Fish Speech