---
title: latin_SpeechT5
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/latin_SpeechT5"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/latin_SpeechT5.md"
repository: AI-ModelScope/latin_SpeechT5
last_updated: 2025-10-13
license: cc-by-4.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - vits
architectures:
  - VitsModelForPreTraining
base_model:
  - microsoft/speecht5_tts
base_model_relation: finetune
parameters: 166.1M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - la
downloads: 97
stars: 0
---

# latin_SpeechT5

> latin_SpeechT5 - AI-ModelScope 在 ModelScope 开源的模型。Latin SpeechT5 - Ken This model is a fine-tuned version of microsoft/speech-t5 on the Latin language with 67 hours of audio from Vox Classica

AI-ModelScope/latin_SpeechT5 是 ModelScope 魔搭社区上的 166.1M 参数text-to-speech模型，采用 cc-by-4.0 许可，基于 microsoft/speecht5_tts 构建。

- **Repository**: AI-ModelScope/latin_SpeechT5
- **License**: cc-by-4.0
- **Tasks**: text-to-speech
- **Parameters**: 166.1M
- **Base model**: microsoft/speecht5_tts
- **Downloads**: 97
- **Stars**: 0
- **Last updated**: 2025-10-13

Source: https://www.modelscope.cn/models/AI-ModelScope/latin_SpeechT5

---

# Latin SpeechT5 - Ken
This model is a fine-tuned version of [microsoft/speech-t5](https://huggingface.co/microsoft/speecht5_tts) on the Latin language with 67 hours of audio from [Vox Classica](https://huggingface.co/datasets/Ken-Z/Latin-Audio)

Try this model directly in your browser: [TTS Demo](https://huggingface.co/spaces/ken-z/latin_speecht5-tts)