---
title: XTTS-v2-trump
canonical_url: "https://www.modelscope.cn/models/zeizeiv9/XTTS-v2-trump"
md_url: "https://www.modelscope.cn/models/zeizeiv9/XTTS-v2-trump.md"
repository: zeizeiv9/XTTS-v2-trump
last_updated: 2024-03-12
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
library_name:
  - pytorch
frameworks:
  - Pytorch
downloads: 214
stars: 3
---

# XTTS-v2-trump

> XTTS-v2-trump - zeizeiv9 在 ModelScope 开源的模型。XTTS-v2-trump 用了特朗普三个小时的语音预料，微调XTTS-v2模型

- **Repository**: zeizeiv9/XTTS-v2-trump
- **Tasks**: text-to-speech
- **Downloads**: 214
- **Stars**: 3
- **Last updated**: 2024-03-12

Source: https://www.modelscope.cn/models/zeizeiv9/XTTS-v2-trump

---

# XTTS-v2-trump
- 用了特朗普三个小时的语音预料，微调XTTS-v2模型

# 使用方法

## 安装包
```code
$ pip install TTS 
$ git clone https://github.com/coqui-ai/TTS
$ cd TTS
$ pip install -e .
```

## 推理
```python
import os
import torch
import torchaudio
from TTS.tts.configs.xtts_config import XttsConfig
from TTS.tts.models.xtts import Xtts

print("Loading model...")
config = XttsConfig()
config.load_json("config.json")
model = Xtts.init_from_config(config)
model.load_checkpoint(config, checkpoint_dir="XTTS-v2-trump", use_deepspeed=True)
model.cuda()

print("Computing speaker latents...")
gpt_cond_latent, speaker_embedding = model.get_conditioning_latents(audio_path=["reference.wav"])

print("Inference...")
out = model.inference(
    "It took me quite a long time to develop a voice and now that I have it I am not going to be silent.",
    "en",
    gpt_cond_latent,
    speaker_embedding,
    temperature=0.7, # Add custom parameters here
)
torchaudio.save("xtts.wav", torch.tensor(out["wav"]).unsqueeze(0), 24000)
```