Parler Tiny V1 Jenny

🚀 Parler-TTS Tiny v1 - Jenny

Parler-TTS Tiny v1 - Jenny 是 Parler-TTS Tiny v1 的微调版本，它基于 30 小时单说话人高质量 Jenny（她是爱尔兰人 ☘️）数据集 进行微调，适用于训练文本转语音（TTS）模型。使用方法与 Parler-TTS v1 大致相同，只需在语音描述中指定关键词 “Jenny” 即可。

• 在 Colab 上的微调指南：

🚀 快速开始

安装

pip install git+https://github.com/huggingface/parler-tts.git

使用示例

基础用法

import torch
from parler_tts import ParlerTTSForConditionalGeneration
from transformers import AutoTokenizer
import soundfile as sf

device = "cuda:0" if torch.cuda.is_available() else "cpu"

model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler-tiny-v1-jenny").to(device)
tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler-tiny-v1-jenny")

prompt = "Hey, how are you doing today? My name is Jenny, and I'm here to help you with any questions you have."
description = "Jenny speaks at an average pace with an animated delivery in a very confined sounding environment with clear audio quality."

input_ids = tokenizer(description, return_tensors="pt").input_ids.to(device)
prompt_input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)

generation = model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids)
audio_arr = generation.cpu().numpy().squeeze()
sf.write("parler_tts_out.wav", audio_arr, model.config.sampling_rate)

📚 详细文档

引用

如果您觉得这个仓库有用，请考虑引用这项工作以及原始的 Stability AI 论文：

@misc{lacombe-etal-2024-parler-tts,
  author = {Yoach Lacombe and Vaibhav Srivastav and Sanchit Gandhi},
  title = {Parler-TTS},
  year = {2024},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/huggingface/parler-tts}}
}

@misc{lyth2024natural,
      title={Natural language guidance of high-fidelity text-to-speech with synthetic annotations},
      author={Dan Lyth and Simon King},
      year={2024},
      eprint={2402.01912},
      archivePrefix={arXiv},
      primaryClass={cs.SD}
}

许可证

在使用此数据集根据用户操作生成音频的软件、网站、项目或界面（包括语音界面）中，必须进行归因。归因意味着：语音必须被称为 “Jenny”，并且在所有实际可行的情况下，称为 “Jenny (Dioco)”。在分发生成的音频片段时，不需要进行归因（尽管欢迎这样做）。允许商业使用。请勿做不公平的事情，例如声称该数据集是您自己的。没有其他限制。

📦 相关信息