库名称: transformers
标签:

• 文本转语音
• 标注
  语言:
• 英语
  管道标签: 文本转语音
  推理: 否
  数据集:
• ylacombe/jenny-tts-tagged-v1
• reach-vb/jenny_tts_dataset

Parler-TTS Large v1 - Jenny

• Colab上的微调指南:

Parler-TTS Large v1 的微调版本，基于30小时单说话者高质量Jenny（她是爱尔兰人☘️）数据集，适合训练TTS模型。
使用方法与Parler-TTS v1基本相同，只需在语音描述中指定关键词“Jenny”：

使用方法

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

然后可以使用以下推理代码片段运行模型：

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

引用

如果您觉得这个仓库有用，请考虑引用本作品以及原始的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

许可证 - 在通过此数据集生成音频的软件/网站/项目/界面（包括语音界面）中，必须注明归属。归属意味着：必须将语音称为“Jenny”，并在实际可行的情况下称为“Jenny (Dioco)”。分发生成的音频片段时不需要注明归属（尽管欢迎这样做）。允许商业用途。不要做不公平的事情，比如声称数据集是你自己的。没有其他限制。