Parler Mini V1 Jenny

🚀 Parler-TTS Mini v1 - Jenny

Parler-TTS Mini v1 - Jenny is a fine - tuned text - to - speech model. It's based on the 30 - hours single - speaker high - quality Jenny dataset, suitable for TTS model training and has similar usage to Parler - TTS v1.

• Fine - tuning guide on Colab:

🚀 Quick Start

This is a fine - tuned version of Parler - TTS Mini v1 on the [30 - hours single - speaker high - quality Jenny (she's Irish ☘️) dataset](https://github.com/dioco - group/jenny - tts - dataset). Its usage is more or less the same as Parler - TTS v1. You just need to specify the keyword “Jenny” in the voice description.

📦 Installation

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

💻 Usage Examples

Basic Usage

You can use the model with the following inference snippet:

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

📚 Documentation

Datasets

• ylacombe/jenny - tts - tagged - v1
• reach - vb/jenny_tts_dataset

Tags

• text - to - speech
• annotation

Pipeline Tag

text - to - speech

Inference

false

Library Name

transformers

📄 Citation

If you found this repository useful, please consider citing this work and also the original Stability AI paper:

@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}
}

📄 License

Attribution is required in software/websites/projects/interfaces (including voice interfaces) that generate audio in response to user action using this dataset. Attribution means: the voice must be referred to as "Jenny", and where at all practical, "Jenny (Dioco)". Attribution is not required when distributing the generated clips (although welcome). Commercial use is permitted. Don't do unfair things like claim the dataset is your own. No further restrictions apply.