Views
No views yet
pip install git+https://github.com/huggingface/parler-tts.git1import torch
2from parler_tts import ParlerTTSForConditionalGeneration
3from transformers import AutoTokenizer
4import soundfile as sf
5
6device = "cuda:0" if torch.cuda.is_available() else "cpu"
7
8model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler-mini-v1-jenny").to(device)
9tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler-mini-v1-jenny")
10
11prompt = "Hey, how are you doing today? My name is Jenny, and I'm here to help you with any questions you have."
12description = "Jenny speaks at an average pace with an animated delivery in a very confined sounding environment with clear audio quality."
13
14input_ids = tokenizer(description, return_tensors="pt").input_ids.to(device)
15prompt_input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
16
17generation = model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids)
18audio_arr = generation.cpu().numpy().squeeze()
19sf.write("parler_tts_out.wav", audio_arr, model.config.sampling_rate)@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}
}