Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Zyphra
/
Zonos-v0.1-transformer

Text-to-Speech
Zonos
Safetensors
Model card Files Files and versions
xet
Community
11

Instructions to use Zyphra/Zonos-v0.1-transformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Zonos

    How to use Zyphra/Zonos-v0.1-transformer with Zonos:

    # pip install git+https://github.com/Zyphra/Zonos.git
    import torchaudio
    from zonos.model import Zonos
    from zonos.conditioning import make_cond_dict
    
    model = Zonos.from_pretrained("Zyphra/Zonos-v0.1-transformer", device="cuda")
    
    wav, sr = torchaudio.load("speaker.wav")           # 5-10s reference clip
    speaker = model.make_speaker_embedding(wav, sr)
    
    cond  = make_cond_dict(text="Hello, world!", speaker=speaker, language="en-us")
    codes = model.generate(model.prepare_conditioning(cond))
    
    audio = model.autoencoder.decode(codes)[0].cpu()
    torchaudio.save("sample.wav", audio, model.autoencoder.sampling_rate)
    
  • Notebooks
  • Google Colab
  • Kaggle
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

This doesn't seem to work at the moment

#12 opened 8 months ago by
svuille

German with english accent?

#11 opened about 1 year ago by
fesrgs

What research is Zonos inspired by? (maybe some info to complement blog post?)

#10 opened about 1 year ago by
Impulse2000

Zonos is excellent, but there's one major issue that makes it's use impractical -- the "uh" (and "um") sounds weren't labelled in the dataset

#7 opened about 1 year ago by
jattoedaltni

Docker compose not exposing ports

#6 opened over 1 year ago by
mnemic

zonos not installing backbone

#5 opened over 1 year ago by
mnemic

espeak not installed on your system

1
#4 opened over 1 year ago by
triumphlj

Colab notebook

๐Ÿ‘ 2
3
#3 opened over 1 year ago by
sardorb3k

Streaming support / batch inference?

๐Ÿ‘๐Ÿ‘€ 5
3
#2 opened over 1 year ago by
brainofchild

Install Zonos Locally - Step by Step Tutorial Video

โค๏ธ 6
#1 opened over 1 year ago by
fahdmirzac
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs