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

  • Log In
  • Sign Up

moonbox-dev
/
VoxCPM2-ONNX

Text-to-Speech
ONNX
VoxCPM
moonbox
onnxruntime
voxcpm2
voice-cloning
48khz
Model card Files Files and versions
xet
Community

Instructions to use moonbox-dev/VoxCPM2-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • VoxCPM

    How to use moonbox-dev/VoxCPM2-ONNX with VoxCPM:

    import soundfile as sf
    from voxcpm import VoxCPM
    
    model = VoxCPM.from_pretrained("moonbox-dev/VoxCPM2-ONNX")
    
    wav = model.generate(
        text="VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech.",
        prompt_wav_path=None,      # optional: path to a prompt speech for voice cloning
        prompt_text=None,          # optional: reference text
        cfg_value=2.0,             # LM guidance on LocDiT, higher for better adherence to the prompt, but maybe worse
        inference_timesteps=10,   # LocDiT inference timesteps, higher for better result, lower for fast speed
        normalize=True,           # enable external TN tool
        denoise=True,             # enable external Denoise tool
        retry_badcase=True,        # enable retrying mode for some bad cases (unstoppable)
        retry_badcase_max_times=3,  # maximum retrying times
        retry_badcase_ratio_threshold=6.0, # maximum length restriction for bad case detection (simple but effective), it could be adjusted for slow pace speech
    )
    
    sf.write("output.wav", wav, 16000)
    print("saved: output.wav")
  • Notebooks
  • Google Colab
  • Kaggle
VoxCPM2-ONNX / fp16
5.11 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
jennyxue's picture
jennyxue
fp16 build of VoxCPM2
dc84c55 verified 1 day ago
  • base_lm.onnx
    17.3 MB
    xet
    fp16 build of VoxCPM2 1 day ago
  • base_lm.onnx.data
    2.88 GB
    xet
    fp16 build of VoxCPM2 1 day ago
  • estimator.onnx
    425 MB
    xet
    fp16 build of VoxCPM2 1 day ago
  • feat_encoder.onnx
    437 MB
    xet
    fp16 build of VoxCPM2 1 day ago
  • fsq.onnx
    4.2 MB
    xet
    fp16 build of VoxCPM2 1 day ago
  • fusion.onnx
    16.8 MB
    xet
    fp16 build of VoxCPM2 1 day ago
  • heads.onnx
    16.8 MB
    xet
    fp16 build of VoxCPM2 1 day ago
  • multichar_tokens.json
    236 kB
    fp16 build of VoxCPM2 1 day ago
  • pipeline.py
    9.51 kB
    fp16 build of VoxCPM2 1 day ago
  • residual_lm.onnx
    118 kB
    xet
    fp16 build of VoxCPM2 1 day ago
  • residual_lm.onnx.data
    822 MB
    xet
    fp16 build of VoxCPM2 1 day ago
  • text_embed.onnx
    301 MB
    xet
    fp16 build of VoxCPM2 1 day ago
  • tokenizer.json
    3.68 MB
    fp16 build of VoxCPM2 1 day ago
  • vae_decoder.onnx
    91.8 MB
    xet
    fp16 build of VoxCPM2 1 day ago
  • vae_encoder.onnx
    96.3 MB
    xet
    fp16 build of VoxCPM2 1 day ago