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

ghananlpcommunity
/
ghana-tts-72k

Text-to-Speech
VoxCPM
Safetensors
ghana-tts
ghanaian-languages
Model card Files Files and versions
xet
Community
1

Instructions to use ghananlpcommunity/ghana-tts-72k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • VoxCPM

    How to use ghananlpcommunity/ghana-tts-72k with VoxCPM:

    import soundfile as sf
    from voxcpm import VoxCPM
    
    model = VoxCPM.from_pretrained("ghananlpcommunity/ghana-tts-72k")
    
    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
ghana-tts-72k
8.14 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 15 commits
michsethowusu's picture
michsethowusu
Update README.md
6b984af verified about 1 month ago
  • prompt_audio
    Prompt audio batch 3 5 months ago
  • .gitattributes
    2.58 kB
    Prompt audio batch 3 5 months ago
  • README.md
    1.22 kB
    Update README.md about 1 month ago
  • audiovae.pth

    Detected Pickle imports (3)

    • "torch.FloatStorage",
    • "collections.OrderedDict",
    • "torch._utils._rebuild_tensor_v2"

    What is a pickle import?

    301 MB
    xet
    Upload audiovae.pth with huggingface_hub 5 months ago
  • config.json
    2.6 kB
    Upload config.json with huggingface_hub 5 months ago
  • model.safetensors
    2.61 GB
    xet
    Upload model.safetensors with huggingface_hub 5 months ago
  • optimizer.pth

    Detected Pickle imports (3)

    • "torch.FloatStorage",
    • "torch._utils._rebuild_tensor_v2",
    • "collections.OrderedDict"

    What is a pickle import?

    5.22 GB
    xet
    Upload optimizer.pth with huggingface_hub 5 months ago
  • scheduler.pth

    Pickle imports

    • No problematic imports detected

    What is a pickle import?

    1.47 kB
    xet
    Upload scheduler.pth with huggingface_hub 5 months ago
  • special_tokens_map.json
    1.63 kB
    Upload special_tokens_map.json with huggingface_hub 5 months ago
  • tokenizer.json
    3.68 MB
    Upload tokenizer.json with huggingface_hub 5 months ago
  • tokenizer_config.json
    4.95 kB
    Upload tokenizer_config.json with huggingface_hub 5 months ago
  • training_state.json
    15 Bytes
    Upload training_state.json with huggingface_hub 5 months ago