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
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

tiny-aya-translate
/
tr-hi-s2st-v0.1

Audio-to-Audio
PEFT
Safetensors
Moshi
Turkish
Hindi
speech-to-speech-translation
speech-translation
simultaneous-translation
lora
mimi
tpu
tinyaya
Model card Files Files and versions
xet
Community

Instructions to use tiny-aya-translate/tr-hi-s2st-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use tiny-aya-translate/tr-hi-s2st-v0.1 with PEFT:

    Task type is invalid.
  • Moshi

    How to use tiny-aya-translate/tr-hi-s2st-v0.1 with Moshi:

    # pip install moshi
    # Run the interactive web server
    python -m moshi.server --hf-repo "tiny-aya-translate/tr-hi-s2st-v0.1"
    # Then open https://localhost:8998 in your browser
    # pip install moshi
    import torch
    from moshi.models import loaders
    
    # Load checkpoint info from HuggingFace
    checkpoint = loaders.CheckpointInfo.from_hf_repo("tiny-aya-translate/tr-hi-s2st-v0.1")
    
    # Load the Mimi audio codec
    mimi = checkpoint.get_mimi(device="cuda")
    mimi.set_num_codebooks(8)
    
    # Encode audio (24kHz, mono)
    wav = torch.randn(1, 1, 24000 * 10)  # [batch, channels, samples]
    with torch.no_grad():
        codes = mimi.encode(wav.cuda())
        decoded = mimi.decode(codes)
  • Notebooks
  • Google Colab
  • Kaggle
tr-hi-s2st-v0.1
2.55 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 7 commits
cataluna84's picture
cataluna84
Card: licence correction (CC-BY-NC-4.0) + lineage and code cross-links
f293bef verified about 2 months ago
  • peft_adapter
    Upload step_015000_final (v0.1.0) 3 months ago
  • .gitattributes
    1.52 kB
    initial commit 3 months ago
  • README.md
    13.2 kB
    Card: licence correction (CC-BY-NC-4.0) + lineage and code cross-links about 2 months ago
  • audio_heads.safetensors
    8.39 MB
    xet
    Upload step_015000_final (v0.1.0) 3 months ago
  • depth_decoder.safetensors
    1.43 GB
    xet
    Upload step_015000_final (v0.1.0) 3 months ago
  • metadata.json
    55 Bytes
    Upload step_015000_final (v0.1.0) 3 months ago
  • model_audio_embed.safetensors
    8.39 MB
    xet
    Upload step_015000_final (v0.1.0) 3 months ago
  • projection.safetensors
    16.8 MB
    xet
    Upload step_015000_final (v0.1.0) 3 months ago
  • text_embed.safetensors
    1.08 GB
    xet
    Upload step_015000_final (v0.1.0) 3 months ago