geniusrise/audio

Issues

• Abstract out inference and batch inference - audio

  #5 opened 6 months ago by ixaxaar
  0

• Add grpc and graphql endpoints

  #18 opened 8 months ago by ixaxaar
  0

• Integrate TorchDistributor based fine-tuning and inference on spark

  #15 opened 9 months ago by ixaxaar
  0

• Support OAUTH token introspection in APIs

  #14 opened 9 months ago by ixaxaar
  0

• Add K-V cache, more options for compilation

  #13 opened 9 months ago by ixaxaar
  0

• Add faster whisper for speech to text

  #9 opened 9 months ago by ixaxaar
  0

• Integrate faster-whisper for whisper family of models

  #12 opened 9 months ago by ixaxaar
  0

• Add whisper.cpp for speech to text

  #10 opened 9 months ago by ixaxaar
  0

• Make bulk inference for speech to text batched

  #8 opened 9 months ago by ixaxaar
  0

• Make bulk inference for text to speech batched

  #7 opened 9 months ago by ixaxaar
  0

• Implement streaming inference - audio

  #3 opened 9 months ago by ixaxaar
  0

• Implement batching for APIs - audio

  #4 opened 9 months ago by ixaxaar
  0

• Add support for local models for whisper.cpp in audio

  #6 opened 9 months ago by ixaxaar
  0