Reverb Diarization V2

🚀 Reverb Diarization V2

Reverb Diarization V2 is an automatic speech recognition model that significantly improves the Word Diarization Error Rate (WDER) compared to the baseline model.

🚀 Quick Start

Details on the model, its performance, and more are available on Arxiv. For more information on how to run this diarization model, see https://github.com/revdotcom/reverb/tree/main/diarization

Reverb Diarization V2 provides a 22.25% relative improvement in WDER (Word Diarization Error Rate) compared to the baseline pyannote3.0 model, evaluated on over 1,250,000 tokens across five different test suites.

💻 Usage Examples

Basic Usage

# taken from https://huggingface.co/pyannote/speaker-diarization-3.1 - see for more details
# instantiate the pipeline
from pyannote.audio import Pipeline
pipeline = Pipeline.from_pretrained(
  "Revai/reverb-diarization-v2",
  use_auth_token="HUGGINGFACE_ACCESS_TOKEN_GOES_HERE")

# run the pipeline on an audio file
diarization = pipeline("audio.wav")

# dump the diarization output to disk using RTTM format
with open("audio.rttm", "w") as rttm:
    diarization.write_rttm(rttm)

📚 Documentation

If you use this model, please use the following citation:

@misc{bhandari2024reverbopensourceasrdiarization,
      title={Reverb: Open-Source ASR and Diarization from Rev}, 
      author={Nishchal Bhandari and Danny Chen and Miguel Ángel del Río Fernández and Natalie Delworth and Jennifer Drexler Fox and Migüel Jetté and Quinten McNamara and Corey Miller and Ondřej Novotný and Ján Profant and Nan Qin and Martin Ratajczak and Jean-Philippe Robichaud},
      year={2024},
      eprint={2410.03930},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2410.03930}, 
}

📄 License

See LICENSE for details.