Reverb Asr

🚀 Reverb ASR Model

Rev's Reverb ASR is an accurate English automatic speech recognition system trained on a large corpus of human - transcribed audio, offering flexible output styles and multiple decoding options.

🚀 Quick Start

Details on the model, its performance, and more are available on Arxiv.

Clone the model

The Reverb ASR model v1 is stored in this model repository.

Install inference requirements

See our inference code at https://github.com/revdotcom/reverb/tree/main/asr

✨ Features

Transcription Style Options

Reverb ASR was trained to produce transcriptions in either a verbatim style, in which every word is transcribed as spoken; or a non - verbatim style, in which disfluencies may be removed from the transcript.

Users can specify Reverb ASR's output style with the verbatimicity parameter. 1 corresponds to a verbatim transcript and 0 corresponds to a non - verbatim transcript. Values between 0 and 1 are accepted and may correspond to a semi - non - verbatim style. See our demo [here](https://huggingface.co/spaces/Revai/reverb - asr - demo) to test the verbatimicity parameter with your own audio.

Decoding Options

Reverb ASR uses the joint CTC/attention architecture described here and [here](https://www.rev.com/blog/speech - to - text - technology/what - makes - revs - v2 - best - in - class), and supports multiple modes of decoding. Users can specify one or more modes of decoding to recognize_wav.py and separate output directories will be created for each decoding mode.

Decoding options are:

• attention
• ctc_greedy_search
• ctc_prefix_beam_search
• attention_rescoring
• joint_decoding

💻 Usage Examples

Basic Usage

python wenet/bin/recognize_wav.py --config model.yaml \
    --checkpoint model.pt \
    --audio hello_world.wav \
    --modes ctc_prefix_beam_search attention_rescoring \
    --gpu 0 \
    --verbatimicity 1.0

Or check out our demo [on HuggingFace](https://huggingface.co/spaces/Revai/reverb - asr - demo).

📚 Documentation

The folder wenet is taken a fork of the [WeNet](https://github.com/wenet - e2e/wenet) repository, with some modifications made for Rev - specific architecture.

The folder wer_evaluation contains instructions and code for running different benchmark utlities. These scripts are not specific to the Reverb architecture.

📊 Benchmarking

See the wer_evaluation folder of https://github.com/revdotcom/reverb/tree/main/asr for details and results.

📄 License

See LICENSE for details.

📖 Cite this Model

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}, 
}

🙏 Acknowledgments

Special thanks to the Wenet team for their work and for making it available under an open - source license.