reazonspeech-espnet-v1 is an ESPnet model trained for Japanese automatic speech recognition (ASR).

  • This model was trained on 15,000 hours of ReazonSpeech corpus.
  • Make sure that your audio file is sampled at 16khz when using this model.

For more details, please visit the official project page.

Downloads last month
Hosted inference API
This model can be loaded on the Inference API on-demand.

Dataset used to train reazon-research/reazonspeech-espnet-v1