This supplies the main interface for using ReazonSpeech ESPnet models.
More information can be found at https://research.reazon.jp/projects/ReazonSpeech
$ git clone https://github.com/reazon-research/ReazonSpeech $ pip install ReazonSpeech/pkg/espnet-asr
from reazonspeech.espnet.asr import load_model, transcribe, audio_from_path
# Load ReazonSpeech model from Hugging Face
model = load_model()
# Read a local audio file
audio = audio_from_path("speech.wav")
# Recognize speech
ret = transcribe(model, audio)$ reazonspeech-espnet-asr speech.wav
Use -h to show a full help.
$ reazonspeech-espnet-asr -h