`harmoni_stt.deepspeech_client`

Module Contents

Classes

DeepSpeechClient

Attributes

class harmoni_stt.deepspeech_client.DeepSpeechClient(model_file_path, scorer_path, alpha, beta, beam_width, t_wait=0.5)

property is_final

property is_streaming

process_audio(in_data): Passes a chunk of audio for the DeepSpeech stream to process

start_stream(): Starts DeepSpeech streaming inference state if it is not already open.

finish_stream(): Ends DeepSpeech streaming inference state if still open. Returns the transcribed text.

restart_stream()

harmoni_stt.deepspeech_client.model_dir