How to use Deepspeech 0.6 with Python on Windows

jfenigan · December 24, 2019, 8:17pm

Hello!
I have recently upgraded Deepspeech from version 0.5 to 0.6 on Python, Windows. I reckon that numerous things have changed and I cannot figure out how to implement the new version in my pipeline.

Previously I could do the following:

import deepspeech_example as deepex
dsmodel = deepex.getModel()
transcription = deepex.speechToText(audio, dsmodel)

that would yield the transcription of the audio. How can I replicate this now with the new version? Are there any updated examples or tutorials?

carlfm01 · December 25, 2019, 3:17am

Hi,

Examples: https://github.com/mozilla/DeepSpeech-examples

github.com

mozilla/DeepSpeech-examples/blob/a07a83c2f209271bbc0eb238da167f3400aa9202/vad_transcriber/wavTranscriber.py#L23




@Retval
Returns a list [DeepSpeech Object, Model Load Time, LM Load Time]
'''
def load_model(models, lm, trie):
    BEAM_WIDTH = 500
    LM_ALPHA = 0.75
    LM_BETA = 1.85


    model_load_start = timer()
    ds = Model(models, BEAM_WIDTH)
    model_load_end = timer() - model_load_start
    logging.debug("Loaded model in %0.3fs." % (model_load_end))


    lm_load_start = timer()
    ds.enableDecoderWithLM(lm, trie, LM_ALPHA, LM_BETA)
    lm_load_end = timer() - lm_load_start
    logging.debug('Loaded language model in %0.3fs.' % (lm_load_end))


    return [ds, model_load_end, lm_load_end]

jfenigan · December 25, 2019, 6:16pm

Thank you, I will give this a try.