templates
/

automatic-speech-recognition

Automatic Speech Recognition

Model card Files Files and versions Community

automatic-speech-recognition / pipeline.py

osanseviero's picture

osanseviero HF staff

Create pipeline.py

e7af9af almost 3 years ago

raw history blame contribute delete

No virus

1.04 kB

	from typing import Dict
	import numpy as np

	class PreTrainedPipeline():
	def __init__(self, path=""):
	# IMPLEMENT_THIS
	# Preload all the elements you are going to need at inference.
	# For instance your model, processors, tokenizer that might be needed.
	# This function is only called once, so do all the heavy processing I/O here"""
	self.sampling_rate = # IMPLEMENT THIS

	raise NotImplementedError(
	"Please implement PreTrainedPipeline __init__ function"
	)

	def __call__(self, inputs: np.array)-> Dict[str, str]:
	"""
	Args:
	inputs (:obj:`np.array`):
	The raw waveform of audio received. By default at 16KHz.
	Return:
	A :obj:`dict`:. The object return should be liked {"text": "XXX"} containing
	the detected text from the input audio.
	"""
	# IMPLEMENT_THIS
	raise NotImplementedError(
	"Please implement PreTrainedPipeline __call__ function"
	)