Precision Mode#

This tutorial is available as an IPython notebook at malaya-speech/example/precision-mode.

Let say you want to run the model in FP16, or FP64.

[1]:

import malaya_speech
import logging
logging.basicConfig(level = logging.INFO)

Use specific precision for specific model#

To do that, pass precision_mode parameter to any load model function in Malaya-Speech,

malaya_speech.gender.deep_model(model = 'vggvox-v2', precision_mode = 'FP16')

Supported precision mode is {'BFLOAT16', 'FP16', 'FP32', 'FP64'}, default is FP32, check code at https://github.com/huseinzol05/malaya-boilerplate/blob/main/malaya_boilerplate/frozen_graph.py

[8]:

gender = malaya_speech.gender.deep_model(model = 'vggvox-v2')
# gender_fp16 = malaya_speech.gender.deep_model(model = 'vggvox-v2', precision_mode = 'FP16')

INFO:root:running gender/vggvox-v2 using device /device:CPU:0

Not all operations supported FP16.