Giters

mozilla / DeepSpeech

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How I execute convert_graphdef_memmapped_format

luis-vera opened this issue · comments

commented

Hi everybody:

I want you to tell that I downloaded convert_graphdef_memmapped_format using taskcluster.py as you mentioned in documentation. I trainned my own model and I got my PB file. Th problem is trying to convert it in PBMM file.

I tried on Centos as you indicate in documentarion, this is:

convert_graphdef_memmapped_format --in_graph=output_graph.pb --out_graph=output_graph.pbmm

But the error message was:

[root@SErverTest Documentos]# convert_graphdef_memmapped_format output_graph.pb
-bash: convert_graphdef_memmapped_format: no se encontró la orden

[root@SErverTest Documentos]# bash convert_graphdef_memmapped_format --in_graph=output_graph.pb --out_graph=output_graph.pbmm
convert_graphdef_memmapped_format: convert_graphdef_memmapped_format: no se puede ejecutar el fichero binario

I tried the same step on Windows 10 but the problem was the same:

"convert_graphdef_memmapped_format" no se reconoce como un comando interno o externo,
programa o archivo por lotes ejecutable.

How can I execute this program for getting the PBMM model file?

Thank's a lot for your help

commented

Please use Discourse for support, this is not a bug.