👂 🎴 🕸️
Hope
You
liked
it
and
let
'
s
stay
in
touch
<
br
/><
br
/>
Daniel
&
Hyungjoong
 <
br
/><
br
/>
daniel
@
udk
-
berlin
.
de
hjk
@
udk
-
berlin
.
de
<
br
/><
br
/>@
DigiEduBerlin
<
br
/><
br
/>
https
://
github
.
com
/
hromi
/
lesen
-
mikroserver
please
turn
off
tutorial
raspberrys
with
a
voiceshell
command
„
halt
“
Let
'
s
load
some
new
scorers
and
see
how
systems
perform
.
<
p
class
=
„
fragment
“
>
Please
create
a
list
of
10
-
50
tokens
relevant
to
Your
domain
of
interest
and
mail
them
to
daniel
@
udk
-
berlin
.
de
and
hjk
@
udk
-
berlin
.
de
''
we
will
create
You
a
microscopic
language
model
(
scorer
)
out
of
it
.
p
><
p
class
=
„
fragment
“
>
Help
extending
the
„
VoiceShell
“
dataset
by
doing
recordings
here
:
https
://
fibel
.
digital
/
22354
(
again
''
login
with
l
:
demo
-
tutorial
p
:
takarthbr
)
p
><
p
class
=
„
fragment
“
>
Feel
free
not
to
do
anything
or
leave
the
room
p
>
Please
connect
to
Hotspot
FibelNet
<
br
/><
br
/>
password
:
cirrostratus
<
br
/><
br
/>
then
try
to
connect
to
one
two
Pi4s
we
made
available
for
You
<
br
/><
br
/>
ssh
demo
-
tutorial
@
tutorial0
.
local
<
br
/><
br
/>
or
 <
br
/><
br
/>
ssh
demo
-
tutorial
@
tutorial1
.
local
<
br
/><
br
/>
password
: 
takarthbr
<
p
class
=
„
fragment
“
>
the
least
efficient
(
1
-
3
Watts
...)
universal
turing
machine
out
there
p
><
p
class
=
„
fragment
“
>
armv6
p
><
p
class
=
„
fragment
“
>
1GHz
512
GB
RAM
p
>
<
p
class
=
„
fragment
“
>
8
-
core
ARM
v8
.
2
64
-
bit
CPU
(
aarch64
)
;
32
GB
RAM
; 
512
-
core
Volta
GPU
with
Tensor
Cores
p
><
p
class
=
„
fragment
“
>
CUDA
-
support
p
><
p
class
=
„
fragment
“
>
every
now
''
NVIDIA
releases
an
debian
-
based
package
(
i
.
e
.
Linux4Tegra
''
L4t
)
with
all
packages
You
need
packed
in
a
so
-
called
„
Jetpack
“
suite
p
>
<
p
class
=
„
fragment
“
>
full
-
fledged
universal
turing
machine
::
1
.
5
GHz
64
-
bit
quad
core
ARM
Cortex
-
A72
processor
''
on
-
board
802
.
11ac
Wi
-
Fi
''
Bluetooth
5
''
full
gigabit
Ethernet
''
two
USB
2
.
0
ports
''
two
USB
3
.
0
ports
''
1
–
8
GB
of
RAM
p
><
p
class
=
„
fragment
“
>
5volts
only
;
power
-
consumption
between
3
-
10
Watt
p
><
p
class
=
„
fragment
“
>
during
this
tutorial
''
You
will
interact
with
Raspi4
running
Raspbian
10
(
buster
)
32
-
bit
armv7l
p
>
Dramatis
personae
:<
p
class
=
„
fragment
“
>
https
://
github
.
com
/
mozilla
/
DeepSpeech
p
><
p
class
=
„
fragment
“
>
https
://
github
.
com
/
coqui
-
ai
/
STT
https
://
coqui
.
ai
/
models
p
><
p
class
=
„
fragment
“
>
https
://
gitlab
.
com
/
Jaco
-
Assistant
/
Scribosermo
Quartznet
model
p
><
p
class
=
„
fragment
“
>
Connectionist
Temporal
Classification
(
CTC
)
beam
search
p
><
p
class
=
„
fragment
“
>
Tensorflow
&
Tensorflow
Lite
p
><
p
class
=
„
fragment
“
>
Random
forests
(
treelite
)
p
>
Edge
computing
is
a
computing
paradigm
that
brings
computation
and
data
storage
closer
to
the
sources
of
data
.
Edge
computing
concentrates
on
servers
„
in
proximity
to
the
last
mile
network
“
.
<
div
><
br
>
div
><
div
><
br
>
div
><
div
>
Mündigkeit
div
>
Web
Primer
allows
wider
public
to
benefit
from
our
growing
collection
of
open
educational
resources
(
OERs
)
without
necessity
to
build
a
physical
Primer
.
Frontend
is
a
Progressive
Web
App
''
backend
is
a
quite
sophisticated
„
knowledge
graph
“
.
Artificial
Intelligence
''
speech
technologies
(
notably
automatic
speech
recognition
ASR
)
and
so
-
called
audio
-
text
play
an
important
role
.
Current
modules
:<
p
class
=
„
fragment
“
>👄
lesen
(
ASR
)
p
><
p
class
=
„
fragment
“
>👂
hören
(
multi
-
voice
)
p
><
p
class
=
„
fragment
“
>👩🏼
‍
💻
trainieren
and
💯
testen
(
human
-
machine
peer
learning
)
p
><
p
class
=
„
fragment
“
>🎴
memory
(
single
-
player
)
spielen
p
>
<
div
>
Personal
Primer
(
is
a
physical
''
do
-
it
-
yourself
(
DIY
)
book
-
like
(
embooked
)
Bildunginstrument
for
fostering
of
reading
skills
in
younger
pupils
and
informatic
skills
in
older
pupils
.
The
idea
is
simple
:<
p
class
=
„
fragment
“
>
older
and
/
or
more
expert
students
strenghten
their
informatic
competences
by
making
the
device
and
fine
-
tuning
acoustic
models
p
><
p
class
=
„
fragment
“
>
younger
ones
(
9
-
12
yrs
.)
pupils
strenghten
their
media
competence
by
producing
and
curating
(
audiotext
)
content
youngest
(
6
-
8
yrs
.)
p
><
p
class
=
„
fragment
“
>
pupils
use
the
device
to
strenghten
their
basic
literacy
(
e
.
g
.
reading
)
competence
p
>
div
>
[Impressum, Datenschutz, Login] Other subprojects of wizzion.com linkring: baumhaus.digital naadam.info refused.science puerto.life fibel.digital gardens.digital udk.ai kyberia.de giver.eu teacher.solar