freetel-codec2 — sub 5 kbit/s open source voice codec

Re: [Freetel-codec2] Rade alternative training

[glen e. L. <gle...@co...>]

For anyone interested in Autoencoders,
I can recommend chapter 17 of "hands on machine learning with sckit"  
ISBN 978-1-492-03264-9
or
David  you might be able to recommend a good online , accessable source  ?

the following can provide some good starting points :

https://medium.com/search?q=understanding+autoencoders+
<https://medium.com/search?q=understanding+autoencoders+>
maybe:

https://medium.com/data-science/understanding-autoencoders-with-an-example-a-step-by-step-tutorial-693c3a4e9836
<https://medium.com/data-science/understanding-autoencoders-with-an-example-a-step-by-step-tutorial-693c3a4e9836>
For medium which I subscribe/donate to, non subs can access a small 
number of articles free


On 17/08/2025 06:59, david wrote:
> Hi Glen,
>
> Yes indeed it can be trained to any channel you like.  We've been doing
> some work for the VHF/UHF land mobile radio (LMR) space where it's
> trained to pass through analog FM radios (see freedv.org blog posts,
> search on BBFM).
>
> Greg - I suspect the final form of this technology arc will be
> something like you suggest, resulting in high quality speech at very
> low SNRs. Current work on RADE V2 has the ML doing the sync (e.g.
> equalisation for the HF channel, fine timing, frame sync) rather than

Re: [Freetel-codec2] Rade alternative training

[david <da...@ro...>]

Hi Glen,

Yes indeed it can be trained to any channel you like.  We've been doing
some work for the VHF/UHF land mobile radio (LMR) space where it's
trained to pass through analog FM radios (see freedv.org blog posts,
search on BBFM).

Greg - I suspect the final form of this technology arc will be
something like you suggest, resulting in high quality speech at very
low SNRs. Current work on RADE V2 has the ML doing the sync (e.g.
equalisation for the HF channel, fine timing, frame sync) rather than
classical DSP, so that can now be trained rather than designed for
specific channels.

- David

On Sat, 2025-08-16 at 16:36 +1000, glen english LIST wrote:
> Hi David
> Have just read all the papers..   as i read it , (
> https://arxiv.org/pdf/2505.06671) 
> 
>  we could alternatively train the system for say aurora channel
> characteristsics on 2m , or rainscatter characteristics on 10 GHz
> 
> and could expand or use different training sets for different
> propagation modes on different bands, 
> ....depending on how general they are.
> 
> IE this is a workiong deomonstration for AWGN and HF style multipath
> channels, but not at all limited it 
> 
> best regards
> -glen
> 
> 
> On 11/08/2025 16:44, david wrote:
> > Hi Richard,
> > 
> > Yes it certainly is planned, but as per the Radio Autoencoder page:
> 
> _______________________________________________
> Freetel-codec2 mailing list
> Fre...@li...
> https://lists.sourceforge.net/lists/listinfo/freetel-codec2

Re: [Freetel-codec2] Rade alternative training

[glen e. L. <gle...@co...>]

Greg, interesting though on speaker dependent fine tuned decoders (I 
think that's what you meant ?).  Would mean for you buddies you could 
store something different  and buy them another half dB on their 
transmit power bill.

and suitable implementation for some other optimised band/propagation 
might not even be OFDM, though that the PAPR 'problem' has been 
mitigated, might now be a more generalized implementation (although 
there wont be something for nothing).

fascinating . the use of bottleneck algorthmic contraints to control 
amplitude distribution...

wondering about embedded implementation...
According to the paper https://arxiv.org/pdf/2505.06671
Vocoder computational workload of about 300MMACS isnt too bad at all.

FARGIN paper  and site with FARGIN at 600 FLOPS sounds amazing
https://ahmed-fau.github.io/fargan_demo/


On 16/08/2025 17:12, Greg Maxwell wrote:
> There is also non-trivial channel specific DSP development likely 
> needed too, not just ML training-- as the ML still relies on the 
> receiver managing to sync and track the signal. Maybe a ML only 
> adjustment for a different channel would be better than doing nothing, 
> but it probably won't get particularly close to the results you'd get 
> with some more direct engineering.
>
> Another fun potential avenue that would avoid more of the human 
> engineered parts: -- for when you know the speaker, hold the RADE 
> encoder constant but fine tune the decoder for a particular parties 
> voice.  Might improve the threshold for intelligibility by some 
> fraction of the channel capacity wasted communicating that info, 
> entirely unlike the advanced decoding in WSJTX is able to exploit the 
> assumption that the callsign of the current message you're 
> receiving is more likely the callsign that you just called.
>
>
> On Sat, Aug 16, 2025 at 6:58 AM glen english LIST 
> <gle...@co...> wrote:
>
>     Hi David
>     Have just read all the papers..   as i read it ,
>     (https://arxiv.org/pdf/2505.06671)
>
>      we could alternatively train the system for say aurora channel
>     characteristsics on 2m , or rainscatter characteristics on 10 GHz
>
>     and could expand or use different training sets for different
>     propagation modes on different bands,
>     ....depending on how general they are.
>
>     IE this is a workiong deomonstration for AWGN and HF style
>     multipath channels, but not at all limited it
>
>     best regards
>     -glen
>

Re: [Freetel-codec2] Rade alternative training

[Greg M. <gma...@gm...>]

There is also non-trivial channel specific DSP development likely needed
too, not just ML training-- as the ML still relies on the receiver managing
to sync and track the signal.  Maybe a ML only adjustment for a different
channel would be better than doing nothing, but it probably won't get
particularly close to the results you'd get with some more direct
engineering.

Another fun potential avenue that would avoid more of the human engineered
parts: -- for when you know the speaker,  hold the RADE encoder constant
but fine tune the decoder for a particular parties voice.  Might improve
the threshold for intelligibility by some fraction of the channel capacity
wasted communicating that info, entirely unlike the advanced decoding in
WSJTX is able to exploit the assumption that the callsign of the current
message you're receiving is more likely the callsign that you just called.


On Sat, Aug 16, 2025 at 6:58 AM glen english LIST <gle...@co...>
wrote:

> Hi David
> Have just read all the papers..   as i read it , (
> https://arxiv.org/pdf/2505.06671)
>
>  we could alternatively train the system for say aurora channel
> characteristsics on 2m , or rainscatter characteristics on 10 GHz
>
> and could expand or use different training sets for different propagation
> modes on different bands,
> ....depending on how general they are.
>
> IE this is a workiong deomonstration for AWGN and HF style multipath
> channels, but not at all limited it
>
> best regards
> -glen
>
>
> On 11/08/2025 16:44, david wrote:
>
> Hi Richard,
>
> Yes it certainly is planned, but as per the Radio Autoencoder page:
>
> _______________________________________________
> Freetel-codec2 mailing list
> Fre...@li...
> https://lists.sourceforge.net/lists/listinfo/freetel-codec2
>

Re: [Freetel-codec2] Rade alternative training

[glen e. L. <gle...@co...>]

Hi David
Have just read all the papers..   as i read it , 
(https://arxiv.org/pdf/2505.06671)

  we could alternatively train the system for say aurora channel 
characteristsics on 2m , or rainscatter characteristics on 10 GHz

and could expand or use different training sets for different 
propagation modes on different bands,
....depending on how general they are.

IE this is a workiong deomonstration for AWGN and HF style multipath 
channels, but not at all limited it

best regards
-glen


On 11/08/2025 16:44, david wrote:
> Hi Richard,
>
> Yes it certainly is planned, but as per the Radio Autoencoder page:

Re: [Freetel-codec2] Rade release?

[Richard S. <hob...@gm...>]

On Mon, Aug 11, 2025 at 1:44 AM Mooneer Salem <mo...@gm...> wrote:

> Hi Richard,
>
> Per https://freedv.org/radio-autoencoder/ we recommend holding off on
> packaging until RADEV2 is released. Please let me know if you have any
> questions.
>

So my question is then if it appears that the current release of FreeDV
requires RADE (I did not see an option to disable it) then it's rather bad
form from a package maintainers point of view to require something that's
not released.

 What is the best course of action for me as the Fedora maintainer or
FreeDV/Codec2/lpcnet/etc?

Thanks,
Richard

[Freetel-codec2] [Announcement] FreeDV Activity Day - August 16-17, 2025

[Mooneer S. <mo...@gm...>]

Hi all,

This is a reminder that this month's FreeDV Activity Day is this coming
weekend. (As a reminder, Activity Day takes place on the third weekend of
every month.) This event will bring together people interested in HF
digital voice on the air for conversation and fun. Contacts using the
official application as well as ezDV, the SM1000 handheld microphone and
other supporting devices and applications are welcome.

*Event time:* 12AM Pacific time (0700Z) on August 16 to 11:59PM on August
17 (0659Z on August 18) (48 hours).

*Suggested frequencies:*
160 meters: 1.997 MHz
80 meters: 3.625, 3.643, 3.693, 3.697 MHz or 3.803 MHz
60 meters (in countries where allowed): 5.4035 MHz or 5.3665 MHz
40 meters: 7.177 MHz or 7.197 MHz
20 meters: 14.236 MHz or 14.240 MHz
17 meters: 18.118 MHz
15 meters: 21.313 MHz
12 meters: 24.933 MHz
10 meters: 28.330 or 28.720 MHz
10 GHz (for those in range of QO-100): 10489.640 MHz

(Note that LSB/DIGL is used below 10MHz as per current convention for voice
modes, USB/DIGU otherwise. 60 meters is of course USB/DIGU only.)

As this isn't a contest, there's no pressure to make contacts or send logs,
but you can always confirm QSOs via the usual means if you'd like (LoTW,
eQSL, QRZ, etc.) Enabling reporting (PSK Reporter and FreeDV Reporter) in
the FreeDV application and joining FreeDV Reporter and Discord are
recommended, however, so others can see that you're on the air and hearing
them (for instance, here's the current map of listeners). :D

Feel free to spread this far and wide among your local ham friends and
groups! :) Let me know if you have any questions about the event and
definitely post here if you have issues getting the application working
prior to the event.

Thanks,

-Mooneer K6AQ

Re: [Freetel-codec2] Question about voice.

[Mooneer S. <mo...@gm...>]

IIRC there has been research done on this in the past but unfortunately I
don't recall any links offhand. Hopefully someone else can provide some
links to relevant papers or similar.

-Mooneer K6AQ

On Mon, Aug 11, 2025, 10:39 AM Facility 406 <
fac...@br...> wrote:

> In analog AM/FM radios, the "voice passband" is generally considered to
> be 300-3000 Hz.
>
> Has anyone here looked at the ACTUAL frequency range of the average voice?
>
> Chances are, when people speak, they don't cover a 2700 Hz range, I'm
> thinking, maybe a few hundred Hz, at most.
>
> Kurt
>

[Freetel-codec2] Question about voice.

[Facility 4. <fac...@br...>]

In analog AM/FM radios, the "voice passband" is generally considered to 
be 300-3000 Hz.

Has anyone here looked at the ACTUAL frequency range of the average voice?

Chances are, when people speak, they don't cover a 2700 Hz range, I'm 
thinking, maybe a few hundred Hz, at most.

Kurt

Re: [Freetel-codec2] Rade release?

[david <da...@ro...>]

Hi Richard,

Yes it certainly is planned, but as per the Radio Autoencoder page:
https://freedv.org/radio-autoencoder/ FAQ (2):

"The current implementation is a hybrid of Python and C. We plan to
develop a stand alone C library suitable for inclusion in other SDRs.
We do not recommend, and will not be supporting packaging or
distribution of RADE V1 – it is an interim release and we are focused
on the next stages of RADE development."

However there are some Appimages available (inlcuding Fedora 42) for
freedv-gui: https://freedv.org/#download

Thanks,
David

On Sun, 2025-08-10 at 19:19 -0500, Richard Shaw wrote:
> I really want to work on getting FreeDV up to current standards on
> Fedora but it looks like Rade is now a requirement but it doesn't
> have an official release.
> 
> Is that something that's planned?
> 
> Thanks,
> RIchard
> KF5OIM
> _______________________________________________
> Freetel-codec2 mailing list
> Fre...@li...
> https://lists.sourceforge.net/lists/listinfo/freetel-codec2

Re: [Freetel-codec2] Rade release?

[Mooneer S. <mo...@gm...>]

Hi Richard,

Per https://freedv.org/radio-autoencoder/ we recommend holding off on
packaging until RADEV2 is released. Please let me know if you have any
questions.

Thanks,

-Mooneer K6AQ

On Sun, Aug 10, 2025 at 5:26 PM Richard Shaw <hob...@gm...> wrote:

> I really want to work on getting FreeDV up to current standards on Fedora
> but it looks like Rade is now a requirement but it doesn't have an
> official release.
>
> Is that something that's planned?
>
> Thanks,
> RIchard
> KF5OIM
> _______________________________________________
> Freetel-codec2 mailing list
> Fre...@li...
> https://lists.sourceforge.net/lists/listinfo/freetel-codec2
>

[Freetel-codec2] Rade release?

[Richard S. <hob...@gm...>]

I really want to work on getting FreeDV up to current standards on Fedora
but it looks like Rade is now a requirement but it doesn't have an
official release.

Is that something that's planned?

Thanks,
RIchard
KF5OIM

[Freetel-codec2] FreeDV 2.0.1 released

[Mooneer S. <mo...@gm...>]

Hi all,

FreeDV 2.0.1 has been released, containing bugfixes for issues discovered
after the release of version 2.0.0. It can be downloaded using the
following links:

Windows:
https://github.com/drowe67/freedv-gui/releases/download/v2.0.1/FreeDV-2.0.1-windows-x86_64.exe
macOS:
https://github.com/drowe67/freedv-gui/releases/download/v2.0.1/FreeDV.dmg
Linux AppImage (Ubuntu 22.04+, Fedora 42):
https://github.com/drowe67/freedv-gui/releases/download/v2.0.1/FreeDV-2.0.1-x86_64.AppImage

More information about this release can be found on the GitHub release
page: https://github.com/drowe67/freedv-gui/releases/tag/v2.0.1

Thanks,

-Mooneer K6AQ

[Freetel-codec2] [Announcement] FreeDV Activity Day - July 19-20, 2025

[Mooneer S. <mo...@gm...>]

Hi all,

This is a reminder that this month's FreeDV Activity Day is this coming
weekend. (As a reminder, Activity Day takes place on the third weekend of
every month.) This event will bring together people interested in HF
digital voice on the air for conversation and fun. Contacts using the
official application as well as ezDV, the SM1000 handheld microphone and
other supporting devices and applications are welcome.

*Event time:* 12AM Pacific time (0700Z) on July 19 to 11:59PM on July 20
(0659Z on July 21) (48 hours).

*Suggested frequencies:*
160 meters: 1.997 MHz
80 meters: 3.625, 3.643, 3.693, 3.697 MHz or 3.803 MHz
60 meters (in countries where allowed): 5.4035 MHz or 5.3665 MHz
40 meters: 7.177 MHz or 7.197 MHz
20 meters: 14.236 MHz or 14.240 MHz
17 meters: 18.118 MHz
15 meters: 21.313 MHz
12 meters: 24.933 MHz
10 meters: 28.330 or 28.720 MHz
10 GHz (for those in range of QO-100): 10489.640 MHz

(Note that LSB/DIGL is used below 10MHz as per current convention for voice
modes, USB/DIGU otherwise. 60 meters is of course USB/DIGU only.)

As this isn't a contest, there's no pressure to make contacts or send logs,
but you can always confirm QSOs via the usual means if you'd like (LoTW,
eQSL, QRZ, etc.) Enabling reporting (PSK Reporter and FreeDV Reporter) in
the FreeDV application and joining FreeDV Reporter and Discord are
recommended, however, so others can see that you're on the air and hearing
them (for instance, here's the current map of listeners). :D

Feel free to spread this far and wide among your local ham friends and
groups! :) Let me know if you have any questions about the event and
definitely post here if you have issues getting the application working
prior to the event.

Thanks,

-Mooneer K6AQ

[Freetel-codec2] Field Day tomorrow

[Mooneer S. <mo...@gm...>]

Hi all,

As you may be aware, the annual ARRL Field Day event is this weekend. This
makes the usual HF bands used for FreeDV extremely busy, which makes
contacts using it more difficult. I'd like to remind people (especially
since we've gotten a lot of new users recently) that FreeDV also has
calling frequencies on the WARC bands:

17 meters: 18.118 MHz
12 meters: 24.933 MHz

These two frequencies are useful as contest operation (including Field Day,
even though it's technically not a contest) is typically not allowed on
WARC bands. Additionally, in my experience, 17 meter propagation is
typically similar to 20 meter propagation as well. If you give the WARC
bands a try this weekend, let us know how it went!

Thanks,

-Mooneer K6AQ

Re: [Freetel-codec2] [Announcement] FreeDV Activity Day - June 21-22, 2025

[Mooneer S. <mo...@gm...>]

Correction: 3.850 MHz in the below list should be 3.803 MHz. This will be
corrected in subsequent announcements. The latest frequency list can always
be found on FreeDV Reporter ("Calling Frequencies" tab at
https://qso.freedv.org/).

-Mooneer K6AQ

On Fri, Jun 20, 2025 at 2:02 PM Mooneer Salem <mo...@gm...> wrote:

> Hi all,
>
> This is a reminder that this month's FreeDV Activity Day is this coming
> weekend. (As a reminder, Activity Day takes place on the third weekend of
> every month.) This event will bring together people interested in HF
> digital voice on the air for conversation and fun. Contacts using the
> official application as well as ezDV, the SM1000 handheld microphone and
> other supporting devices and applications are welcome.
>
> *Event time:* 12AM Pacific time (0700Z) on June 21 to 11:59PM on June 22
> (0659Z on June 23) (48 hours).
>
> *Suggested frequencies:*
> 160 meters: 1.997 MHz
> 80 meters: 3.625, 3.643, 3.693, 3.697 MHz or 3.850 MHz
> 60 meters (in countries where allowed): 5.4035 MHz or 5.3665 MHz
> 40 meters: 7.177 MHz or 7.197 MHz
> 20 meters: 14.236 MHz or 14.240 MHz
> 17 meters: 18.118 MHz
> 15 meters: 21.313 MHz
> 12 meters: 24.933 MHz
> 10 meters: 28.330 or 28.720 MHz
> 10 GHz (for those in range of QO-100): 10489.640 MHz
>
> (Note that LSB/DIGL is used below 10MHz as per current convention for
> voice modes, USB/DIGU otherwise. 60 meters is of course USB/DIGU only.)
>
> As this isn't a contest, there's no pressure to make contacts or send
> logs, but you can always confirm QSOs via the usual means if you'd like
> (LoTW, eQSL, QRZ, etc.) Enabling reporting (PSK Reporter
> and FreeDV Reporter) in the FreeDV application and joining FreeDV Reporter
> and Discord are recommended, however, so others can see that you're on the
> air and hearing them (for instance, here's the current map of listeners). :D
>
> Feel free to spread this far and wide among your local ham friends and
> groups! :) Let me know if you have any questions about the event and
> definitely post here if you have issues getting the application working
> prior to the event.
>
> Thanks,
>
> -Mooneer K6AQ
>

[Freetel-codec2] [Announcement] FreeDV Activity Day - June 21-22, 2025

[Mooneer S. <mo...@gm...>]

Hi all,

This is a reminder that this month's FreeDV Activity Day is this coming
weekend. (As a reminder, Activity Day takes place on the third weekend of
every month.) This event will bring together people interested in HF
digital voice on the air for conversation and fun. Contacts using the
official application as well as ezDV, the SM1000 handheld microphone and
other supporting devices and applications are welcome.

*Event time:* 12AM Pacific time (0700Z) on June 21 to 11:59PM on June 22
(0659Z on June 23) (48 hours).

*Suggested frequencies:*
160 meters: 1.997 MHz
80 meters: 3.625, 3.643, 3.693, 3.697 MHz or 3.850 MHz
60 meters (in countries where allowed): 5.4035 MHz or 5.3665 MHz
40 meters: 7.177 MHz or 7.197 MHz
20 meters: 14.236 MHz or 14.240 MHz
17 meters: 18.118 MHz
15 meters: 21.313 MHz
12 meters: 24.933 MHz
10 meters: 28.330 or 28.720 MHz
10 GHz (for those in range of QO-100): 10489.640 MHz

(Note that LSB/DIGL is used below 10MHz as per current convention for voice
modes, USB/DIGU otherwise. 60 meters is of course USB/DIGU only.)

As this isn't a contest, there's no pressure to make contacts or send logs,
but you can always confirm QSOs via the usual means if you'd like (LoTW,
eQSL, QRZ, etc.) Enabling reporting (PSK Reporter and FreeDV Reporter) in
the FreeDV application and joining FreeDV Reporter and Discord are
recommended, however, so others can see that you're on the air and hearing
them (for instance, here's the current map of listeners). :D

Feel free to spread this far and wide among your local ham friends and
groups! :) Let me know if you have any questions about the event and
definitely post here if you have issues getting the application working
prior to the event.

Thanks,

-Mooneer K6AQ

Re: [Freetel-codec2] [digitalvoice] FreeDV 2.0.0 released

[Mooneer S. <mo...@gm...>]

Hi Steve,

Currently we recommend use of Barry G4MKT's build script for
compilation/installation on Linux:
https://github.com/barjac/freedv-rade-build. This should work fine on a
Raspberry Pi 5 AFAIK but if not, please submit a GitHub issue to his repo.

Thanks,

-Mooneer K6AQ

On Wed, Jun 4, 2025 at 10:12 AM Steve Stroh <ste...@gm...> wrote:

> Will this version be released for use on a Raspberry Pi 5 as was demo’d at
> Hamvention 2025?
>
> Steve N8GNJ
>
> Steve Stroh (he / him / his)
> ste...@gm...
>
> For Amateur Radio / Zero Retries / Conference:
> *Steve Stroh N8GNJ*
> Editor
> *Zero Retries Newsletter*
> st...@ze... <//st...@ze...>
> https://www.zeroretries.org
> *Zero Retries Digital Conference 2025*
> https://www.zeroretries.org/p/conference
> Radios are Computers - With Antennas!
>
>
>
> On Tue, Jun 3, 2025 at 18:58 Mooneer Salem <mo...@gm...> wrote:
>
>> Hi all,
>>
>> FreeDV 2.0.0 has been released, containing the first official release of
>> the RADE V1 mode previously trialled over several preview releases. Radio
>> Autoencoder (RADE) technology is a new approach to sending speech over HF
>> radio. It combines Machine Learning (ML) with classical DSP to send high
>> quality speech over HF radio at SNRs as low as -2dB in a bandwidth of 1500
>> Hz. More information about Radio Autoencoder can be found at
>> https://freedv.org/radio-autoencoder/.
>>
>> As part of this effort, deprecated modes (700C, 800XA, 2020 and 2020B)
>> have been removed from the application. Additionally, this contains
>> numerous bug fixes and non-RADE specific enhancements from the last
>> official release (1.9.9.2).
>>
>> It can be downloaded using the following links:
>>
>> Windows:
>> https://github.com/drowe67/freedv-gui/releases/download/v2.0.0/FreeDV-2.0.0-windows-x86_64.exe
>> macOS:
>> https://github.com/drowe67/freedv-gui/releases/download/v2.0.0/FreeDV.dmg
>>
>> More information about this release, including changelog, can be found on
>> GitHub release page:
>> https://github.com/drowe67/freedv-gui/releases/tag/v2.0.0
>>
>> Thanks,
>>
>> -Mooneer K6AQ
>>
>> --
>> You received this message because you are subscribed to the Google Groups
>> "digitalvoice" group.
>> To unsubscribe from this group and stop receiving emails from it, send an
>> email to dig...@go....
>> To view this discussion visit
>> https://groups.google.com/d/msgid/digitalvoice/CAAzDfxPFVxO3B172pUZO9OrTfhP%3DZ%2B%3DvJSPCudhBKpZ7arUcOw%40mail.gmail.com
>> <https://groups.google.com/d/msgid/digitalvoice/CAAzDfxPFVxO3B172pUZO9OrTfhP%3DZ%2B%3DvJSPCudhBKpZ7arUcOw%40mail.gmail.com?utm_medium=email&utm_source=footer>
>> .
>>
> --
> You received this message because you are subscribed to the Google Groups
> "digitalvoice" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to dig...@go....
> To view this discussion visit
> https://groups.google.com/d/msgid/digitalvoice/CAGh1Bg4dnf2XXFXqC0xg1js3bSYY%3DAf%3Dk-Roa-3p8ihi6K%2BJWw%40mail.gmail.com
> <https://groups.google.com/d/msgid/digitalvoice/CAGh1Bg4dnf2XXFXqC0xg1js3bSYY%3DAf%3Dk-Roa-3p8ihi6K%2BJWw%40mail.gmail.com?utm_medium=email&utm_source=footer>
> .
>

Re: [Freetel-codec2] FreeDV 2.0.0 released

[<gar...@ya...>]

Hi all, 
  
  
  
  FreeDV 2.0.0 has been released, containing the first official release of 
the RADE V1 mode previously trialled over several preview releases. Radio 
Autoencoder (RADE) technology is a new approach to sending speech over HF 
radio. It combines Machine Learning (ML) with classical DSP to send high 
quality speech over HF radio at SNRs as low as -2dB in a bandwidth of 1500 
Hz. More information about Radio Autoencoder can be found at  
https://freedv.org/radio-autoencoder/ . 
  
  As part of this effort, deprecated modes (700C, 800XA, 2020 and 2020B) 
have been removed from the application. Additionally, this contains 
numerous bug fixes and non-RADE specific enhancements from the last 
official release (1.9.9.2). 
  
  It can be downloaded using the following links: 
  
  Windows:  
https://github.com/drowe67/freedv-gui/releases/download/v2.0.0/FreeDV-2.0.0-windows-x86_64.exe 
  
macOS:  
https://github.com/drowe67/freedv-gui/releases/download/v2.0.0/FreeDV.dmg 
  
  More information about this release, including changelog, can be found on 
GitHub release page:  
https://github.com/drowe67/freedv-gui/releases/tag/v2.0.0 
  
  
  
  
  
  Thanks, 
  
  
  
  
  -Mooneer K6AQ 
  
  
  
  
  Hi all, 
  
  
  
  FreeDV 2.0.0 has been released, containing the first official release of 
the RADE V1 mode previously trialled over several preview releases. Radio 
Autoencoder (RADE) technology is a new approach to sending speech over HF 
radio. It combines Machine Learning (ML) with classical DSP to send high 
quality speech over HF radio at SNRs as low as -2dB in a bandwidth of 1500 
Hz. More information about Radio Autoencoder can be found at  
https://freedv.org/radio-autoencoder/ . 
  
  As part of this effort, deprecated modes (700C, 800XA, 2020 and 2020B) 
have been removed from the application. Additionally, this contains 
numerous bug fixes and non-RADE specific enhancements from the last 
official release (1.9.9.2). 
  
  It can be downloaded using the following links: 
  
  Windows:  
https://github.com/drowe67/freedv-gui/releases/download/v2.0.0/FreeDV-2.0.0-windows-x86_64.exe 
  
macOS:  
https://github.com/drowe67/freedv-gui/releases/download/v2.0.0/FreeDV.dmg 
  
  More information about this release, including changelog, can be found on 
GitHub release page:  
https://github.com/drowe67/freedv-gui/releases/tag/v2.0.0 
  
  
  
  
  
  Thanks, 
  
  
  
  
  -Mooneer K6AQ 
  
  
  
  
  Hi all, 
  
  
  
  FreeDV 2.0.0 has been released, containing the first official release of 
the RADE V1 mode previously trialled over several preview releases. Radio 
Autoencoder (RADE) technology is a new approach to sending speech over HF 
radio. It combines Machine Learning (ML) with classical DSP to send high 
quality speech over HF radio at SNRs as low as -2dB in a bandwidth of 1500 
Hz. More information about Radio Autoencoder can be found at  
https://freedv.org/radio-autoencoder/ . 
  
  As part of this effort, deprecated modes (700C, 800XA, 2020 and 2020B) 
have been removed from the application. Additionally, this contains 
numerous bug fixes and non-RADE specific enhancements from the last 
official release (1.9.9.2). 
  
  It can be downloaded using the following links: 
  
  Windows:  
https://github.com/drowe67/freedv-gui/releases/download/v2.0.0/FreeDV-2.0.0-windows-x86_64.exe 
  
macOS:  
https://github.com/drowe67/freedv-gui/releases/download/v2.0.0/FreeDV.dmg 
  
  More information about this release, including changelog, can be found on 
GitHub release page:  
https://github.com/drowe67/freedv-gui/releases/tag/v2.0.0 
  
  
  
  
  
  Thanks, 
  
  
  
  
  -Mooneer K6AQ

[Freetel-codec2] FreeDV 2.0.0 released

[Mooneer S. <mo...@gm...>]

Hi all,

FreeDV 2.0.0 has been released, containing the first official release of
the RADE V1 mode previously trialled over several preview releases. Radio
Autoencoder (RADE) technology is a new approach to sending speech over HF
radio. It combines Machine Learning (ML) with classical DSP to send high
quality speech over HF radio at SNRs as low as -2dB in a bandwidth of 1500
Hz. More information about Radio Autoencoder can be found at
https://freedv.org/radio-autoencoder/.

As part of this effort, deprecated modes (700C, 800XA, 2020 and 2020B) have
been removed from the application. Additionally, this contains numerous bug
fixes and non-RADE specific enhancements from the last official release
(1.9.9.2).

It can be downloaded using the following links:

Windows:
https://github.com/drowe67/freedv-gui/releases/download/v2.0.0/FreeDV-2.0.0-windows-x86_64.exe
macOS:
https://github.com/drowe67/freedv-gui/releases/download/v2.0.0/FreeDV.dmg

More information about this release, including changelog, can be found on
GitHub release page:
https://github.com/drowe67/freedv-gui/releases/tag/v2.0.0

Thanks,

-Mooneer K6AQ

[Freetel-codec2] [Announcement] FreeDV Activity Day - May 17-18, 2025

[Mooneer S. <mo...@gm...>]

(Sorry for the delay in sending this out, I'm currently at Dayton and have
been pretty busy.)

Hi all,

This is a reminder that this month's FreeDV Activity Day is this coming
weekend. (As a reminder, Activity Day takes place on the third weekend of
every month.) This event will bring together people interested in HF
digital voice on the air for conversation and fun. Contacts using the
official application as well as ezDV, the SM1000 handheld microphone and
other supporting devices and applications are welcome.

*Event time:* 12AM Pacific time (0700Z) on May 17 to 11:59PM on May 18
(0659Z on May 19) (48 hours).

*Suggested frequencies:*
160 meters: 1.997 MHz
80 meters: 3.625, 3.643, 3.693, 3.697 MHz or 3.850 MHz
60 meters (in countries where allowed): 5.4035 MHz or 5.3665 MHz
40 meters: 7.177 MHz or 7.197 MHz
20 meters: 14.236 MHz or 14.240 MHz
17 meters: 18.118 MHz
15 meters: 21.313 MHz
12 meters: 24.933 MHz
10 meters: 28.330 or 28.720 MHz
10 GHz (for those in range of QO-100): 10489.640 MHz

(Note that LSB/DIGL is used below 10MHz as per current convention for voice
modes, USB/DIGU otherwise. 60 meters is of course USB/DIGU only.)

As this isn't a contest, there's no pressure to make contacts or send logs,
but you can always confirm QSOs via the usual means if you'd like (LoTW,
eQSL, QRZ, etc.) Enabling reporting (PSK Reporter and FreeDV Reporter) in
the FreeDV application and joining FreeDV Reporter and Discord are
recommended, however, so others can see that you're on the air and hearing
them (for instance, here's the current map of listeners). :D

Feel free to spread this far and wide among your local ham friends and
groups! :) Let me know if you have any questions about the event and
definitely post here if you have issues getting the application working
prior to the event.

Thanks,

-Mooneer K6AQ

[Freetel-codec2] FreeDV at Dayton Hamvention

[Mooneer S. <mo...@gm...>]

Hi all,

Just wanted to give you guys a heads up about our plans for Dayton this
weekend:

1. FreeDV booth: Same place as last year (Building 1, #1909). If you
haven't seen what RADE is capable of, you'll be able to listen to a recent
QSO as it was originally transmitted.
2. Talks: I'll be giving a ~5 minute synopsis of what we've been doing this
past year at the ARDC forum (12:50pm in Room 3 on Friday) as well as a
longer FreeDV/RADE talk on Saturday at 9:15 in Room 4.

Hope to see you guys there if you happen to be in the area :)

Thanks,

-Mooneer K6AQ

Re: [Freetel-codec2] [digitalvoice] Fwd: RATPAC Wednesday MAY 7 - Machine Learning and FreeDV

[Jim T. <jti...@gm...>]

>
>
> *TOMORROW - Wednesday, MAY 7,* *RATPAC Zoom Presentation *
> 9:00 PM ET / 6:00 PM PT /  GMT 02:00 AM Thursday
> *TOPIC: Machine Learning and FreeDV*
> *Facilitator:  Mooneer Salem, *K6AQ <https://www.qrz.com/db/K6AQ>* ◄ Be
> sure to check out Mooneer's QRZ page*
>

I think the meeting is at 9:00 PM ET / 6:00 PM PT, which means it is
actually at 01:00 GMT on Thursday.

- Jim 7J1AJH

[Freetel-codec2] Fwd: RATPAC Wednesday MAY 7 - Machine Learning and FreeDV

[Mooneer S. <mo...@gm...>]

Reminder about my talk tomorrow. Hope to see you there!

-Mooneer K6AQ

---------- Forwarded message ---------
From: RATPAC <rat...@gm...>
Date: Tue, May 6, 2025, 8:10 PM
Subject: RATPAC Wednesday MAY 7 - Machine Learning and FreeDV
To: <mo...@gm...>


*TOMORROW - Wednesday, MAY 7,* *RATPAC Zoom Presentation *
9:00 PM ET / 6:00 PM PT /  GMT 02:00 AM Thursday
*TOPIC: Machine Learning and FreeDV*
*Facilitator:  Mooneer Salem, *K6AQ <https://www.qrz.com/db/K6AQ>* ◄ Be
sure to check out Mooneer's QRZ page*
------------------------------
------------------------------
*Please Join Wednesday's Zoom Meeting*





*https://us02web.zoom.us/j/2128884758?pwd=VAFBYhN9lrnf7ubNOLr93HJoMENQBa.1
<https://us02web.zoom.us/j/2128884758?pwd=VAFBYhN9lrnf7ubNOLr93HJoMENQBa.1>Meeting
ID: 212 888 4758Passcode: RATPAC*
------------------------------
▬ *THURSDAY's PRESENTATION  *▬
*Please plan to join us, Thursday, May 1 - **Topic**: Field Day Update*

*Facilitators: Marty Woll, N6VI <https://www.qrz.com/db/N6VI> and Anthony
Luscre, K8ZT <https://www.qrz.com/db/K8ZT>**Be sure to check out** Marty
and Anthony's QRZ pages (call signs above are linked)*
------------------------------

*·       Past RATPAC Presentations : Published Format list
<https://docs.google.com/spreadsheets/d/e/2PACX-1vTVywG1s025_zsAaKrn8Lr_DPGT6tGV0SVsV5LEdBA91dFCYk_LP8S3kXhMcD9vXFM3Cg-q468jf6Nd/pubhtml>**
//  Menu Format list
<https://docs.google.com/spreadsheets/d/1xwGRjICRo6Cq6nYLgQbZt2bN2xVDb6_SIDW6KFK4nbk/edit#gid=0>*


*·       Website link: https://www.ratpac.us <https://www.ratpac.us>*

*·       Facebook: https://www.facebook.com/ratapacfb
<https://www.facebook.com/ratapacfb>*

*·       YouTube:  https://tinyurl.com/y8sc3jyy
<https://tinyurl.com/y8sc3jyy>*

*·       RATPAC Speaker & Suggestion Form: http://tiny.cc/rp-suggest
<http://tiny.cc/rp-suggest>*

*·       Online scheduler for presenters: *
*https://forms.gle/Vtw6kTHQWYwWM7pUA* <https://forms.gle/Vtw6kTHQWYwWM7pUA>

*73 ~Dan*


*Dan Marler, K7REX <https://www.qrz.com/db/k7rex>*
*rat...@gm... <rat...@gm...>*

<https://www.ratpac.us>

*Join one or more of our Groups.io to receive notifications and participate
in related discussions: *







*RATPAC - https://groups.io/g/RATPAC <https://groups.io/g/RATPAC> NewHams -
https://groups.io/g/NewHams <https://groups.io/g/NewHams> EMCOMM -
https://sec-emcomm.groups.io/g/main <https://sec-emcomm.groups.io/g/main>*
*Please be sure to include your name and call sign when registering. *



*Radio Amateur Training Planning and Activities Committee (RATPAC) *comprises
Amateur Radio Operators of a wide variety of backgrounds and experiences.
Together, we host *twice-a-week* nationwide Amateur Radio Zoom
presentations each *Wednesday and Thursday*. The presentation audience
consists of thousands of amateur radio operators worldwide who participate
directly in the Zoom sessions or with video links of the presentation and
related documentation sent out after each session.

[Freetel-codec2] FreeDV RATPAC talk - May 7, 2025

[Mooneer S. <mo...@gm...>]

Hi all,

I just wanted to let everyone know that I'll be giving a talk on Zoom for
RATPAC about the latest RADE work we've been doing on May 7th, 2025 at 9PM
EDT (UTC-4). More information about RATPAC can be found at
https://www.ratpac.us/. Zoom information is below as well:

https://us02web.zoom.us/j/2128884758?pwd=RG94eEY2L3FiMEg0U3ZIWmhXaEdwdz09
Password: RATPAC

Hope to see you there!

Thanks,

-Mooneer K6AQ