Can deepspeech process longer audio files

[JRMeyer]

>>> jehoshua
[January 23, 2018, 1:22am]

The other day I was testing DeepSpeech and by mistake specified a long
audio file. Longer than 10 seconds. It was one of the 45 to 60 minute
audios.

Computer froze totally, no response, hard drive light on full. Only
resolve was to power down. Now that computer has a 'clunk' noise when I
power up. Past experiences have shown me this is early warnings of HDD
failure.

Maybe the developers can check an audio duration when DeepSpeech starts
up and if more than (say) 60 seconds, give the option of
cancelling/aborting.

The computer I was using has Processors: 4 x Intel Core i5-2430M CPU
2.40GHz slash
Memory: 3.8 GiB of RAM , so not what I would call 'underpowered'. It was
a gift from my son...hmm, not impressed.
![:frowning:](

I appreciate DS is still alpha but one would hope that common sense
would prevail.

[This is an archived TTS discussion thread from discourse.mozilla.org/t/can-deepspeech-process-longer-audio-files]

[JRMeyer]

>>> lissyx
[January 23, 2018, 5:59am]

Regarding longer audio files, you might have hints in Longer audio
files with Deep
Speech.
Long story short, the actual design with bidirectional recurrent layers
requires us to have full knowledge of the audio we want to decode.

Regarding the cancelling for long audio, that feels like a good idea but
then it means more questions: where do we draw the line? And moreover,
it's not just based on the audio length itself, it also depends on your
hardware, and it might be very very different.

Said otherwise, given it's alpha software, I think we should not spend
our time on this kind of workaround and instead:

That being said, if you want to submit a workaround doing this kind of
limitation, we'll be happy to help and review your patches
![:slight_smile:](

[Archived Post]

[JRMeyer]

>>> jehoshua
[January 24, 2018, 1:56am]

> Regarding longer audio files, you might have hints in Longer audio
> files with Deep
> Speech.
> Long story short, the actual design with bidirectional recurrent
> layers requires us to have full knowledge of the audio we want to
> decode.

Thanks, yes I did read through that post before starting this thread,
but that was more about how to train, not an answer as such, about can
'Deepspeech process (produce a transcripton) longer audio files'. The
audios we have are from between 44 minutes and 1 hr 18 miutes. If I
deployed the solution in that thread about cutting up just one audio, I
would need 936 wav files for DeepSpeech to do the training.

Even if I did that for 1 audio (and there are hundreds), what will the
expected output be. The accuracy of the transcript ? I calculated the
WER of a 19 second audio transcript (output from DeepSpeech) and the
error rate was about 46 %

Sure, if I spent the time building a specific model just for this
speaker, that makes sense. But will I be able to run DeepSpeech on that
computer after the training has been done ? Or will it consume so much
resources that the computer freezes ? More hard drive damage ?

> Regarding the cancelling for long audio, that feels like a good idea
> but then it means more questions: where do we draw the line? And
> moreover, it's not just based on the audio length itself, it also
> depends on your hardware, and it might be very very different.

Yes, good point. How about enabling Ctrl-C at least ?

I'm wondering if I should just learn to touch type to produce the
transcriptions.
![:wink:](

[Archived Post]

[JRMeyer]

>>> lissyx
[January 24, 2018, 8:13am]

Well, the thread I pointed you at contains an answer from Kelly, who
explicitely documents that because of the architecture of the network
and because of the current training dataset, processing very long audio
will likely not work as expected :).

Regarding the accuracy, there are a number of other factors. You say 46%
on 19 secs audio, that feels not expected, but it might depend on a lot
of stuff: the dataset we have makes the model behave erratically if you
don't really have american english clean sound. It could also be mic
interferences ...

Besides, sorry, but DeepSpeech does not 'damage' your computer. It's
computationnally intensive, but we know that, and again, we are working
on that. But all of that takes time to accomplish properly. If you train
for a specific speaker, I would suggest taking a look at TUTORIAL : How
I trained a specific french model to control my
robot
where Vincent produced a model dedicated to himself, smaller and running
good on NVIDIA GPU for his robot. It's not magic, he has been able to
produce enough audio data to train seriously, but he also reduced the
model size, making it much smaller, and thus much less computationnally
intensive. There's a balance between the generalization capabilities of
the model and its complexity.

For CTRL+C, I guess you are referring to Python binding? It's likely the
usual mess of Python and threads, not even sure we can do something to
that.

[Archived Post]

[JRMeyer]

>>> kouohhashi
[December 18, 2019, 9:08am]

Hi, I have similar question? slash
What if I have 1 hours of audio to transcribe?

Should I split the audio file into bunch of small files. slash
Then transcribe all files and combine them? slash
or is there any better ( or known ) way to transcribe long audio?

If there is best practice, could you share the idea?

Thanks in advance.

[Archived Post]

[JRMeyer]

>>> lissyx
[December 18, 2019, 9:12am]

This is a two-years old topic. Not valid anymore. There should be no
problem in dealing with arbitrary-long audio samples at inferencen, now.

[Archived Post]