Practical scenario for ML Transcribe on cloud

One of the well-known services in AI/ML stack (artificial intelligence & machine learning) of cloud computing is transcribing (speech to text) the audio and analyzing it.

While cleaning up my phone, I realised, that it has piled up a lot of voice recordings that I did on various conferences & seminars I attended.  Recording the speeches/discussions directly on phone, is a quick way of taking notes, which you can refer later & if you label it & make a transcript, it’s even better for indexing.
Thus, my experiments with Transcription services on the cloud started! (I wonder whether Evernote or OneNote has transcribe feature which converts speech-to-text on-the-go on mobile).

I had to trim a 45 minutes long audio file to 1 min. sample & convert it to mp3 (using VLC Player). To keep things simple there’s only 1 speaker talking in the audio file, although the job is not simple enough for machines, you can listen to sample audio (and try to text it in comment section!)

Google Cloud pleased me as it supports long range of input languages as audio source, so I could choose Indian English, but on the downside, it only supported 1 min audio file for free-demo. (for longer files, you may have to call APIs & write a code). Here’s the result  from Google:

the world's most interesting thing and I think you are the advantage of building for 
India and building the world have a domestic economy is big enough for you to grow 
as a starter and global market also I don't need to both the option that I want to 
talk to someone is very difficult to the reason is these words between is true that 
was open find out the world after appoint the world can give the field of India 
can eat Universal pain

But it gives different results if you select US English as source language, much better if selected model is ‘video’ (other options are phone call, search/command, default) Video model is not available for IN-EN.

We are around 250 in India.  to the point that
the world could have come in and they want to be locked up all over the top again, 
but more importantly I think is huge opportunity for startups the third and most 
interesting thing and I think you can speak about the relevant is after the DND 
Festival we spend some time at Israel is India has this unique Vantage of building
 for India and building for the world. We have a domestic economy, which is big 
enough for you to grow as a start-up and it has a and a global market. 
Also, I think we need a bill for both the opportunity that I only focus on one is 
very defensive because the reason is these words between these two that what 
have different kind navigation for the world to start learning after a point 
because India will be the world's and usually right so the because the scene of 
India can be Universal game.

If you check out AWS AI/ML/DL stack, it gives you ready to use tools such as Rekognition, Translate, Polly which can process the input without requiring any coding. What we need in our case is: AWS Transcribe which reads audio files stored in S3 and export the text in json format. The best part is you do not need to write any code for this nor there’s 1 min. restriction for audio. But it understands only US-EN and Spanish, which did not give great results.

Get it. So with that the ones they want. 
So  we have all but one party is huge over to you first. The most impressive thing. 
And i think you could spend some time. Is there? He has a unique case beginning for
the world. You have a domestic big enough to stop it and the opportunity only 
focused on one very defensive because of easiness. These words that was a different
world will start learning after a point because and you two guys with big feet,
you know what?

IBM Watson is a dark horse here, showed relatively fewer errors. But if you choose British English, the result was full of ‘yeah’, which is funny (and stupid!)

We get 150. This. For the one that. The one. The what we love to help all those 
online games at 148 is huge opportunity for stocks the most interesting thing 
and I think you would be more than enough for the effects of the sense of time 
and was there. Is media has unique blockades probability for India and before 
the war. Yeah domestic economy big enough for you to go in the stock and it 
has a. And over the hallways like the need to clear the board the all the Jews 
that only focus on one is very different too because the reason is these lawyers
 or differently from the way the stock offer appointed with nearly the word off 
and you could be like the because of being in the op he or university.

Lastly, Microsoft’s Azure cognitive Services gave me hard time. Unlike other cloud service providers mentioned above, it doesn’t have a quick demo page where I could simply upload a minute long file to test. So I had to sign-up for Azure services using credit card, email, mobile, & OTP verification, only to find that I am not eligible for their 30 day free trial. I somehow got the free trial after contacting the customer support. After much fooling around Azure Cognitive Services API documentation, I realised that API only allows 10 seconds of audio file (certainly not a tool we are looking for, this one is more suited for command/search). Apparently, does a batch transcription, which is again a lot of efforts. After few RestAPI experiments, I ditched! I may be missing something @Azure for such a simple task, (Please add a comment below if you can guide me to right path, or if you know easier way which I missed). But I think they should have made it simple ready-to-use service/demo.

Finally, I decided to transcribe it myself as none of the above cloud players are up to the mark.
Human interpretation *(who knows the context.)
I am trying verbatim here. I must confess, this audio was very tough to crack even for someone who was present in that discussion and recorded it. I can imagine more errors if this assigned to a layman.

...Twenty hundred accelerators. And we are around hundred and fifteen. so almost… 
So to the point that, the world’s gonna come in. and we gonna...  
..upper game but more importantly, I think it’s huge opportunity for startups.
The third and most interesting thing and I think you’ll speak about it, 
Amey, after the DLD festival where we spent some time in Israel, is 
India has this unique advantage of building for India and building for world. 
We have a domestic economy big enough for you to grow as a startup and it has a 
and a global market also I think we need to build for both.
The opportunity that I wanna focus is very different because the reason is these
worlds between the what is different for India different for world is start
blurring after a point because India will be the world. And mutually so bigger the 
theme for India is Universal theme.

Surely, above results has some errors as well!
Conclusion: Are we there yet? What do you think?

Clearly, you still need human intervention and cannot rely fully (in this case not at all) on these automate services.  In Translation job these machines at least aid 50-70% but for transcription we still have a lot to cover (& miles to go 🙂 ).

Oh, who cares who sang that song before?
It really didn’t matter.

What you do if you want to sing?
And you never had any training,
And you never had an original song to sing?
— Hey, you just sing, anyway!

– Usha Uthup.

Follow up on resolution

This is a follow-up on my previous post about my resolution in 2018. Today is a good occasion (my birthday) to ponder on what I had decided and how much I reached towards my goal.

Each of my four resolution deserves a detailed blogpost with some insights and learning but here’s glimpse of what’s going on and how far I am.

1. Workout & Stay fit: I did a couple of medium treks without a sweat! So, I am fit & have been fit but I had lost a confidence whether I could run/sprint for more than 30 seconds, whether I still have stamina… This resolution was more about joining some gym and getting a proper work-out routine. & yes, I did that. After checking out with dozens of gyms I finally decided on one and started my gym membership. Once on treadmill, I started building my stamina and done some 3-5 minutes sprints. So, there’s some progress there. I haven’t gone into body-building and weight exercise but I’ll start that soon.

2. Alternative Investment: I have been quite active in trading last couple of quarters and have found some unique investment opportunities. Although this is not how I had planned in Jan-2018 of investing in startups like Angels ( or building a portfolio etc., this definitely falls in alternative investment. And I indeed became on angle for a startup. On a second thought I can still explorer Angelist, that option is open, but the ROI/money is not quick nor guaranteed.

3. Make something: I don’t remember of making something this year. I finally purchased soldering kit & fixed some bluetooth speakers (along with my father, we did it together!!). I also purchased a hot melt glue-gun, but that product is a rip-off. They should remove the word ‘glue’ or I should dig more to get actually sticky cartridge, which would stick like soldering /welding in case of metal. I guess that’s the closes I have been. As far as the open source project goes I haven’t short-listed any idea yet (You can share one). I need to build a shade for car parking that could be my DIY project this year.
Plastic Recycling
4. Solid Waste management: When I had posted about it in Jan, I had no clue of how things work, how solid waste it treated/processed/recycled if not sent to dumping ground. I know the seriousness it holds and thus started with first step. Earlier this year, I visited Dharavi’s plastic garbage shredding and recycling industry and bit relieved that there’s hope!

To summarise, I have not reached 50% of goal but the resolutions are still alive and I’m getting there. I should post an update in December before the year ends. Meanwhile if you have any comments to share (especially #2 a startup idea/project, #3 DIY/IoT projects for me, #4 how I can contribute on solid waste management) feel free to email me [email protected] or post a comment below.

https baby!

That was long overdue! I’ve been meaning to add secure certificate for the domain (and all subdomains) for quite some time. Finally, I made the site connection secure, thanks to Let’sEncrypt.

By the way you should donate to its wonderful cause of providing SSL/TLS certificate for free (even the wildcard certificates!!) LetsEncrypt is free, automated & Open certificate authority(CA).

Resolution 2018

It’s that time of the year when you make yet another new year resolution/s. Mostly it’s the same commitment you make every year and barely mange to complete it. So, do you have anything new this time?
Well, in my case, I’ve thought of something new and I think it’s important for me to put it out here (makes me accountable).  I can then look back next year and write couple of follow up posts on the progress on each of projects. This year I am planning to spend quite a bit of my time and money on some personal as well as public projects.

  1. Workout & stay fit: Yeah, the usual one! I know it’s a bit obvious, but this one’s new for me. Crossed 35 and still never been to a gym, never followed a diet or done real physical training. So this is going to be my personal challenge.
  2. Alternative investments: Although, I’ve had worked on startups, and mentored/invested in a few; I never did this professionally. Hence, this year I am planning to do this professionally, a venture capital fund (comes under alternative investment in the fund’s portfolio). This is going to be my professional challenge. To raise funds and build a portfolio of bankable businesses.
  3. Make something: I just love maker‘s community and how they inspire each other to build something new. You can earn millions of dollars in stock trading but nothing gives you more satisfaction than fixing things and creating stuff. This year I am going to make something – a smart automation hardware for me/my house, which others can use. It’ll be an open-source project so others can benefit and improve. This is going to be my community project.
  4. Solid waste management: Last and not the least, the most challenging project I am going to take up is “disposing off garbage”. Yes, and you guessed it right, this one’s my public project. Things that you don’t want, go to the trash bin; but what happens to it next? The rate at which we are consuming materials is way higher than it can be decomposed or recycled. Soon we will end up on acres of land filled with trash. Dumping ground cannot be a permanent solution and I’ve come to realize that this is a grave issue which needs to be taken care on priority. If not, the next generation would have to face the aftermath of our actions, and by then it will be too late.

You know, what grinds my gears?

Do you know, what really grinds my gears?
Yes, those little suckers are deadly. In fact they are the most lethal species, deadlier than shark, lions, or any other animal for that matter. In fact all animals combined would not match the harm that mosquitoes make.

Check this video /infographic /or should I call it videographics? (ah, new term!!). The video lists most lethal animals who are responsible for human deaths. I was waiting for the twist & the surprise; and I got one. I thought, humans kill most humans (murders and accidents), obviously. And I thought, they would miss including the humans in the list of animals. But I was stunned at the end.

Mosquitoes are dangerous; and I want to get rid of those. Ah! who doesn’t want to get rid of them? All of us, right? Except you might not know what mosquitoes are if you are living in colder regions of developed countries.

I hope you all remember, Mr. Bill Gates opening the jar of mosquitoes in TED talks.  Well, that did the trick, I think. Many labs are working on mosquito borne diseases such as Malaria, Dengue, Chikunguniya.

There are experiments that could prevent mosquitoes to reproduce, but what are the consequences of eradicating the entire species is unknown and dangerous.

Secret Book

I tweeted about it and viola, mission fulfilled within a week.

So the law of attraction from the secret book really works, huh?

Here we go (& will not come)

Here Maps will no longer be available on Windows 10 mobile phones. Starting from 30 June 2016 the mapping & navigation software from Nokia will be discontinued on Windows 10 mobile devices. If you happen to have updated here maps app on windowsphone 8.1 you would receive this message.
Thank me, hopefully it wont affect as I would still have WP8.1 since earlier Lumia Phones are not eligible for Windows 10 upgrade.

Sliders don’t convert

Sliders, image rotator, slideshow, carasoule (spell check: carousel 😉 ) or whatever you’re calling it, all look cool & make some fancy magic using JavaScript but sadly don’t convert.
Yes, sad but true. It’s bit tough to absorb but you can a/b test to draw your own conclusions; I’m sure numbers would convince you better. Or take a look at reliable source. Microsoft, Windows, Abode and many large/popular websites used to keep sliders on front page. Now they don’t.
Not only it’s bad for SEO, it’s not good for UX as well. Adds extra js files for ‘animation/lively effects’. Sliders are big distraction. Takes 75% of front page real estate. Confuses users as to where to go next (to choose user flow).
Now I know that our front page (of the business site ) has a slider; and that is why I’m writing this post. I’m in process of building new site for biz & it was tough decision to discard sliders, but yes, most likely I’m not going to have it for new site.

The last straw #Facebook

Facebook feed algorithm is driving people to extremism. It’s making their beliefs even stronger, cementing it further by watching likeable content repetitively. While Facebook notoriously, has been working on some or the other secret social experiments at large scale, this is the last straw. I have been tempted to stop using Facebook since many years but had hold back the thought because of the business clients on social media.
I don’t know how Mahesh Murthy manages to take a stand and use fb the same time… something to learn?
But I think they are not prepared for the negative consequences, the negative sentiments and extremism causing on the society at large. This may look bit vague, but this is a very serious concern.
This should be the movement, to stop Facebook from manipulating peoples mind. I think a mentor would help! Do you feel the same? Are you game for this? RT below tweet, or better yet, comment below (using your facebook credentials 😐 )

DrupalCon Asia here I come

DrupalCon is happening in Asia for the first time. Lucky for me it’s happening in India, Mumbai near I live (at IIT Bombay to be precise). I’ve been following Drupal Events and news since the launch of D8; and thinking of attending the conference. Today is the last day to pay for the tickets and register for the event. I delayed my decision to max and paid more than double the super-early bird price. ₹ 8,000 is still considered an costly conference in India even if you bill it as business expense. I know it’ll payback. Drupal is a whole new level, compared to other obvious choices for website development (read WordPress & Joomla). I was blown away by the built-in features & the possibilities with Drupal 8. D8 took forever to launch since the last version (released in 2011) and it changed everything. I hope the wait is well worth, especially now, when I’ve decided to work on the project using Drupal platform. Currently I’m building it on D7 due to lack of mature modules. But, eventually more mods will be available to D8. Sooner the better. Better even before the launch of our app. My plan is to start working on Drupal 8 as soon as I am satisfied with MVP (minimum viable product/ prototype) on D7, and built it on HHVM instead of currently available version of PHP.  HHVM, the hacked PHP by Facebook team, is surely faster than PHP.
DrupalCon is multi-track (parallel lectures) event with loads of informative sessions and non-stop flow of the tips, lessons & knowledge. They have very unique session (or should I call it un-session?) called BoF.

Birds of a Feather sessions (or BOFs) are informal gatherings of like-minded individuals who wish to discuss a certain topic without a pre-planned agenda. BOFs allow groups to meet and discuss issues relating to regular conference sessions and talk out common problems facing the community.

Isn’t it cool? A space for like minded people with informal settings and no-agenda. I’m really excited to attend this conference. I never attended DrupalCamps (the smaller version) nor DrupalCons before. And I’m sure there’s going to be loads of take-away. I’ll write post-event blog about my experience.
If you happened to be coming to DrupalCon Asia next week feel free to ping me on twitter.

5 growth hacking tips from AirBnB

Rebecca, Growth hacker at AirBnB, explains her success with the experiments AirBnB did at the early years of the startup. Here’s 5 tips to go extra mile when everything else fails or isn’t enough. or to use the title she used here’s :

5 Guerrilla Tactics When the Slick Stuff Fails

Ah! And by the way, if you noticed, this is not your ordinary YouTube embeded video (although it’s uploaded on YouTube!). The video is indexed on clipmine to easily navigate and skip to relevant parts. Cool!

Great insights and something new I learned today.
NPS stands for net promoter score!
Litmus for Email testing & analysis.
Thanks the internet & thanks Rebecca, & 500 Startups.

On your marks. Get set Go!

Vir Das, the comedian, actor in Bollywood has more active and less popular facet that you might not know. Perhaps he’s one of very few people in the film industry who are real, well versed & make sense.
He’s pretty active on social media, so go, follow him!

I’m bit late posting his YouTube video on anxiety about the exam results but I think it’s timeless, so here you go!