Join devRant
Do all the things like
++ or -- rants, post your own rants, comment on others' rants and build your customized dev avatar
Sign Up
Pipeless API
From the creators of devRant, Pipeless lets you power real-time personalized recommendations and activity feeds using a simple API
Learn More
Search - "speech-synthesis"
-
To be able to code blind folded - literally. A few years back when the web speech synthesis apis came out and chat bots were raging I thought it would be cool to dictate pseudo code on the fly whole whiteboard the problem. When I investigated the easiest way to implement a mvp I was shocked to learn that there are BLIND programmers.
That alone is impressive and I went on to find that many have years of experience and add valuable contributions on a regular basis. Unfortunately I havnt had an opportunity to meet one yet but I am in utter awe of their accomplishment.
Should I get the chance I want to try and walk in their shoes, live a day without my eyes and learn to solve problems without spotting a pattern8 -
If you don't know how to explain about your software, but you want to be featured in Forbes (or other shitty sites) as quickly as possible, copy this:
I am proud that this software used high-tech technology and algorithms such as blockchain, AI (artificial intelligence), ANN (Artificial Neural Network), ML (machine learning), GAN (Generative Adversarial Network), CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), DNN (Deep Neural Network), TA (text analysis), Adversarial Training, Sentiment Analysis, Entity Analysis, Syntatic Analysis, Entity Sentiment Analysis, Factor Analysis, SSML (Speech Synthesis Markup Language), SMT (Statistical Machine Translation), RBMT (Rule Based Machine Translation), Knowledge Discovery System, Decision Support System, Computational Intelligence, Fuzzy Logic, GA (Genetic Algorithm), EA (Evolutinary Algorithm), and CNTK (Computational Network Toolkit).
🤣 🤣 🤣 🤣 🤣3 -
Me and tech coworker opens office front door. Another coworker starts ranting how he accidentally hit som key combo and started some speech synthesis feature in Windows. Me and tech coworker both declared we had never heard of that feature before.
Ten minutes goes by, then muggle coworker comes by asking for help to turn it off. Tech coworker Googles solution in literally 6 seconds on the phone without even stopping the conversation we had going on when muggle interrupted.
How is it that muggles haven't found out that the Internet contains stuff?! And that it's searchable!!
Gaaaahhh -
I setup stable diffusion today. Still figuring it out but I'm like an artist now right? Right?
Next step is figuring out how to train models.
Then I have to make some samples of various words in spectrogram form for training.
After that we'll see if stable diffusion can reconstruct phonemes.
I'll train using both my voice and a couple others, and apply them as styles.
And then finally, I can accomplish my lifes goal.
To have the voice of morgan freeman with me at all times, everywhere I go.5 -
When Google Engineers Made a Speech Synthesis Program, they hadn't figured out a name until:
"What should we name our advanced speech synthesis program"
"Hey bob what are going to order for lunch today"
"Tacos."
"What was that weird movie with the laser bikes that make light walls"
"Tron."
"Bob you're a genius" -
Here is a personal project I've been working on lately. It's not public, but just wanted to share. It's a custom chatbot I created using a LAMP stack. Its built on top of a framework called Program-O to handle the knowledgebase storage and processing along with some basic NLP. I added the web speech api functionality myself so it supports recognition as well as speech synthesis. Anyways, pretty proud of this one.7
-
Next personal fail ...
previous rant
https://devrant.com/rants/2060249/...
Turned out that wavenet is sequential so it needs previous step to predict next.
Quite obvious when you look at how people speak sentences, they hardly stop in the middle of the word.
🤔
need to think how to proceed next, how to cut sentences.
Watched deepvoice3 and some accent models from baidu.
I can generate 8 sentences at a time, each takes 8 minutes so if I cut between words and got last mels between words right I can get 1 minute but I need to store model somewhere.
I forgot my machine learning and speech synthesis skills from previous life, time to load more skills ... -
Developed this project "Audio Book Generator"
Implementing speech synthesis(📖 to 🗣) on eBooks
Bored with writing notes in a lecture? How about we convert the notes dictated by the lecturer into text? Use the speechtotext.py script to get the text format of spoken notes, which saves the text in a .txt file.
Too lazy to read a novel? Get an Ebook version of the novel and run the finalAudioBookGenerator.py script. It will generate an mp3(audio) format of the book. Enjoy book listening :)
You can also convert your single images using the singleImageReader.py script.
Demonstration:
https://youtu.be/xhMvGg1dAsg
Project:
https://github.com/globefire/...
Star If you liked it. :)rant project python github audio books speech synthesis youtube text to speech speech to text tesseract3 -
Do you prefer audiobooks? Are you an active medium reader? Do you want audio for the medium articles you read? Are you out of your free medium articles?😢 My Scrapy is here for the rescue.💸
This is a simple application of web scraping, it scrapes the articles of medium and allows you to read or hear the article. If you use this on computer there will be a number of accents in the option.
The audio feature is provided only to the premium medium users, so here comes My Scrapy to save your 5$/month. 💸
.
Tech Stack used :
Python, beautiful soup, Django, speech synthesis
PS: This application was built for educational purpose.
Fun Fact: You can still read any medium articles if they are asking you to upgrade, you must be wondering how? Well, copy the link of the article and browse it in incognito mode on any browser or sign out and read it.😂🤣
githublink:
https://github.com/globefire/...
demo link:
https://youtube.com/watch/...
instagram link:
https://instagram.com/p/...3 -
Are you out of your free medium articles?😢 My Scrapy is here for the rescue.💸
This is simple application of web scraping, it scrapes the articles of medium and allows you to read or hear the article. If you use this on computer there will be a number of accents in the option.
The audio feature is provided only to the premium medium users, so here comes My Scrapy to save your 5$/month. 💸
.
Tech Stack used :
Python, beautiful soup, Django, speech synthesis
.
PS: This application was built for educational purpose and the source code for this application is not open sourced anywhere.
Fun Fact : You can still read any medium articles if they ask you to upgrade, you must be wondering how? Well, copy the link of the article and browse it in incognito mode on any browser.😂🤣
Try the app and lemme know if you liked it:
https://mymediumscraper.herokuapp.com/...4