Advertisement Β· 728 Γ— 90

Posts by Peter

Preview
GitHub - pevers/parkiet: Parkiet is a 1.6B parameter Dutch text-to-speech model (TTS) Parkiet is a 1.6B parameter Dutch text-to-speech model (TTS) - GitHub - pevers/parkiet: Parkiet is a 1.6B parameter Dutch text-to-speech model (TTS)

github.com/pevers/parkiet for open weights and training code on Google Cloud TPUs using free research credit. #MLSky #MachineLearning #TTS #ML

6 months ago 2 0 0 0
Video

Can you train a state of the art text-to-speech (TTS) model with little resources? It seems you can! I've used Google's free TPU research credit to train a Dutch version of "Dia" called Parkiet, a natural conversation speech model and the quality is on-par with ElevenLabs.

6 months ago 2 0 1 0
Post image

Any idea how to get a hold of Google's free Research TPU credits? I get these assigned for 30 days but there is either no capacity or the accelerator is not available at all #ml

7 months ago 2 0 0 0

Thank you! There are still many things I have in mind to improve, but there is a solid base to practice with immersion.

11 months ago 1 0 0 0

Hah I doubt it because they make mistakes

11 months ago 0 0 1 0
Post image

Three other people have now surpassed me in all-time XP earned on my own language learning app! Great milestone. #buildinpublic #languagelearning

11 months ago 6 0 2 0

Our Weekly Update #18 is live! πŸŽ₯✨

Watch now: https://youtu.be/G2FQRFcLawQ
Don’t forget to subscribe & hit the bell πŸ””!

Subscribe to our weekly newsletter!
πŸ‘‰ https://urlroulette.net/newsletter/subscribeform πŸš€

@pevers.bsky.social
#christmas #marketplace #onlinetv

1 year ago 2 1 0 0
Advertisement

Reached the front-page of HN and now the app is really hammered by traffic 😬.

1 year ago 0 0 0 0

Got my first sale for Fluentsubs! Key things to make it happen:

- Shipped an awesome feature for beginner learners
- Made some exercises public to check out w/o an account
- Locked a lot of the features behind a "Pro" paywall and made it clear what the benefits are

#buildinpublic

1 year ago 5 0 3 0
Video

Finished the Duolingo-like daily exercises for news content. You can try it out at app.fluentsubs.com/exercises/da... for 11 languages (will add more soon). Tomorrow I'll finally do some proper marketing and fix the membership option (basically everything is free) #buildinpublic #langsky

1 year ago 6 0 0 0

Thanks I’ll check it out! Almost done implementing it

1 year ago 1 0 1 0
Video

DuoLingo like exercises for YouTube content is coming to Fluentsubs! #buildinpublic #langsky

1 year ago 9 0 2 0

Thanks! I have many ideas for improvements but didn't yet manage to get them deployed.

1 year ago 0 0 0 0
Preview
Discover Fluentsubs on Uneed Turn YouTube videos into language learning lessons

I launched Fluentsubs on @uneed.best today at www.uneed.best/tool/fluents... #buildinpublic

1 year ago 7 0 2 0
Preview
Fluentsubs Transform your favorite videosβ€”from trending shows to viral clipsβ€”into powerful language lessons that stick. Supports over 32 languages.

Example of Macrons speech about Europe tonight app.fluentsubs.com/stream?v=cm7...

1 year ago 1 0 0 0
Post image

Videos with excellent transcripts can now be publicly shared! #buildinpublic

1 year ago 2 0 1 0
Video

In a major upgrade to Fluentsubs I've added "cloze" for subtitles. Based on the accuracy of the transcript and the word length, random gaps are created as a listening exercise to the user to bridge the gap between reading/listening skills in a language. #buildinpublic #langsky

1 year ago 4 0 0 0
Advertisement

I’m fiddling with the idea of just running tests locally and signing them automatically. Basically a decentralized CI/CD . User X signs that commit Y runs fine -> merge!

1 year ago 2 0 0 0

But how do you do test selection in a large monolith? How do you know which parts are affected?

1 year ago 2 0 1 0

Thanks! Luckily it was during the night so I couldn’t ship more bugs

1 year ago 1 0 0 0
Show HN: Language Learning from YouTube content | Hacker News

Fluentsubs made it to the Hackernews "Show HN" front! news.ycombinator.com/item?id=4290...

Now I suddenly have the problem of not being able to YOLO deploy because I have users πŸ˜….

I've also shipped better transcription models, more feedback and a fine-grained control adding new words to a deck!

1 year ago 3 0 1 0
Video

Fluentsubs just got smarter! πŸš€ Now you can pick only the part that you need for your deckβ€”perfect for short spaced repetition cards. Check it out! πŸ“šβœ¨ #LanguageLearning #buildinpublic

1 year ago 6 0 0 0
Post image

Foundation models are overhyped. SAM2 was hard to fine-tune and we got some great results after tweaking the training process a lot. Decided to give YOLO11 another try (even after the crypto miner debacle) and it seems to be on par with SAM2 in terms of quality and much much faster!

1 year ago 2 0 0 0
Video

Had some nice feedback from the first users and implemented the playlist feature, and added some basic channels so beginner language learners are not completely overwhelmed. The videos are pre-transcribed so that they can be watched immediately! #langsky #japanese #buildinpublic

1 year ago 6 1 0 0

Would be curious about this too

1 year ago 0 0 0 0

Thanks for trying! Will fix it!

1 year ago 1 0 0 0
Advertisement
Preview
Fluentsubs Transform your favorite videosβ€”from trending shows to viral clipsβ€”into powerful language lessons that stick. Supports over 32 languages.

πŸš€ Just gave fluentsubs.com a complete makeover!
βœ… New landing page – cleaner & easier to grasp
🎨 Fresh logo – friendlier & polished

I’d love to hear your thoughts! Put in a lot of effort to make everything super clear. #buildinpublic

1 year ago 7 0 1 0

I think it is possible to create a separate file and feed that to the context window using β€˜@β€˜. But it is a bit of a hassle.

1 year ago 1 0 0 0

GitHub. Main reason it is being so used to it for the last 10 years. I’m also addicted to the GH trending feed to scout for new stuff

1 year ago 1 0 1 0

I noticed a huge difference with using Claude + Sonnet 3.5 instead. Less mistakes and way more context is taken into account.

1 year ago 1 0 0 0