HackerTrans
TopNewTrendsCommentsPastAskShowJobs

eginhard

no profile record

Submissions

Extracting Signal from the Noise: What We Learned Auto-Triaging Agent PRs

huggingface.co
1 points·by eginhard·قبل شهرين·0 comments

comments

eginhard
·السنة الماضية·discuss
Someone already did: https://github.com/stlohrey/chatterbox-finetuning

And someone else fine-tuned it for German: https://huggingface.co/SebastianBodza/Kartoffelbox-v0.1
eginhard
·قبل سنتين·discuss
This is just the code license. Parents are referring to the XTTS model (their best one).
eginhard
·قبل سنتين·discuss
Some insights from one former lead: https://erogol.com/2024/01/09/goodsandbadsofopensource

TLDR: Making money from open-source is hard.
eginhard
·قبل سنتين·discuss
The licenses of the code (MPL 2.0, allowing commercial use) and the available pretrained models (https://github.com/idiap/coqui-ai-TTS/blob/dev/TTS/.models.j...) are all clearly stated and won't change unless the model owners decide to do so. So the XTTS model is still under CPML, which doesn't allow commercial use.
eginhard
·قبل سنتين·discuss
Many of them still allow commercial use. The question is most likely about the XTTS model, which doesn't, but its license is up to the original Coqui team.
eginhard
·قبل سنتين·discuss
Yes, you can train/fine-tune models on your own voice with Coqui
eginhard
·قبل سنتين·discuss
We do maintain a fork, mostly with bug fixes for now: https://github.com/idiap/coqui-ai-TTS PRs welcome :)
eginhard
·قبل سنتين·discuss
They just shared the paper for XTTS, which got accepted to Interspeech and might be the reason for this being posted now: https://arxiv.org/abs/2406.04904
eginhard
·قبل سنتين·discuss
Sleeper trains need a supplement and are often booked out in advance, so he sleeps on the night ICE trains (https://leben-im-zug.de/howto-nachtreise-im-ice/). These are regular trains with standard seating only, all lights on and announcements for the (frequent) stops at normal volume. He mentions that he sleeps on an air mattress on the floor.
eginhard
·قبل 3 سنوات·discuss
After such a long time it's probably not comparable to one at a more normal ripening stage. The region is mostly known for Raclette, but for these cheeses the milk is apparently heated higher for a firmer result: https://www.24heures.ch/grimentz-des-meules-de-fromage-de-14...
eginhard
·قبل 3 سنوات·discuss
STT training data includes all kinds of "noisy" speech so that the model learns to recognise speech in any conditions. TTS training data needs to be as clean as possible so that you don't introduce artefacts in the output and this high-quality data is much harder to get. A simple inversion is not really feasible or at least requires filtering out much of the data.
eginhard
·قبل 3 سنوات·discuss
The "Understanding Deep Learning" book covers more recent models as well: https://udlbook.github.io/udlbook/ (free PDF and Jupyter notebooks available)