webdataset
TTS
Our great sponsors
webdataset | TTS | |
---|---|---|
7 | 62 | |
1,962 | 8,806 | |
7.4% | 2.2% | |
8.8 | 0.0 | |
17 days ago | 6 months ago | |
Python | Jupyter Notebook | |
BSD 3-clause "New" or "Revised" License | Mozilla Public License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
webdataset
-
How to use data stored in a (private) S3 Bucket for training?
As an alternative, I've looked into using WebDataset, but couldn't figure out how to access data that is stored in a private bucket.
- [D] Title: Best tools and frameworks for working with million-billion image datasets?
-
[D] Training networks on extremely large datasets (10+TB)?
You can try webdataset (https://github.com/webdataset/webdataset).
- Question: TIFF image dataset - size in RAM.
-
How to upload large amounts of data to a server?
compress it to .tar format and then load it as a webdataset
-
Does mit 6.824 help for distributed deep learning?
Would guess not but there should be some good niche resources: check out the introductory videos here https://github.com/webdataset/webdataset
-
How to effectively load a large text dataset with PyTorch?
I found a pretty good solution that is similar to the TFRecord from Tensorflow. You just need to load the data, tokenized it, and save the arrays in shards with webdataset package.
TTS
-
Any recommendation for human like voice AI model for conversation AI?
Fast or good, choose one
Mozilla's TTS is a python package installable with pip and uses cpu or gpu resources to render a choice of voices, they mostly sound natural and this is the good. https://github.com/mozilla/TTS
Mycroft's mimic3 is the default voice renderer for the Mycroft project that runs on pi hardware and sounds ok-ish, that is the fast. https://github.com/MycroftAI/mimic3
There are many others but these are the two I use according to if it needs to run on limited hardware or if the cycles fall freely from the sky.
-
Coqui.ai Is Shutting Down
Coqui-ai was a commercial continuation of Mozilla TTS and STT (https://github.com/mozilla/TTS).
At the time (2018-ish), it was really impressive for on-device voice synthesis (with a quality approaching the Google and Azure cloud-based voice synthesis options) and open source, so a lot of people in the FOSS community were hoping it could be used for a privacy-respecting home assistant, Linux speech synthesis that doesn't suck, etc.
After Mozilla abandoned the project, Coqui continued development and had some really impressive one-shot voice cloning, but pivoted to marketing speech synthesis for game developers. They were probably having trouble monetizing it, and it doesn't surprise me that they shut down.
An equivalent project that's still in active development and doing really well is Piper TTS (https://github.com/rhasspy/piper).
-
What self hosted app do you wish existed?
An RSS reader that integrates TTS (or TTS)
-
Audio Converter! How to write one in c/c++?
My solution would be to use a speech synthesis library, maybe eSpeak or Festival, just for ease of use; I think they each provide a library that you could use from C or C++ easily. This one from Mozilla is a more modern system with better-quality output, but it looks like it's set up to run through Python, and I haven't looked at it closely enough to see how much work it would be to get it working for you.
-
Web Speech API is (still) broken on Linux circa 2023
There is a lot of TTS and SST development going on (https://github.com/mozilla/TTS; https://github.com/mozilla/DeepSpeech; https://github.com/common-voice/common-voice). That is the only way they work: Contributions from the wild.
-
[P] Balacoon: free-to-use text-to-speech
unfortunately not yet. I need to expand the library of languages and voices. looking around, it seems only Coqui had some traction re Brazilian Portuguese: https://github.com/mozilla/TTS/issues/160. If you foresee wide adoption of the tech for this locale, hit me up with DM
-
Text to speech free
I haven't used it, but there's also mozilla/TTS.
-
Does anyone know how to set up Mozilla TTS to work with firefox's reader view?
Mozilla TTS
- Conteúdo removido do rb que fiz sobre a destruição do Rio Doce 853KM de rio pela Vale e BHP Billings
-
[D] Looking for someone to do a small coding job
Instead, just use Firefox's open-source TTS model: https://github.com/mozilla/TTS
What are some alternatives?
Practical_RL - A course in reinforcement learning in the wild
Real-Time-Voice-Cloning - Clone a voice in 5 seconds to generate arbitrary speech in real-time
NYU-DLSP20 - NYU Deep Learning Spring 2020
TensorFlowTTS - :stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
Made-With-ML - Learn how to design, develop, deploy and iterate on production-grade ML applications.
STT - 🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.
ffcv - FFCV: Fast Forward Computer Vision (and other ML workloads!)
DeepSpeech - DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
fastai - The fastai deep learning library
NeMo - A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
ModelNet40-C - Repo for "Benchmarking Robustness of 3D Point Cloud Recognition against Common Corruptions" https://arxiv.org/abs/2201.12296
TTS - 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production