Readit NewsLow Latency: WebCodecs and Streams enable real-time video processing with low latency, which is essential for applications like video conferencing, gaming, and live streaming. With low latency, users can experience a smooth and responsive interaction with the video content.
Customization: Real-time video processing with WebCodecs and Streams allows for customization of the video processing pipeline. Developers can modify and optimize the processing steps to fit the specific needs of their application, such as reducing bandwidth usage or improving video quality.
Performance: WebCodecs and Streams leverage hardware acceleration to achieve better performance than traditional software-based processing. This means that real-time video processing can be done more efficiently and with lower CPU usage, resulting in a smoother and more responsive experience for users.
Accessibility: WebCodecs and Streams are built on top of web technologies like JavaScript, HTML, and CSS, making them accessible to a wide range of developers. This opens up new possibilities for developers who may not have expertise in traditional video processing techniques.
Thanks for the share!
Thanks so much to everyone for sharing! It's awesome to see the positive feedback from the community. As you'll see from the demo, everything runs inside the browser!
As of 2023/03/16, the library supports BERT, ALBERT, DistilBERT, T5, T5v1.1, FLAN-T5, GPT2, BART, CodeGen, Whisper, CLIP, Vision Transformer, and VisionEncoderDecoder models, for a variety of tasks including: masked language modelling, text classification, text-to-text generation, translation, summarization, question answering, text generation, automatic speech recognition, image classification, zero-shot image classification, and image-to-text. Of course, we plan to add many more models and tasks in the near future!
Try out some of the other models/tasks from the "Task" dropdown (like the code-completion or speech-to-text demos).
---
To respond to some comments about poor translation/generation quality, many of the models are actually quite old (e.g., T5 is from 2020)... and if you run the same prompt through the PyTorch version of the model, you will get similar outputs. The purpose of the library/project is to bring these models to the browser; we didn't train the models, so, poor quality can (mostly) be blamed on the original model.
Also, be sure to play around with the generation parameters... as with many LLMs, generation parameters matter a lot.
---
If you want to keep up-to-date with the development, check us out on twitter: https://twitter.com/xenovacom :)
Dead Comment
Dead Comment