https://github.com/lostbeard/spawndev.blazorjs.transformersjs
Use Transformers.js from Blazor WebAssembly to run pretrained models with the ONNX Runtime in the browser.
https://github.com/lostbeard/spawndev.blazorjs.transformersjs
blazor blazor-webassembly browser deep-learning depth-estimation huggingface huggingface-transformers javascript machine-learning neural-networks onnx pretrained-models tensorflow text-to-speech transformers
Last synced: 7 months ago
JSON representation
Use Transformers.js from Blazor WebAssembly to run pretrained models with the ONNX Runtime in the browser.
- Host: GitHub
- URL: https://github.com/lostbeard/spawndev.blazorjs.transformersjs
- Owner: LostBeard
- License: mit
- Created: 2025-01-04T23:26:46.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2025-02-07T17:06:27.000Z (8 months ago)
- Last Synced: 2025-02-17T03:33:36.080Z (8 months ago)
- Topics: blazor, blazor-webassembly, browser, deep-learning, depth-estimation, huggingface, huggingface-transformers, javascript, machine-learning, neural-networks, onnx, pretrained-models, tensorflow, text-to-speech, transformers
- Language: C#
- Homepage: https://lostbeard.github.io/SpawnDev.BlazorJS.TransformersJS/
- Size: 46 MB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
# SpawnDev.BlazorJS.TransformersJS
[](https://www.nuget.org/packages/SpawnDev.BlazorJS.TransformersJS)
#### WIP
This project is a "Work In Progress" and is currently limited. If you are interested in this project, please start an issue to suggest features or areas of interest.
## State-of-the-art Machine Learning for the Web in Blazor WebAssembly
SpawnDev.BlazorJS.TransformersJS brings the awesome Transformers.js library into Blazor WebAssembly apps.
Transformers.js is designed to be functionally equivalent to Hugging Face’s transformers python library, meaning you can run the same pretrained models using a very similar API. These models support common tasks in different modalities, such as:
- 📝 Natural Language Processing: text classification, named entity recognition, question answering, language modeling, summarization, translation, multiple choice, and text generation.
- 🖼️ Computer Vision: image classification, object detection, segmentation, and depth estimation.
- 🗣️ Audio: automatic speech recognition, audio classification, and text-to-speech.
- 🐙 Multimodal: embeddings, zero-shot audio classification, zero-shot image classification, and zero-shot object detection.
Transformers.js uses ONNX Runtime to run models in the browser. The best part about it, is that you can easily convert your pretrained PyTorch, TensorFlow, or JAX models to ONNX using 🤗 Optimum.
### Demo
The current demo app uses Transformers.js, Blazor, and WebGL.
NOTE: The models used can be large. A fast connection is recommended.
[Live Demo](https://lostbeard.github.io/SpawnDev.BlazorJS.TransformersJS)
[2D to 2D+Z](https://lostbeard.github.io/SpawnDev.BlazorJS.TransformersJS)
[2D to Anaglyph](https://lostbeard.github.io/SpawnDev.BlazorJS.TransformersJS/AnaglyphImageDemo)
[Text To Speech](https://lostbeard.github.io/SpawnDev.BlazorJS.TransformersJS/TextToSpeechClient)
[Keypoint Detection](https://lostbeard.github.io/SpawnDev.BlazorJS.TransformersJS/KeypointDetectionDemo)