| base_model: openai/whisper-tiny | |
| library_name: transformers.js | |
| https://huggingface.co/openai/whisper-tiny with ONNX weights to be compatible with Transformers.js. | |
| If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using: | |
| ```bash | |
| npm i @huggingface/transformers | |
| ``` | |
| ```js | |
| import { pipeline } from '@huggingface/transformers'; | |
| // Create the pipeline | |
| const pipe = await pipeline('automatic-speech-recognition', 'whitphx/test-transformersjs-whisper-tiny', { | |
| dtype: 'fp32', // Options: "fp32", "fp16", "q8", "q4" | |
| }); | |
| // Use the model | |
| const result = await pipe('input text or data'); | |
| console.log(result); | |
| ``` | |
| Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`). |