Move Transformers.js-compatible version to separate repo (#5)
Browse files- Move Transformers.js-compatible version to separate repo (cd3da4a54110bfdc7cbe0b875ddc16a7c7f60aed)
Co-authored-by: Joshua <Xenova@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -6,7 +6,6 @@ library_name: transformers
|
|
| 6 |
tags:
|
| 7 |
- audio
|
| 8 |
- automatic-speech-recognition
|
| 9 |
-
- transformers.js
|
| 10 |
widget:
|
| 11 |
- example_title: LibriSpeech sample 1
|
| 12 |
src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
|
|
@@ -621,34 +620,6 @@ print(result["text"])
|
|
| 621 |
The Distil-Whisper model can also be used with the OpenAI Whisper CLI. Refer to the [following instructions](https://huggingface.co/distil-whisper/distil-large-v3.5-openai#cli-usage)
|
| 622 |
for details.
|
| 623 |
|
| 624 |
-
### Transformers.js
|
| 625 |
-
|
| 626 |
-
Distil-Whisper can be run completely in your web browser with [Transformers.js](http://github.com/xenova/transformers.js):
|
| 627 |
-
|
| 628 |
-
1. Install Transformers.js from [NPM](https://www.npmjs.com/package/@xenova/transformers):
|
| 629 |
-
|
| 630 |
-
```bash
|
| 631 |
-
npm i @xenova/transformers
|
| 632 |
-
```
|
| 633 |
-
|
| 634 |
-
2. Import the library and perform inference with the pipeline API.
|
| 635 |
-
|
| 636 |
-
```js
|
| 637 |
-
import { pipeline } from '@xenova/transformers';
|
| 638 |
-
|
| 639 |
-
const transcriber = await pipeline('automatic-speech-recognition', 'distil-whisper/distil-large-v3');
|
| 640 |
-
|
| 641 |
-
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';
|
| 642 |
-
const output = await transcriber(url);
|
| 643 |
-
// { text: " And so, my fellow Americans, ask not what your country can do for you. Ask what you can do for your country." }
|
| 644 |
-
```
|
| 645 |
-
|
| 646 |
-
Check out the online [Distil-Whisper Web Demo](https://huggingface.co/spaces/Xenova/distil-whisper-web) to try it out yourself.
|
| 647 |
-
As you'll see, it runs locally in your browser: no server required!
|
| 648 |
-
|
| 649 |
-
Refer to the Transformers.js [docs](https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.AutomaticSpeechRecognitionPipeline)
|
| 650 |
-
for further information.
|
| 651 |
-
|
| 652 |
### Candle
|
| 653 |
|
| 654 |
Through an integration with Hugging Face [Candle](https://github.com/huggingface/candle/tree/main) 🕯️, Distil-Whisper is
|
|
|
|
| 6 |
tags:
|
| 7 |
- audio
|
| 8 |
- automatic-speech-recognition
|
|
|
|
| 9 |
widget:
|
| 10 |
- example_title: LibriSpeech sample 1
|
| 11 |
src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
|
|
|
|
| 620 |
The Distil-Whisper model can also be used with the OpenAI Whisper CLI. Refer to the [following instructions](https://huggingface.co/distil-whisper/distil-large-v3.5-openai#cli-usage)
|
| 621 |
for details.
|
| 622 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 623 |
### Candle
|
| 624 |
|
| 625 |
Through an integration with Hugging Face [Candle](https://github.com/huggingface/candle/tree/main) 🕯️, Distil-Whisper is
|