Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -3,17 +3,18 @@ base_model: openai/whisper-tiny.en
|
|
| 3 |
library_name: transformers.js
|
| 4 |
---
|
| 5 |
|
|
|
|
| 6 |
# Whisper
|
| 7 |
|
| 8 |
[openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) with ONNX weights to be compatible with [Transformers.js](https://huggingface.co/docs/transformers.js).
|
| 9 |
|
| 10 |
-
## Usage (Transformers.js)
|
| 11 |
-
|
| 12 |
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:
|
| 13 |
```bash
|
| 14 |
npm i @huggingface/transformers
|
| 15 |
```
|
| 16 |
|
|
|
|
|
|
|
| 17 |
**Example:** Transcribe English.
|
| 18 |
|
| 19 |
```js
|
|
@@ -21,7 +22,7 @@ import { pipeline } from '@huggingface/transformers';
|
|
| 21 |
|
| 22 |
// Create speech recognition pipeline
|
| 23 |
const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/whisper-tiny.en', {
|
| 24 |
-
dtype: 'fp32'
|
| 25 |
});
|
| 26 |
|
| 27 |
// Transcribe audio from URL
|
|
@@ -37,7 +38,7 @@ import { pipeline } from '@huggingface/transformers';
|
|
| 37 |
|
| 38 |
// Create speech recognition pipeline
|
| 39 |
const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/whisper-tiny.en', {
|
| 40 |
-
dtype: 'fp32'
|
| 41 |
});
|
| 42 |
|
| 43 |
// Transcribe audio from URL with timestamps
|
|
@@ -59,7 +60,7 @@ import { pipeline } from '@huggingface/transformers';
|
|
| 59 |
|
| 60 |
// Create speech recognition pipeline
|
| 61 |
const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/whisper-tiny.en', {
|
| 62 |
-
dtype: 'fp32'
|
| 63 |
});
|
| 64 |
|
| 65 |
// Transcribe audio from URL with word-level timestamps
|
|
|
|
| 3 |
library_name: transformers.js
|
| 4 |
---
|
| 5 |
|
| 6 |
+
|
| 7 |
# Whisper
|
| 8 |
|
| 9 |
[openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) with ONNX weights to be compatible with [Transformers.js](https://huggingface.co/docs/transformers.js).
|
| 10 |
|
|
|
|
|
|
|
| 11 |
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:
|
| 12 |
```bash
|
| 13 |
npm i @huggingface/transformers
|
| 14 |
```
|
| 15 |
|
| 16 |
+
## Usage (Transformers.js)
|
| 17 |
+
|
| 18 |
**Example:** Transcribe English.
|
| 19 |
|
| 20 |
```js
|
|
|
|
| 22 |
|
| 23 |
// Create speech recognition pipeline
|
| 24 |
const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/whisper-tiny.en', {
|
| 25 |
+
dtype: 'fp32' // Options: "fp32", "fp16", "q8", "q4"
|
| 26 |
});
|
| 27 |
|
| 28 |
// Transcribe audio from URL
|
|
|
|
| 38 |
|
| 39 |
// Create speech recognition pipeline
|
| 40 |
const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/whisper-tiny.en', {
|
| 41 |
+
dtype: 'fp32' // Options: "fp32", "fp16", "q8", "q4"
|
| 42 |
});
|
| 43 |
|
| 44 |
// Transcribe audio from URL with timestamps
|
|
|
|
| 60 |
|
| 61 |
// Create speech recognition pipeline
|
| 62 |
const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/whisper-tiny.en', {
|
| 63 |
+
dtype: 'fp32' // Options: "fp32", "fp16", "q8", "q4"
|
| 64 |
});
|
| 65 |
|
| 66 |
// Transcribe audio from URL with word-level timestamps
|